Determining spatial-temporal informative patterns for users and devices in data networks

Patent metadata

Field	Value
Publication number	US-12107741-B2
Application number	US-202117453404-A
Country	US
Kind code	B2
Filing date	Nov 3, 2021
Priority date	Nov 3, 2021
Publication date	Oct 1, 2024
Grant date	Oct 1, 2024

Abstract

Spatial-temporal informative patterns for users and devices associated with data networks can be predicted or determined. An information management component (IMC) can analyze respective groups of items of data stored in respective formats in respective databases. Some items of data can comprise respective signal measurement data representative of respective signal measurements associated with respective devices associated with a communication network. Based on the analysis results, IMC can determine a spatial-temporal pattern(s) associated with the respective groups of items of data, wherein the spatial-temporal pattern(s) can relate to a subject of interest. The IMC can utilize artificial intelligence and/or machine learning algorithms and models to facilitate determining the spatial-temporal pattern(s). In response to a query relating to the subject of interest, the IMC can provide information relating to the subject of interest and responsive to the query based on the spatial-temporal pattern(s).

First claim

What is claimed is:

1. A method, comprising:
analyzing, by a system comprising a processor, a first group of items of data that was stored in a first format in a first data store and a second group of items of data that was stored in a second format in a second data store, wherein the second group of items of data comprises respective signal measurement data representative of respective signal measurements associated with respective devices associated with network equipment that is part of a communication network, wherein the analyzing comprises performing an analysis using an artificial intelligence or machine learning model on the first group of items of data and the second group of items of data; and
based on a result of the analyzing, determining, by the system, a spatial-temporal pattern associated with the first group of items of data and the second group of items of data, wherein the spatial-temporal pattern relates to a subject of interest, wherein the determining the spatial-temporal pattern comprises predicting, by the system, to a defined probability level, the spatial-temporal pattern associated with the first group of items of data and the second group of items of data based on the artificial intelligence or machine learning model.

2. The method of claim 1 , wherein the first data store is a relational data store that stores the first group of items of data in the first format that is associated with a relational structure, wherein the second data store is a non-relational data store that stores the second group of items of data in the second format that is associated with a non-relational structure, and wherein the non-relational data store comprises a graph data store.

3. The method of claim 1 , wherein the first data store is associated with an internal data source, and wherein the second data store is associated with an external data source and is accessed via a device that is external to the system and associated with an external identity.

4. The method of claim 1 , further comprising:
receiving, by the system, search query data representative of a search query, the search query data being in a third format, and the search query relating to the subject of interest;
converting, by the system, the search query data from the third format to generate first modified search query data in the first format associated with the first data store;
querying, by the system, the first data store for first responsive information that is responsive to the search query based on the first modified search query data, wherein the first responsive information comprises or relates to the first group of items of data;
converting, by the system, the search query data from the third format to generate second modified search query data in the second format associated with the second data store; and
querying, by the system, the second data store for second responsive information that is responsive to the search query based on the second modified search query data, wherein the second responsive information comprises or relates to the second group of items of data.

5. The method of claim 1 , wherein the method further comprises:
training, by the system, the artificial intelligence or machine learning model based on the artificial intelligence or machine learning analysis and the first group of items of data and the second group of items of data input to the artificial intelligence or machine learning model.

6. The method of claim 5 , wherein the defined probability level is a first defined probability level, and wherein the method further comprises:
based on the artificial intelligence or machine learning model and the performing of the artificial intelligence or machine learning analysis on the first group of items of data and the second group of items of data, predicting, by the system, to a second defined probability level, relationships between a first portion of the first group of items of data and a second portion of the second group of items of data; and
clustering, by the system, the first portion of the first group of items of data and the second portion of the second group of items of data to form a cluster.

7. The method of claim 1 , wherein the first group of items of data or the second group of items of data comprises the respective signal measurement data representative of the respective signal measurements associated with the respective devices associated with the network equipment associated with the communication network, and wherein the method further comprises:
estimating, by the system, respective locations of the respective devices based on the spatial-temporal pattern.

8. The method of claim 1 , wherein the first group of items of data or the second group of items of data comprises respective performance indicator data representative of respective performance indicators associated with respective devices associated with a communication network, comprising network equipment, and wherein the method further comprises:
based on the spatial-temporal pattern, detecting, by the system, a geographical area that is associated with a performance level relating to provision of device communication-related services that does not satisfy a defined minimum threshold performance level relating to the provision of the device communication-related services, wherein the geographical area is associated with a portion of the respective devices; and
determining, by the system, a cause of the performance level relating to the provision of the device communication-related services not satisfying the defined minimum threshold performance level.

9. The method of claim 1 , wherein the first group of items of data or the second group of items of data comprise performance data and usage data, wherein the performance data relates to respective performances of respective devices, comprising a first device of a first device type and a second device of a second device type, in respective geographical regions, comprising a first geographical region and a second geographical region, wherein the usage data relates to geographical locations where a third device associated with a user identity is determined to have been located, and wherein the method further comprises:
based on the spatial-temporal pattern:
determining, by the system, that the third device associated with the user identity has been located in the first geographical region more than the second geographical region;
determining, by the system, that, in the first geographical region, the first device of the first device type performs better than the second device of the second device type; and
presenting, by the system, visual data that indicates that the first device of the first device type performs better than the second device of the second device type in the first geographical region.

10. The method of claim 1 , wherein the first group of items of data and the second group of items of data comprise information relating to respective data traffic associated with respective devices and respective interactions between the respective devices, wherein the respective devices comprise network equipment associated with a communication network,
wherein the determining of the spatial-temporal pattern comprises determining an aggressive or malicious spatial-temporal pattern associated with a portion of the respective devices based on the respective interactions between the respective devices, and wherein the aggressive or malicious spatial-temporal pattern indicates that the portion of the respective devices is acting in an aggressive or malicious manner against the network equipment, based on an aggressive or malicious device criterion.

11. The method o

Assignees

• At & T Ip I Lp

Inventors

• Malboubi Mehdi
• Jiang Baofeng
• Zheng Yuhong

Classifications

• H04L43/045

  for graphical visualisation of monitoring data · CPC title

• G05B19/0425

  Safety, monitoring · CPC title

• G05B23/0289

  Reconfiguration to prevent failure, e.g. usually as a reaction to incipient failure detection · CPC title

• H04L41/16

  using machine learning or artificial intelligence · CPC title

• G06N20/00

  Machine learning · CPC title