# US 2026/0089068 A1 · Method for predicting internet of things (iot) data inconsistency

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0089068 A1
- Document ID: US20260089068A1
- Status: Published application
- Kind: A1
- Application number: 19/108,629
- Filed: 2022-09-08
- Published: 2026-03-26
- Earliest claimed: 2022-09-08
- Assignees: Telefonaktiebolaget LM Ericsson (publ)
- Applicants: Telefonaktiebolaget Lm Ericsson (Publ)
- Inventors: Carla MOURADIAN; Mbarka SOUALHIA
- Web page: https://patentgrep.com/patent/US20260089068A1

## CPC

- H04L 41/147: for predicting network behaviour
- G06F 16/906: Clustering; Classification
- G06N 3/045: Combinations of networks
- G06N 3/09: Supervised learning
- H04L 41/16: using machine learning or artificial intelligence
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- H04L 67/12: specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The disclosure relates to a method and apparatus for predicting Internet of Things (IoT) data inconsistency. The method comprises obtaining labelled IoT data, the IoT data being collected from a plurality of IoT devices by a monitoring system. The method comprises analyzing characteristics of the labelled IoT data and identifying features of IoT data inconsistency. The method comprises training, using the labelled IoT devices data and the features of IoT data inconsistency, a ML model to predict the IoT data inconsistency. The method comprises generating, using the labelled IoT data and the features of IoT data inconsistency, a set of inconsistency rules to be applied to live IoT data predicted as inconsistent by the ML model.

## Claims

### Claim 1

A computer implemented method for predicting Internet of Things (IoT) data inconsistency, comprising:
obtaining labelled IoT data, the IoT data being collected from a plurality of IoT devices by a monitoring system;
analyzing characteristics of the labelled IoT data and identifying features of IoT data inconsistency;
training, using the labelled IoT devices data and the features of IoT data inconsistency, a ML model to predict the IoT data inconsistency; and
generating, using the labelled IoT data and the features of IoT data inconsistency, a set of inconsistency rules to be applied to live IoT data predicted as inconsistent by the ML model.

### Claim 2 (depends on 1)

The method of claim 1, wherein the labelled IoT data comprises the IoT data of a plurality of IoT devices and a plurality of features for each of the IoT data including at least one of: a type of IoT data, a type of IoT device, a location of acquisition of the IoT data, a time of acquisition of the IoT data, a destination for the IoT data, a sampling rate of the IoT data, a latency-sensitiveness of the IoT data, a network condition when the IoT data was acquired, and an indication whether the IoT data is consistent or not.

### Claim 3 (depends on 1)

The method of claim 1, wherein analyzing characteristics of the labelled IoT data comprises measuring a degree of correlation between features of the labelled IoT data.

### Claim 4 (depends on 3)

The method of claim 3, wherein the degree of correlation is measured using Spearman's correlation coefficients between the features of the labelled IoT data.

### Claim 5 (depends on 4)

The method of claim 4, wherein the resulting correlation coefficients form a matrix with N rows and N columns; wherein N defines a number of feature elements; wherein values of the matrix indicates a degree of relationship between the feature elements; and wherein the feature elements having a higher degree of relationship with the IoT data inconsistency are selected as the features of IoT data inconsistency.

### Claim 6 (depends on 1)

The method of claim 1 wherein the set of inconsistency rules is further used for refining the IoT data collected from the plurality of IoT devices for continuous training of the ML model.

### Claim 7 (depends on 1)

The method of claim 1, wherein training the ML model comprises training a plurality of ML models to address different types of performance in terms of accuracy, precision, recall and F1-score.

### Claim 8 (depends on 7)

The method of claim 7, wherein the plurality of ML models is selected among Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN).

### Claim 9 (depends on 1)

The method of claim 1, further comprising performing data inconsistency prediction on live IoT data, using the ML model.

### Claim 10 (depends on 9)

The method of claim 9, further comprising, if a data inconsistency of live IoT data is predicted, generating refinement actions using the set of inconsistency rules.

### Claim 11 (depends on 10)

The method of claim 10, further comprising using the refinement actions to guide live data collection to avoid future inconsistencies.

### Claim 12 (depends on 1)

The method of claim 1, further comprising, performing a data inconsistency verification on live IoT data, using the ML model and information in the labeled IoT data.

### Claim 13 (depends on 12)

The method of claim 12, further comprising, if a data inconsistency is verified, generating a resolution action using the set of inconsistency rules, to fix the IoT data inconsistency.

### Claim 14

An apparatus for predicting Internet of Things (IoT) data inconsistency comprising processing circuits and a memory, the memory containing instructions executable by the processing circuits whereby the apparatus is operative to:
obtain labelled IoT data, the IoT data being collected from a plurality of IoT devices by a monitoring system;
analyze characteristics of the labelled IoT data and identify features of IoT data inconsistency;
train, using the labelled IoT devices data and the features of IoT data inconsistency, a ML model to predict IoT data inconsistency; and
generate, using the labelled IoT data and the features of IoT data inconsistency, a set of inconsistency rules to be applied to live IoT data predicted as inconsistent by the ML model.

### Claim 15 (depends on 14)

The apparatus of claim 14, wherein the apparatus is a data inconsistency resolution system.

### Claim 16 (depends on 14)

The apparatus of claim 14, wherein the apparatus is an IoT gateway.

### Claim 17

(canceled)

### Claim 18

A non-transitory computer readable media having stored thereon instructions for predicting Internet of Things (IoT) data inconsistency, the instructions comprising:
obtaining labelled IoT data, the IoT data being collected from a plurality of IoT devices by a monitoring system;
analyzing characteristics of the labelled IoT data and identifying features of IoT data inconsistency;
training, using the labelled IoT devices data and the features of IoT data inconsistency, a ML model to predict the IoT data inconsistency; and
generating, using the labelled IoT data and the features of IoT data inconsistency, a set of inconsistency rules to be applied to live IoT data predicted as inconsistent by the ML model.
