# US 2021/0342560 A1 · Rfid motion detection for dense rfid tag environments

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

- Number: US 2021/0342560 A1
- Document ID: US20210342560A1
- Status: Published application
- Kind: A1
- Application number: 17/093,418
- Filed: 2020-11-09
- Published: 2021-11-04
- Earliest claimed: 2019-11-26
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Chieh-Yih Wan; Rahul C. Shah; Cagri C. Tanriover; Ke-Yu Chen
- Web page: https://patentgrep.com/patent/US20210342560A1

## CPC

- G06K 7/10425: {the interrogation device being arranged for interrogation of record carriers passing by the interrogation device}
- G06N 20/20: Ensemble learning
- G01S 5/02: using radio waves (using satellite radio beacon systems for determining position G01S19/00)
- G01S 11/02: using radio waves (G01S19/00 takes precedence)
- G01S 11/06: using intensity measurements
- G06K 7/10297: {arrangements for handling protocols designed for non-contact record carriers such as RFIDs NFCs, e.g. ISO/IEC 14443 and 18092 (cryptographic protocols H04L9/00; network security protocols H04L63/00; real-time communication protocols in data switching networks H04L65/00; network protocols for data switching network services H04L67/00)}
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q 10/0877: {by inventory control or reporting using inventory tracking or counting}
- G06K: GRAPHICAL DATA READING (image or video recognition or understanding G06V); PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

In one embodiment, an apparatus comprises processing circuitry to: receive wireless signal data corresponding to an RFID tag, wherein the wireless signal data comprises signal strength data and signal phase data corresponding to wireless signals transmitted by the RFID tag and received by an RFID reader; generate decomposed signal strength data based on a seasonal decomposition of the signal strength data; generate a frequency-phase curve based on the signal phase data; extract a set of signal strength features based on the decomposed signal strength data; extract a set of signal phase features based on the frequency-phase curve; and detect a motion state of the RFID tag using a machine learning classifier, wherein the machine learning classifier is trained to detect the motion state based on the set of signal strength features and the set of signal phase features.

## Claims

### Claim at position 1

1-25. (canceled)

### Claim 26

A device to perform motion detection for radio frequency identification (RFID) tags, comprising:
interface circuitry; and
processing circuitry to:
receive, via the interface circuitry, wireless signal measurements associated with an RFID tag, wherein the wireless signal measurements comprise signal strength measurements and signal phase measurements obtained from wireless signals transmitted by the RFID tag over a time window;
extract decomposed signal strength data from the signal strength measurements, wherein the decomposed signal strength data comprises one or more decomposed time series datasets;
extract frequency-phase data from the signal phase measurements, wherein the frequency-phase data indicates a plurality of signal phases detected across a plurality of transmission frequencies of the wireless signals transmitted by the RFID tag; and
perform motion detection for the RFID tag, wherein the motion detection is to detect motion of the RFID tag based on the decomposed signal strength data and the frequency-phase data.

### Claim 27 (depends on 26)

The device of claim 26, wherein the processing circuitry to extract the decomposed signal strength data from the signal strength measurements is further to:
perform a seasonal decomposition on the signal strength measurements, wherein the seasonal decomposition is to decompose the signal strength measurements into the one or more decomposed time series datasets, wherein the one or more decomposed time series datasets comprise one or more of:
a seasonal data series;
a trend data series; or
a residual data series.

### Claim 28 (depends on 27)

The device of claim 27, wherein the frequency-phase data represents a frequency-phase curve, wherein the frequency-phase curve indicates the plurality of signal phases detected across the plurality of transmission frequencies of the wireless signals transmitted by the RFID tag.

### Claim 29 (depends on 28)

The device of claim 28, wherein the processing circuitry to perform motion detection for the RFID tag is further to:
extract a set of signal strength features based on the decomposed signal strength data;
extract a set of signal phase features based on the frequency-phase curve; and
perform motion detection for the RFID tag using a machine learning classifier, wherein the machine learning classifier is trained to perform motion detection based on at least the set of signal strength features and the set of signal phase features.

### Claim 30 (depends on 29)

The device of claim 29, wherein the processing circuitry to perform motion detection for the RFID tag using the machine learning classifier is further to:
generate a motion state of the RFID tag, wherein the motion state indicates:
an identity of the RFID tag;
a time of occurrence of the motion state;
whether the RFID tag is stationary or moving; and
a movement energy intensity of the RFID tag.

### Claim 31 (depends on 29)

The device of claim 29, wherein the set of signal strength features comprises:
one or more trend features extracted from the trend data series in the decomposed signal strength data;
one or more residual features extracted from the residual data series in the decomposed signal strength data; and
a standard deviation of received signal strength indicators (RSSIs) extracted from the signal strength measurements.

### Claim 32 (depends on 29)

The device of claim 29, wherein the set of signal phase features comprises one or more of:
a slope of a linear regression of the frequency-phase curve;
a correlation coefficient of a least-squares regression of the frequency-phase curve;
a descending trend corresponding to a phase variation of the plurality of signal phases;
a dynamic range of the plurality of signal phases; or
a number of zero crossings of the frequency-phase curve.

### Claim 33 (depends on 26)

The device of claim 26, wherein the processing circuitry is further to:
detect, based on the motion of the RFID tag, behavior associated with a physical asset corresponding to the RFID tag.

### Claim 34

At least one non-transitory machine accessible storage medium having instructions stored thereon, wherein the instructions, when executed on processing circuitry, cause the processing circuitry to:
receive wireless signal measurements associated with a radio frequency identification (RFID) tag, wherein the wireless signal measurements comprise signal strength measurements and signal phase measurements obtained from wireless signals transmitted by the RFID tag over a time window;
extract decomposed signal strength data from the signal strength measurements, wherein the decomposed signal strength data comprises one or more decomposed time series datasets;
extract frequency-phase data from the signal phase measurements, wherein the frequency-phase data indicates a plurality of signal phases detected across a plurality of transmission frequencies of the wireless signals transmitted by the RFID tag; and
perform motion detection for the RFID tag, wherein the motion detection is to detect motion of the RFID tag based on the decomposed signal strength data and the frequency-phase data.

### Claim 35 (depends on 34)

The storage medium of claim 34, wherein the one or more decomposed time series datasets comprises:
one or more periodic data series; and
one or more non-periodic data series.

### Claim 36 (depends on 34)

The storage medium of claim 34, wherein:
the one or more decomposed time series datasets comprises one or more of:
a seasonal data series;
a trend data series; or
a residual data series; and
the frequency-phase data represents a frequency-phase curve, wherein the frequency-phase curve indicates the plurality of signal phases detected across the plurality of transmission frequencies of the wireless signals transmitted by the RFID tag.

### Claim 37 (depends on 36)

The storage medium of claim 36, wherein the instructions that cause the processing circuitry to perform motion detection for the RFID tag further cause the processing circuitry to:
extract a set of signal strength features based on the decomposed signal strength data;
extract a set of signal phase features based on the frequency-phase curve; and
perform motion detection for the RFID tag using a machine learning classifier, wherein the machine learning classifier is trained to perform motion detection based on at least the set of signal strength features and the set of signal phase features.

### Claim 38 (depends on 37)

The storage medium of claim 37, wherein the instructions that cause the processing circuitry to perform motion detection for the RFID tag using the machine learning classifier further cause the processing circuitry to:
generate a motion state of the RFID tag, wherein the motion state indicates:
an identity of the RFID tag;
a time of occurrence of the motion state;
whether the RFID tag is stationary or moving; and
a movement energy intensity of the RFID tag.

### Claim 39 (depends on 37)

The storage medium of claim 37, wherein the set of signal strength features comprises:
one or more trend features extracted from the trend data series in the decomposed signal strength data;
one or more residual features extracted from the residual data series in the decomposed signal strength data; and
a standard deviation of received signal strength indicators (RSSIs) extracted from the signal strength measurements.

### Claim 40 (depends on 37)

The storage medium of claim 37, wherein the set of signal phase features comprises one or more of:
a slope of a linear regression of the frequency-phase curve;
a correlation coefficient of a least-squares regression of the frequency-phase curve;
a descending trend corresponding to a phase variation of the plurality of signal phases;
a dynamic range of the plurality of signal phases; or
a number of zero crossings of the frequency-phase curve.

### Claim 41 (depends on 37)

The storage medium of claim 37, wherein the machine learning classifier comprises a voting classifier, wherein the voting classifier is to perform motion detection for the RFID tag based on motion detection predictions from a plurality of machine learning models.

### Claim 42 (depends on 37)

The storage medium of claim 37, wherein the machine learning classifier comprises a single model classifier, wherein the single model classifier comprises:
a support-vector machine (SVM) model;
a random forest model; or
a logistic regression model.

### Claim 43 (depends on 34)

The storage medium of claim 34, wherein the instructions further cause the processing circuitry to:
detect, based on the motion of the RFID tag, behavior associated with a physical asset corresponding to the RFID tag.

### Claim 44 (depends on 43)

The storage medium of claim 43, wherein:
the physical asset comprises a retail product; and
the behavior associated with the physical asset comprises a human interaction with the retail product.

### Claim 45

A method of performing motion detection for radio frequency identification (RFID) tags, comprising:
receiving wireless signal measurements associated with an RFID tag, wherein the wireless signal measurements comprise signal strength measurements and signal phase measurements obtained from wireless signals transmitted by the RFID tag over a time window;
extracting decomposed signal strength data from the signal strength measurements, wherein the decomposed signal strength data comprises one or more decomposed time series datasets;
extracting frequency-phase data from the signal phase measurements, wherein the frequency-phase data indicates a plurality of signal phases detected across a plurality of transmission frequencies of the wireless signals transmitted by the RFID tag; and
performing motion detection for the RFID tag, wherein the motion detection is to detect motion of the RFID tag based on the decomposed signal strength data and the frequency-phase data.

### Claim 46 (depends on 45)

The method of claim 45, wherein performing motion detection for the RFID tag comprises:
extracting a set of signal strength features based on the decomposed signal strength data;
extracting a set of signal phase features based on the frequency-phase data; and
performing motion detection for the RFID tag using a machine learning classifier, wherein the machine learning classifier is trained to perform motion detection based on at least the set of signal strength features and the set of signal phase features.

### Claim 47 (depends on 45)

The method of claim 45, further comprising:
detecting, based on the motion of the RFID tag, behavior associated with a physical asset corresponding to the RFID tag.

### Claim 48 (depends on 47)

The method of claim 47, wherein:
the physical asset comprises a retail product; and
the behavior associated with the physical asset comprises a human interaction with the retail product.

### Claim 49

A system, comprising:
a radio frequency identification (RFID) reader to communicate with a plurality of RFID tags; and
processing circuitry to:
receive, from the RFID reader, wireless signal measurements associated with an RFID tag of the plurality of RFID tags, wherein the wireless signal measurements comprise signal strength measurements and signal phase measurements obtained from wireless signals transmitted by the RFID tag over a time window;
extract decomposed signal strength data from the signal strength measurements, wherein the decomposed signal strength data comprises one or more decomposed time series datasets;
extract frequency-phase data from the signal phase measurements, wherein the frequency-phase data indicates a plurality of signal phases detected across a plurality of transmission frequencies of the wireless signals transmitted by the RFID tag; and
perform motion detection for the RFID tag, wherein the motion detection is to detect motion of the RFID tag based on the decomposed signal strength data and the frequency-phase data.

### Claim 50 (depends on 49)

The system of claim 49, wherein:
the RFID tag corresponds to a physical asset; and
the processing circuitry is further to detect behavior associated with the physical asset based on the motion of the RFID tag.
