CN-121984831-A - Data processing method and device and electronic equipment

CN121984831ACN 121984831 ACN121984831 ACN 121984831ACN-121984831-A

Abstract

The embodiment of the invention discloses a data processing method, a device and electronic equipment, wherein the method comprises the steps of responding to a data fusion request initiated aiming at a target application scene, obtaining historical fusion fault data in the target application scene, analyzing the historical fusion fault data in the target application scene, determining resource availability corresponding to the historical fusion fault data, constructing a candidate system group set and a candidate resource group set in the target application scene based on the determined resource availability, planning a fusion path for each candidate system group based on the fault probability predicted for each candidate system group to form a fusion path set, selecting a target resource group from the candidate resource group set based on the fault prediction result of the multi-mode data after the multi-mode data to be fused is obtained, fusing the multi-mode data to be fused based on the target fusion path and the target resource group, and outputting the fusion result.

Inventors

LI WENSI
ZHENG HAIPENG
LI HAICHUAN
XIE QIN
GUO XUANJIANG

Assignees

中国移动(浙江)创新研究院有限公司
中国移动通信集团浙江有限公司
中国移动通信集团有限公司
浙江移动数智科技有限公司
中国移动通信集团江苏有限公司
中国移动通信集团四川有限公司

Dates

Publication Date: 20260505
Application Date: 20251215

Claims (10)

1. A method of data processing, the method comprising: Receiving a data fusion request initiated for a target application scene; responding to the data fusion request, acquiring historical fusion fault data in the target application scene, and determining the resource availability corresponding to the historical fusion fault data; Constructing a candidate system group set and a candidate resource group set in the target application scene based on the resource availability corresponding to the historical fusion fault data, determining the fault probability corresponding to each candidate system group in the candidate system group set, and planning a fusion path for each candidate system group based on the fault probability to form a fusion path set; Acquiring multi-mode data to be fused in the target application scene, and performing fault prediction on the multi-mode data to obtain a fault prediction result of the multi-mode data; and selecting a target fusion path corresponding to the multi-mode data from the fusion path set based on the fault prediction result, selecting a target resource set corresponding to the multi-mode data from the candidate resource set, fusing the multi-mode data to be fused based on the target fusion path and the target resource set, and outputting a fusion result.
2. The method of claim 1, wherein constructing the set of candidate system groups and the set of candidate resource groups in the target application scenario based on the resource availability comprises: Determining an influence association degree under the target application scene based on the historical fusion fault data and the resource availability, wherein the influence association degree is used for representing an association relation between a fault type and the resource availability; selecting a plurality of candidate systems from application systems associated with the target application scene based on the resource availability corresponding to the historical fusion fault data; Based on the influence relevance and a preset resource threshold, allocating resources in a plurality of candidate systems to obtain a plurality of resource combinations so as to construct a candidate resource group set in the target application scene; And obtaining a plurality of candidate system groups based on the plurality of candidate resource groups and the association relation between the candidate resources and the candidate systems so as to construct a candidate system group set in the target application scene.
3. The method of claim 2, wherein determining the impact association in the target application scenario based on the historical fusion failure data comprises: Determining a historical effect value of data fusion according to the resource availability of the historical fusion result and the historical fusion fault data; Acquiring an ideal effect value of data fusion, and calculating an effect difference value between the ideal effect value and the historical effect value; and determining the influence association degree for representing the association relation between the fault type and the resource availability based on the effect difference value, the historical fusion fault data and the resource availability.
4. The method of claim 1, wherein planning a fused path for each candidate system group based on the probability of failure to form a fused path set comprises: Determining other fault types associated with each fault type based on the influence relation among different fault types in the fault probability set corresponding to the candidate system group; determining the fault types associated with other fault types as a first fault type, and determining the fault types not associated with other fault types as a second fault type, so as to obtain a first fault type set and a second fault type set corresponding to the candidate system group; based on the first fault type set and the second fault type set corresponding to each candidate system group, sequencing the candidate system groups according to the fault probability corresponding to each fault type to obtain a first fault system group set or a second fault system group set corresponding to each fault type; Determining the transmission distance corresponding to each candidate system group, and constructing a system group distance set containing the transmission distances corresponding to a plurality of candidate system groups; and planning a fusion path for each candidate system group according to the system group distance set, the first fault system group set and the second fault system group set to form a fusion path set.
5. The method according to claim 1, wherein selecting the target resource group corresponding to the multi-modal data from the candidate resource group set based on the failure prediction result comprises: Cutting the multi-mode data according to the fault prediction result to obtain a data segment set; recombining the data segments in the data segment set to obtain at least one combined data segment, and constructing a combined data segment length set based on the data segment length corresponding to the at least one combined data segment; Based on the fusion path set, sorting the candidate resource groups in the candidate resource group set to obtain a candidate resource group sorting set, and setting a resource occupation ratio critical threshold according to the candidate resource group sorting set; and selecting a target resource group for each combined data segment from the candidate resource group set according to the resource duty ratio critical threshold and the data segment lengths contained in the data segment length set, and taking the target resource group selected for the at least one combined data segment as the target resource group corresponding to the multi-mode data.
6. The method according to claim 1, wherein the fusing the multimodal data to be fused based on the target fusion path and the target resource group, and outputting a fusion result, includes: marking the key data area, the front auxiliary verification data area and the rear auxiliary verification data area of the multi-mode data, and outputting three data area marking result sets; and fusing the multi-mode data to be fused based on the target fusion path, the target resource group and the three data area marking result sets, and outputting a fusion result.
7. A data processing apparatus, the apparatus comprising: The analysis module is used for receiving a data fusion request initiated aiming at a target application scene, responding to the data fusion request, acquiring historical fusion fault data in the target application scene, and determining the resource availability corresponding to the historical fusion fault data; The processing module is used for constructing a candidate system group set and a candidate resource group set in the target application scene based on the resource utilization degree corresponding to the historical fusion fault data, determining the fault probability corresponding to each candidate system group in the candidate system group set, and planning a fusion path for each candidate system group based on the fault probability to form a fusion path set; the prediction module is used for acquiring multi-mode data to be fused in the target application scene, and performing fault prediction on the multi-mode data to obtain a fault prediction result of the multi-mode data; The matching module is used for selecting a target fusion path corresponding to the multi-mode data from the fusion path set based on the fault prediction result, and selecting a target resource group corresponding to the multi-mode data from the candidate resource group set; And the fusion module is used for fusing the multi-mode data to be fused based on the target fusion path and the target resource group and outputting a fusion result.
8. An electronic device comprising a processor, a memory and a computer program stored on the memory and executable on the processor, which when executed by the processor implements the steps of the data processing method according to any one of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored, which computer program, when being executed by a processor, implements the steps of the data processing method according to any of claims 1 to 6.
10. A computer program product comprising a computer program which, when executed by a processor, implements the steps of the data processing method of any one of claims 1 to 6.

Description

Data processing method and device and electronic equipment Technical Field The present invention relates to the field of computer technologies, and in particular, to a data processing method, a data processing device, and an electronic device. Background The visual network is an intelligent perception and interaction network which is built by taking visual information as a core and through technologies such as the Internet of things and 5G. The multiple scenes and the complex demands of the view network make the data of a single mode already unable to meet the sensing demands under the complex environment, for example, the data of the automatic driving scene is difficult to cope with heavy rain or strong light interference. Therefore, the method and the system have the advantages that the limitation of a single mode is broken through by integrating data of different modes, and the perception, understanding and decision making capability of the system on complex environments is improved. At present, only simple data splicing is performed on the multi-mode data, deep fusion of the multi-mode data cannot be achieved, the fused multi-mode data cannot be subjected to deep adaptation to scene requirements, and the fusion effect of the multi-mode data is poor. Therefore, a technical solution capable of effectively improving the multi-modal data fusion effect is needed. Disclosure of Invention The embodiment of the invention aims to provide a technical scheme capable of improving the fusion effect of multi-mode data. In order to solve the technical problems, the embodiment of the invention is realized as follows: in a first aspect, an embodiment of the present invention provides a data processing method, where the method includes: Receiving a data fusion request initiated for a target application scene; responding to the data fusion request, acquiring historical fusion fault data in the target application scene, and determining the resource availability corresponding to the historical fusion fault data; Constructing a candidate system group set and a candidate resource group set in the target application scene based on the resource availability corresponding to the historical fusion fault data, determining the fault probability corresponding to each candidate system group in the candidate system group set, and planning a fusion path for each candidate system group based on the fault probability to form a fusion path set; Acquiring multi-mode data to be fused in the target application scene, and performing fault prediction on the multi-mode data to obtain a fault prediction result of the multi-mode data; and selecting a target fusion path corresponding to the multi-mode data from the fusion path set based on the fault prediction result, selecting a target resource set corresponding to the multi-mode data from the candidate resource set, fusing the multi-mode data to be fused based on the target fusion path and the target resource set, and outputting a fusion result. In a second aspect, an embodiment of the present invention provides a data processing apparatus, including: The analysis module is used for receiving a data fusion request initiated aiming at a target application scene, responding to the data fusion request, acquiring historical fusion fault data in the target application scene, and determining the resource availability corresponding to the historical fusion fault data; The processing module is used for constructing a candidate system group set and a candidate resource group set in the target application scene based on the resource utilization degree corresponding to the historical fusion fault data, determining the fault probability corresponding to each candidate system group in the candidate system group set, and planning a fusion path for each candidate system group based on the fault probability to form a fusion path set; the prediction module is used for acquiring multi-mode data to be fused in the target application scene, and performing fault prediction on the multi-mode data to obtain a fault prediction result of the multi-mode data; And the fusion module is used for selecting a target fusion path corresponding to the multi-mode data from the fusion path set based on the fault prediction result, selecting a target resource group corresponding to the multi-mode data from the candidate resource group set, fusing the multi-mode data to be fused based on the target fusion path and the target resource group, and outputting a fusion result. In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a memory, and a computer program stored on the memory and executable on the processor, where the computer program when executed by the processor implements the steps of the data processing method provided in the foregoing embodiment. In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having stored thereo