# US 2021/0084494 A1 · Predictively providing access to resources

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

- Number: US 2021/0084494 A1
- Document ID: US20210084494A1
- Status: Published application
- Kind: A1
- Application number: 16/571,363
- Filed: 2019-09-16
- Published: 2021-03-18
- Earliest claimed: 2019-09-16
- Assignees: MicroStrategy Incorporated
- Applicants: MicroStrategy Incorporated
- Inventors: Konstantin Angelov; Hyunmo Kang; Hector Vazquez; Ren-Jay Huang
- Web page: https://patentgrep.com/patent/US20210084494A1

## CPC

- H04W 12/062: Pre-authentication
- G06N 3/0499: Feedforward networks
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- G06N 20/00: Machine learning
- H04L 47/83: based on usage prediction
- H04W 12/069: using certificates or pre-shared keys
- H04W 12/08: Access security
- H04W 12/63: Location-dependent; Proximity-dependent
- H04W 12/67: Risk-dependent, e.g. selecting a security level depending on risk profiles
- H04W 16/22: Traffic simulation tools or models
- H04W 28/0226: {based on location or mobility (handoff or reselection H04W36/00; mobile application services making use of the location of users or terminals H04W4/02)}
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Methods, systems, and apparatus, including computer-readable media, for predictively providing access to resources. In some implementations, a method includes receiving movement data indicating movement of a mobile device associated with a user while the mobile device approaches a resource is received. A credential of the user authorizes access to the resource. Based on the movement data, the movement of the mobile device is classified as corresponding to an attempt to access the resource. The mobile device is determined to be in proximity to the resource. Before the user interacts with the resource, the resource is caused to be unlocked or opened in response to determining that the credential of the user authorizes access to the resource, classifying the movement of the mobile device as corresponding to an attempt to access the resource, and determining that the mobile device is in proximity to the resource.

## Claims

### Claim 1

A method performed by one or more computing devices, the method comprising:
receiving, by the one or more computing devices, movement data indicating movement of a mobile device associated with a user while the mobile device approaches a secured resource;
determining, by the one or more computing devices, that a credential of the user authorizes access to the secured resource;
based on the movement data, classifying, by the one or more computing devices, the movement of the mobile device as corresponding to an attempt to access the secured resource;
determining, by the one or more computing devices, that the mobile device is in proximity to the secured resource; and
before the user interacts with the secured resource, causing the secured resource to be unlocked or opened in response to (i) determining that the credential of the user authorizes access to the secured resource, (ii) classifying the movement of the mobile device as corresponding to an attempt to access the secured resource, and (iii) determining that the mobile device is in proximity to the secured resource.

### Claim 2 (depends on 1)

The method of claim 1, comprising determining that the user is currently authenticated using the mobile device;
wherein causing the secured resource to be unlocked or opened is based on determining that the user is currently authenticated using the mobile device.

### Claim 3 (depends on 1)

The method of claim 1, wherein the one or more computing devices are a server system;
wherein causing the secured resource to be unlocked or opened comprises sending, by a server system and over a computer network, access data that causes the secured resource to unlock or open itself in response to receiving the access data.

### Claim 4 (depends on 1)

The method of claim 1, wherein the secured resource is a door, locker, machine, electronic device, or vehicle.

### Claim 5 (depends on 1)

The method of claim 1, wherein the movement data comprises data indicating a path that the mobile device travelled to reach proximity with the secured resource.

### Claim 6 (depends on 1)

The method of claim 1, wherein the movement data comprises data identifying wireless beacons detected by the mobile device at different point in time while the mobile device approaches a secured resource.

### Claim 7 (depends on 6)

The method of claim 6, wherein the movement data indicates times and signal strengths with which messages from the beacons were received by the mobile device.

### Claim 8 (depends on 1)

The method of claim 1, wherein the movement data indicates sensor data from an accelerometer, inertial measurement unit, or compass of the mobile device.

### Claim 9 (depends on 1)

The method of claim 1, wherein classifying the movement of the mobile device comprises:
generating, by the one or more computing devices, an access likelihood score based on the movement data, wherein the likelihood score indicates a predicted likelihood that the user will attempt to access the secured resource; and
determining that the access likelihood score satisfies a threshold.

### Claim 10 (depends on 9)

The method of claim 9, wherein generating the access likelihood score comprises:
providing, as input to a trained machine learning model, feature values generated from the movement data, wherein the trained machine learning model is configured to classify whether movement patterns represent an attempt to access a resource; and
receiving the access likelihood score as an output that the trained machine learning model provides in response to receiving the feature values as input.

### Claim 11 (depends on 10)

The method of claim 10, wherein the trained machine learning model is a trained artificial neural network.

### Claim 12 (depends on 10)

The method of claim 10, wherein the trained machine learning model has been trained based on a plurality of training examples indicating movement patterns that resulted in a user accessing a secured resource and a plurality of training examples indicating movement patterns that did not result in a user accessing a secured resource.

### Claim 13 (depends on 1)

The method of claim 1, wherein determining that the mobile device is in proximity to the secured resource comprises determining that mobile device is within a predetermined distance of the secured resource based on a signal strength of a communication between the mobile device and a location beacon device that is located at a predetermined location with respect to the secured resource.

### Claim 14 (depends on 1)

The method of claim 1, wherein classifying the movement of the mobile device is based on a similarity between (i) characteristics of the current approach to the secured resource by the user and characteristics of (ii) characteristics of one or more previous approaches by the user that resulted in the user accessing the secured resource or another secured resource.

### Claim 15 (depends on 14)

The method of claim 14, wherein classifying the movement of the mobile device comprises:
comparing the movement data with movement patterns for multiple users leading to access of any of multiple resources of a same type as the secured resource;
comparing the movement data with movement patterns for multiple users leading to access to the secured resource;
comparing the movement data with user-specific movement patterns leading to previous accesses by the user to multiple resources of the same type as the secured resource; or
comparing the movement data with user-specific movement patterns leading to previous accesses by the user to the secured resource.

### Claim 16 (depends on 14)

The method of claim 14, wherein the characteristics of the current approach to the secured resource by the user comprise at least one of:
a current time of day,
a current speed of movement of the mobile device,
a current acceleration of the mobile device,
a current direction of movement of the mobile device,
a current orientation of the mobile device,
a path travelled by the mobile device as the mobile device approaches the secured resource,
a sequence of location beacons detected by the mobile device as the mobile device approaches the secured resource, or
a signal strength of communications with the location beacons;
wherein the characteristics of one or more previous approaches comprise at least one of:
a time of day of a previous access to the secured resource by the user,
a speed of movement of the mobile device during an approach leading to access to the secured resource by the user,
an acceleration of the mobile device during an approach leading to access to the secured resource by the user,
a direction of movement of the mobile device during an approach leading to access to the secured resource by the user,
an orientation of the mobile device during an approach leading to access to the secured resource by the user,
a path travelled by the mobile device as the mobile device during an approach leading to access to the secured resource by the user,
a sequence of location beacons detected by the mobile device during an approach leading to access to the secured resource by the user, or
a signal strength of communications with the location beacons during an approach leading to access to the secured resource by the user.

### Claim 17 (depends on 1)

The method of claim 1, wherein the mobile device is a phone or a watch.

### Claim 18 (depends on 1)

The method of claim 1, comprising determining, based on the movement data, (i) a path that that the mobile device has travelled while the mobile device approaches the secured resource, the path being determined based on identifiers for location beacons that the mobile device received beacon messages from while approaching the secured resource and signal strengths at which the beacon messages were received, (ii) speed and acceleration of the mobile device at multiple positions along the path, (iii) a current location of the mobile device, and (iv) a current speed and direction of the mobile device;
wherein classifying the movement of the mobile device comprises:
comparing (i) the path and speed and acceleration of the mobile device along the path with (ii) a path of a previous approach of the user to the secured resource that resulted in the user accessing the secured resource and the speed and acceleration along the path of the previous approach;
comparing a time of the approach to the secured resource with one or more times that the user previously accessed the resource;
wherein the method includes determining, based on the current location, speed, and direction of the mobile device, a time to cause the cause the secured resource to be unlocked or opened, wherein the secured resource is caused to be opened at the determined time by sending an instruction to the secured resource that specifies the determined time or sending an instruction to the secured resource at the determined time.

### Claim 19

A system comprising:
one or more computing devices; and
one or more computer-readable media storing instructions that, when executed by the one or more computing devices, cause the one or more computing devices to perform operations comprising:
receiving, by the one or more computing devices, movement data indicating movement of a mobile device associated with a user while the mobile device approaches a secured resource;
determining, by the one or more computing devices, that a credential of the user authorizes access to the secured resource;
based on the movement data, classifying, by the one or more computing devices, the movement of the mobile device as corresponding to an attempt to access the secured resource;
determining, by the one or more computing devices, that the mobile device is in proximity to the secured resource; and
before the user interacts with the secured resource, causing the secured resource to be unlocked or opened in response to (i) determining that the credential of the user authorizes access to the secured resource, (ii) classifying the movement of the mobile device as corresponding to an attempt to access the secured resource, and (iii) determining that the mobile device is in proximity to the secured resource.

### Claim 20

One or more non-transitory computer-readable media storing instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform operations comprising:
receiving, by the one or more computing devices, movement data indicating movement of a mobile device associated with a user while the mobile device approaches a secured resource;
determining, by the one or more computing devices, that a credential of the user authorizes access to the secured resource;
based on the movement data, classifying, by the one or more computing devices, the movement of the mobile device as corresponding to an attempt to access the secured resource;
determining, by the one or more computing devices, that the mobile device is in proximity to the secured resource; and
before the user interacts with the secured resource, causing the secured resource to be unlocked or opened in response to (i) determining that the credential of the user authorizes access to the secured resource, (ii) classifying the movement of the mobile device as corresponding to an attempt to access the secured resource, and (iii) determining that the mobile device is in proximity to the secured resource.
