CN-121985368-A - Indoor network quality difference positioning method and device and electronic equipment

Abstract

The invention discloses a positioning method, a device and electronic equipment for indoor network quality difference, which are characterized in that a network data source is firstly obtained, then the network data source is subjected to first preprocessing to obtain repair data, then the repair data is subjected to time granularity unification to obtain unified data, then the unified data is subjected to multi-source data aggregation to obtain associated data, the associated data is processed based on a time dimension algorithm to obtain a first causal graph, the associated data is processed based on a static dimension algorithm to obtain a second causal graph, finally a third causal graph is obtained according to the first causal graph and the second causal graph, and the indoor network quality difference is automatically positioned based on the third causal graph, so that human resource waste is avoided.

Inventors

• HU SIMIAO

Assignees

• 中国移动通信集团辽宁有限公司
• 中国移动通信集团有限公司

Dates

Publication Date

20260505

Application Date

20260114

Claims (10)

1. 1. The method for positioning the indoor network quality difference is characterized by comprising the following steps: acquiring a network data source; Performing first preprocessing on the network data source to obtain repair data; Performing time granularity unification treatment on the repair data to obtain unified data; Carrying out multi-source data aggregation on the unified data to obtain associated data; Processing the associated data based on a time dimension algorithm to obtain a first causal graph; Processing the associated data based on a static dimension algorithm to obtain a second causal graph; And obtaining a third causal graph according to the first causal graph and the second causal graph, and positioning indoor network quality difference based on the third causal graph.
2. 2. The method of claim 1, wherein performing multi-source data aggregation on the unified data to obtain associated data comprises: The unified data at least comprises a device ID and a time stamp; The association data is obtained based on the device ID and the timestamp.
3. 3. The method of claim 2, wherein the processing the associated data based on the time dimension algorithm to obtain a first causal graph comprises: And processing the associated data based on No Tears algorithm to obtain a first causal graph.
4. 4. A method according to claim 3, wherein said processing said associated data based on a static dimension algorithm to obtain a second causal graph comprises: and processing the associated data based on TTPM algorithm to obtain a second causal graph.
5. 5. The method of claim 4, wherein locating indoor network quality differences based on the third causal graph comprises: And processing the third causal graph based on a first preset strategy to obtain a final anomaly score and a topology influence coefficient.
6. 6. The method of claim 5, wherein the obtaining the final anomaly score and the topology influencing coefficients comprises: Obtaining edge weights according to the final anomaly scores and the topology influence coefficients; And processing the edge weight based on a preset random walk strategy to obtain root cause probability.
7. 7. The method of claim 6, wherein processing the edge weights based on a preset random walk strategy comprises: The preset random walk strategy at least comprises a first-order random walk and a second-order random walk; generating a next hop probability according to the edge weight; And the second-order random walk is to introduce a history node memory mechanism, and balance the transfer weights of the current node and the previous node through a first preset parameter.
8. 8. The method of claim 7, wherein processing the edge weights based on a preset random walk strategy comprises: Obtaining a directed graph based on the root cause probability and the final anomaly score; and processing the directed graph based on Dijkstra reverse search algorithm to obtain a positioning result.
9. 9. The positioning device is characterized by comprising an acquisition unit, an analysis unit and a processing unit: The acquisition unit is used for acquiring a network data source; The analysis unit is used for carrying out first preprocessing on the network data source to obtain repair data, carrying out time granularity unification processing on the repair data to obtain unified data, carrying out multi-source data convergence on the unified data to obtain associated data, processing the associated data based on a time dimension algorithm to obtain a first causal graph, and processing the associated data based on a static dimension algorithm to obtain a second causal graph; And the processing unit is used for obtaining a third causal graph according to the first causal graph and the second causal graph, and positioning indoor network quality difference based on the third causal graph.
10. 10. An electronic device, comprising: a memory for storing at least one set of instructions; the processor is used for acquiring a network data source; Performing first preprocessing on the network data source to obtain repair data; Performing time granularity unification treatment on the repair data to obtain unified data; Carrying out multi-source data aggregation on the unified data to obtain associated data; Processing the associated data based on a time dimension algorithm to obtain a first causal graph; Processing the associated data based on a static dimension algorithm to obtain a second causal graph; And obtaining a third causal graph according to the first causal graph and the second causal graph, and positioning indoor network quality difference based on the third causal graph.

Description

Indoor network quality difference positioning method and device and electronic equipment Technical Field The embodiment of the application relates to network technology, and relates to a positioning method and device for indoor network quality difference and electronic equipment. Background With the development of society and the progress of the age, networks become living necessities of people, whether the networks are outdoors or indoors, but with the massive use of the networks, indoor network quality difference diagnosis and positioning become very important, judgment is mainly performed through basic performance indexes such as signal strength, time delay and packet loss rate mainly reported by acquisition terminal equipment, but judgment is performed only through the basic performance indexes, so that the accuracy is poor, and the problem of how to accurately perform positioning is an urgent need to be solved. The traditional solution adopts the mode of manual setting and manual layer-by-layer investigation to fix a position, leads to the waste of manpower resources. Disclosure of Invention In view of the above, the embodiments of the present application provide a method, an apparatus, and an electronic device for positioning poor indoor network quality. The technical scheme of the embodiment of the application is realized as follows: the embodiment of the application provides a positioning method for indoor network quality difference, which comprises the steps of obtaining a network data source, carrying out first preprocessing on the network data source to obtain repair data, carrying out time granularity unification on the repair data to obtain unified data, carrying out multi-source data aggregation on the unified data to obtain associated data, processing the associated data based on a time dimension algorithm to obtain a first causal graph, processing the associated data based on a static dimension algorithm to obtain a second causal graph, obtaining a third causal graph according to the first causal graph and the second causal graph, and positioning the indoor network quality difference based on the third causal graph. Optionally, multi-source data aggregation is carried out on the unified data to obtain associated data, wherein the unified data at least comprises an equipment ID and a time stamp, and the associated data is obtained based on the equipment ID and the time stamp. Optionally, the processing the associated data based on the time dimension algorithm to obtain a first causal graph includes processing the associated data based on No Tears algorithm to obtain a first causal graph. Optionally, the processing the associated data based on the static dimension algorithm to obtain a second causal graph includes processing the associated data based on TTPM algorithm to obtain a second causal graph. Optionally, locating the indoor network quality difference based on the third causal graph includes processing the third causal graph based on a first preset strategy to obtain a final anomaly score and a topology influence coefficient. Optionally, after the final anomaly score and the topology influence coefficient are obtained, the method comprises the steps of obtaining edge weights according to the final anomaly score and the topology influence coefficient, and processing the edge weights based on a preset random walk strategy to obtain root cause probability. The method comprises the steps of selecting a first order random walk and a second order random walk, wherein the first order random walk is used for generating a next hop probability according to the edge weight, and the second order random walk is used for introducing a history node memory mechanism and balancing transfer weights of a current node and a previous node through a first preset parameter. Optionally, after the edge weight is processed based on a preset random walk strategy, a directed graph is obtained based on the root cause probability and the final anomaly score, and the directed graph is processed based on a Dijkstra reverse search algorithm to obtain a positioning result. The positioning device comprises an acquisition unit, an analysis unit and a processing unit, wherein the acquisition unit is used for acquiring a network data source, the analysis unit is used for carrying out first preprocessing on the network data source to obtain repair data, carrying out time granularity unification on the repair data to obtain unified data, carrying out multi-source data aggregation on the unified data to obtain associated data, processing the associated data based on a time dimension algorithm to obtain a first causal graph, processing the associated data based on a static dimension algorithm to obtain a second causal graph, and the processing unit is used for obtaining a third causal graph according to the first causal graph and the second causal graph and positioning indoor network quality difference based on the third causal