CN-122027016-A - Sample generation method, device, computer equipment, storage medium and product

CN122027016ACN 122027016 ACN122027016 ACN 122027016ACN-122027016-A

Abstract

The present application relates to the field of communications technologies, and in particular, to a sample generating method, apparatus, computer device, storage medium, and product. The method comprises the steps of receiving sample light path data of a light path simulated by a generator, determining a target light path attenuation coefficient of the light path according to the sample light path data, carrying out confidence analysis on the sample light path data according to the target light path attenuation coefficient to obtain confidence probability corresponding to the sample light path data, and sending the sample light path data and the confidence probability corresponding to the sample light path data to the generator so that the generator can adjust the sample light path data of the light path according to the sample light path data and the confidence probability to enable the confidence probability of the adjusted sample light path data to be close to a standard value.

Inventors

GAO XIA
QIN XIN
DING YI
GU ZHIQUN
LI JIE

Assignees

中国电信股份有限公司技术创新中心
中国电信股份有限公司
北京邮电大学

Dates

Publication Date: 20260512
Application Date: 20251031

Claims (10)

1. A method of sample generation, the method comprising: receiving sample light path data of a light path simulated by a generator; Determining a target optical path attenuation coefficient of the optical path according to the sample optical path data; Performing confidence analysis on the sample light path data according to the target light path attenuation coefficient to obtain a confidence probability corresponding to the sample light path data; And sending the sample light path data and the confidence probability corresponding to the sample light path data to the generator, so that the generator adjusts the sample light path data of the light path according to the sample light path data and the confidence probability, and the confidence probability of the adjusted sample light path data is close to a standard value.
2. The method of claim 1, wherein said determining a target path attenuation coefficient for said optical path from said sample optical path data comprises: acquiring target transmission quality data of the optical path at the time of generating the sample optical path data; and carrying out optical path attenuation analysis on the optical path according to the target transmission quality data to obtain a target optical path attenuation coefficient corresponding to the sample optical path data.
3. The method according to claim 2, wherein the performing optical path attenuation analysis on the optical path according to the target transmission quality data to obtain a target optical path attenuation coefficient corresponding to the sample optical path data includes: and determining a target optical path attenuation coefficient matched with the target transmission quality data based on the corresponding relation between the different transmission quality data and the optical path attenuation coefficient.
4. The method according to claim 1, wherein the performing confidence analysis on the sample optical path data according to the target optical path attenuation coefficient to obtain a confidence probability corresponding to the sample optical path data includes: Determining a real light path attenuation coefficient and a tolerance error corresponding to the sample light path data; And carrying out confidence analysis on the sample light path data according to the target light path attenuation coefficient, the real light path attenuation coefficient and the tolerance error to obtain the confidence probability corresponding to the sample light path data.
5. The method of claim 4, wherein performing a confidence analysis on the sample optical path data according to the target optical path attenuation coefficient, the real optical path attenuation coefficient, and the tolerance error to obtain a confidence probability corresponding to the sample optical path data, comprises: determining the probability attenuation speed corresponding to the tolerance error; Determining a difference value operation result of the target light path attenuation coefficient and the real light path attenuation coefficient; And determining the confidence probability corresponding to the sample light path data according to the ratio between the difference operation result and the attenuation speed.
6. The method of any of claims 1-5, wherein the sample optical path data is data output by the generator based on random noise.
7. A sample generation device, the device comprising: the receiving module is used for receiving sample light path data of the light path simulated by the generator; the determining module is used for determining a target light path attenuation coefficient of the light path according to the sample light path data; The analysis module is used for carrying out confidence analysis on the sample light path data according to the target light path attenuation coefficient to obtain a confidence probability corresponding to the sample light path data; And the sending module is used for sending the sample light path data and the confidence probability corresponding to the sample light path data to the generator so that the generator can adjust the sample light path data of the light path according to the sample light path data and the confidence probability, and the confidence probability of the adjusted sample light path data is close to a standard value.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.

Description

Sample generation method, device, computer equipment, storage medium and product Technical Field The present application relates to the field of communications technologies, and in particular, to a sample generating method, apparatus, computer device, storage medium, and product. Background With the continuous evolution of communication technology, the optical access network is gradually developed from a static state to a dynamic state. In order to make full use of physical layer resources and improve the resource utilization efficiency of the network, accurate sensing of the real-time running state of the network is required. In modern optical networks, the application of coherent transmission techniques provides a large number of flexibly configurable parameters for the deployment of optical paths. In order to evaluate in real time whether a given lightpath configuration scheme is valid, optimizing the overall network design, it is important to quickly and accurately estimate the quality of transmission estimate (QoT, quality of Transmission) of the candidate lightpath prior to lightpath deployment. However, in actual optical network deployment, it is difficult to collect enough data for model training due to the small number of optical paths deployed by the early network, lack of monitoring equipment at the network nodes, and so on. Disclosure of Invention In view of the foregoing, it is desirable to provide a sample generation method, apparatus, computer device, storage medium, and product that can collect a sufficient amount of data for model training. In a first aspect, the present application provides a sample generation method. The method comprises the following steps: receiving sample light path data of a light path simulated by a generator; Determining a target optical path attenuation coefficient of the optical path according to the sample optical path data; Performing confidence analysis on the sample light path data according to the target light path attenuation coefficient to obtain a confidence probability corresponding to the sample light path data; And sending the sample light path data and the confidence probability corresponding to the sample light path data to the generator, so that the generator adjusts the sample light path data of the light path according to the sample light path data and the confidence probability, and the confidence probability of the adjusted sample light path data is close to a standard value. In one embodiment, the determining the target optical path attenuation coefficient of the optical path according to the sample optical path data includes: acquiring target transmission quality data of the optical path at the time of generating the sample optical path data; and carrying out optical path attenuation analysis on the optical path according to the target transmission quality data to obtain a target optical path attenuation coefficient corresponding to the sample optical path data. In one embodiment, the performing optical path attenuation analysis on the optical path according to the target transmission quality data to obtain a target optical path attenuation coefficient corresponding to the sample optical path data includes: and determining a target optical path attenuation coefficient matched with the target transmission quality data based on the corresponding relation between the different transmission quality data and the optical path attenuation coefficient. In one embodiment, the performing confidence analysis on the sample optical path data according to the target optical path attenuation coefficient to obtain a confidence probability corresponding to the sample optical path data includes: Determining a real light path attenuation coefficient and a tolerance error corresponding to the sample light path data; And carrying out confidence analysis on the sample light path data according to the target light path attenuation coefficient, the real light path attenuation coefficient and the tolerance error to obtain the confidence probability corresponding to the sample light path data. In one embodiment, the performing confidence analysis on the sample optical path data according to the target optical path attenuation coefficient, the real optical path attenuation coefficient and the tolerance error to obtain a confidence probability corresponding to the sample optical path data includes: determining the probability attenuation speed corresponding to the tolerance error; Determining a difference value operation result of the target light path attenuation coefficient and the real light path attenuation coefficient; And determining the confidence probability corresponding to the sample light path data according to the ratio between the difference operation result and the attenuation speed. In one embodiment, the sample optical path data is data output by the generator according to random noise. In a second aspect, the application further provides a sample generati