# US 2023/0156450 A1 · Wireless device detection systems and methods incorporating streaming survival modeling for discrete rotating identifier data

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

- Number: US 2023/0156450 A1
- Document ID: US20230156450A1
- Status: Published application
- Kind: A1
- Application number: 17/975,443
- Filed: 2022-10-27
- Published: 2023-05-18
- Earliest claimed: 2020-10-16
- Assignees: Ubiety Technologies, Inc.
- Applicants: Ubiety Technologies, Inc.
- Inventors: Mark Hoffmann
- Web page: https://patentgrep.com/patent/US20230156450A1

## CPC

- H04W 8/005: {Discovery of network devices, e.g. terminals}
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- H04W 12/02: Protecting privacy or anonymity, e.g. protecting personally identifiable information [PII]
- H04W 12/122: Counter-measures against attacks; Protection against rogue devices
- H04W 12/75: Temporary identity
- H04W 8/26: Network addressing or numbering for mobility support
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A wireless device detection system can include processors, memory devices, and sensors to receive temporary identifiers transmitted between a base station and a mobile wireless device. The memory devices include instructions that cause the processors to build a cumulative distribution function for survival probability based on delta times between multiple access events for each of multiple temporary identifiers received from the sensors. In response to a new access event, the processors add a corresponding temporary identifier to a streaming list and assign a survival probability value, based on the cumulative distribution function, to a latest access event for each temporary identifier contained in the streaming list. The processors remove temporary identifiers from the streaming list that have a survival probability value less than a threshold value, compare the number of temporary identifiers contained in the streaming list to a number of devices known to be present, and calculate the probability that a device corresponding to each of the temporary identifiers contained in the streaming list is present.

## Claims

### Claim at position 1

1-18. (canceled)

### Claim 19

A wireless device detection system, comprising:
one or more sensors configured to receive temporary identifiers transmitted between a base station and a mobile wireless device;
one or more processors; and
one or more memory devices having stored thereon instructions that when executed by the one or more processors cause the one or more processors to:
build a cumulative distribution function for survival probability based on delta times between a plurality of access events for each of a plurality of temporary identifiers received from the one or more sensors;
in response to a new access event, add a corresponding temporary identifier to a streaming list and assign a survival probability value, based on the cumulative distribution function, to a latest access event for each temporary identifier contained in the streaming list; and
remove temporary identifiers from the streaming list that have a survival probability value less than a threshold value.

### Claim 20 (depends on 19)

The system of claim 19, wherein the base station is a cell station and the temporary identifiers comprise a Temporary Mobile Subscriber Identity (TMSI).

### Claim 21 (depends on 19)

The system of claim 19, wherein the one or more sensors contains the one or more processors and the one or more memory devices.

### Claim 22 (depends on 19)

The system of claim 19, wherein building the cumulative distribution function comprises:
building a histogram of the delta times between the plurality of access events for each of the plurality of temporary identifiers;
fitting a probability distribution function to the histogram; and
converting the probability distribution function to the cumulative distribution function for survival probability.

### Claim 23 (depends on 22)

The system of claim 22, wherein fitting a probability distribution function to the histogram uses an exponential kernel density estimate.

### Claim 24 (depends on 19)

The system of claim 19, further comprising comparing the number of temporary identifiers contained in the streaming list to a number of confirmed devices known to be present at a location of interest; and
calculating an intruder probability corresponding to the probability that a device corresponding to each of the temporary identifiers contained in the streaming list is present at the location of interest.

### Claim 25 (depends on 24)

The system of claim 24, further comprising adjusting the threshold value to minimize the difference between the number of temporary identifiers contained in the streaming list and the number of confirmed devices known to be present at the location of interest.

### Claim 26 (depends on 24)

The system of claim 24, wherein calculating the intruder probability comprises calculating the probability that the streaming list contains at least one temporary identifier more than the number of confirmed devices known to be present at the location of interest.

### Claim 27

A wireless device detection system, comprising:
one or more sensors configured to receive temporary identifiers transmitted between a base station and a mobile wireless device;
one or more processors; and
one or more memory devices having stored thereon instructions that when executed by the one or more processors cause the one or more processors to:
build a cumulative distribution function for survival probability by:
building a histogram of delta times between a plurality of access events for each of a plurality of temporary identifiers received from the one or more sensors;
fitting a probability distribution function to the histogram;
converting the probability distribution function to a cumulative distribution function for survival probability;
assigning a survival probability value, based on the cumulative distribution function, to a latest access event for each temporary identifier contained in a streaming list; and
remove temporary identifiers from the streaming list that have a survival probability value less than a threshold value;
in response to a new access event, add a corresponding temporary identifier to the streaming list and assign a survival probability value, based on the cumulative distribution function, to the latest access event for each temporary identifier contained in the streaming list; and
remove temporary identifiers from the streaming list that have a survival probability value less than the threshold value.

### Claim 28 (depends on 27)

The system of claim 27, wherein fitting a probability distribution function to the histogram uses an exponential kernel density estimate.

### Claim 29 (depends on 27)

The system of claim 27, wherein the base station is a cell station and the temporary identifiers comprise a Temporary Mobile Subscriber Identity (TMSI).

### Claim 30 (depends on 27)

The system of claim 27, wherein the one or more sensors contains the one or more processors and the one or more memory devices.

### Claim 31 (depends on 27)

The system of claim 27, further comprising calculating an intruder probability comprising calculating the probability that the streaming list contains at least one temporary identifier more than the number of confirmed devices known to be present at the location of interest.

### Claim 32

A method for detecting wireless devices, comprising:
receiving temporary identifiers transmitted between a base station and a mobile wireless device with one or more passive sensors;
building a cumulative distribution function for survival probability based on delta times between a plurality of access events for each of a plurality of temporary identifiers received from the one or more sensors;
in response to a new access event, adding a corresponding temporary identifier to a streaming list and assigning a survival probability value, based on the cumulative distribution function, to a latest access event for each temporary identifier contained in the streaming list; and
removing temporary identifiers from the streaming list that have a survival probability value less than a threshold value.

### Claim 33 (depends on 32)

The method of claim 32, wherein the base station is a cell station and the temporary identifiers comprise a Temporary Mobile Subscriber Identity (TMSI).

### Claim 34 (depends on 32)

The method of claim 32, wherein building the cumulative distribution function comprises:
building a histogram of the delta times between the plurality of access events for each of the plurality of temporary identifiers;
fitting a probability distribution function to the histogram; and
converting the probability distribution function to the cumulative distribution function for survival probability.

### Claim 35 (depends on 34)

The method of claim 34, wherein fitting a probability distribution function to the histogram uses an exponential kernel density estimate.

### Claim 36 (depends on 32)

The method of claim 32, further comprising comparing the number of temporary identifiers contained in the streaming list to a number of confirmed devices known to be present at a location of interest; and
calculating an intruder probability corresponding to the probability that a device corresponding to each of the temporary identifiers contained in the streaming list is present at the location of interest.

### Claim 37 (depends on 36)

The method of claim 36, further comprising adjusting the threshold value to minimize the difference between the number of temporary identifiers contained in the streaming list and the number of confirmed devices known to be present at the location of interest.

### Claim 38 (depends on 36)

The method of claim 36, wherein calculating the intruder probability comprises calculating the probability that the streaming list contains at least one temporary identifier more than the number of confirmed devices known to be present at the location of interest.
