# US 12,762,216 B2 · Driving record authentication method, electronic device, storage medium

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

- Number: US 12,762,216 B2
- Document ID: US12762216B2
- Status: Granted
- Kind: B2
- Application number: 17/972,764
- Filed: 2022-10-25
- Published: 2024-02-22
- Granted: 2026-10-13
- Earliest claimed: 2022-08-19
- Assignees: Fulian Precision Electronics (Tianjin) Co., LTD.
- Applicants: Fulian Precision Electronics (Tianjin) Co., LTD.
- Inventors: Shih Chun Wang; Yu-Wen Chen; Shih-Yin Tseng; Ting-Yu Du
- Web page: https://patentgrep.com/patent/US12762216B2

## CPC

- G06F 21/32: using biometric data, e.g. fingerprints, iris scans or voiceprints
- G06Q 20/389: {Keeping log of transactions for guaranteeing non-repudiation of a transaction}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- 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

A driving record authentication method is provided. The method includes acquiring historical driving records of a driver and associated records of the driver. Once a non-fungible token image of the driver is minted based on the historical driving records and the associated records, the non-fungible token image is transmitted to a user terminal in response to a query request associated with the driver that sent the user terminal.

## Claims

### Claim 1

A driving record authentication method, applied to an electronic device serving as a node of a blockchain, the driving record authentication method comprising:
receiving a login request from a vehicle, the login request being generated based on personal information of a driver of the vehicle in response that the driver is detected to be in a driving position of the vehicle;
in response that the login request is a valid request, receiving real-time driving record of the driver, associating the real-time driving record with a current time, and storing the real-time driving record associated with the current time to the blockchain according to personal information of the driver;
periodically acquiring historical driving records of the driver and acquiring associated records of the driver, the historical driving records comprising driving records of the driver within a preset time period;
determining a level of the driver based on the historical driving records and the associated records;
minting a non-fungible token (NFT) image corresponding to the level of the driver;
in response to a query request associated with the driver, transmitting the NFT image to a user terminal that sent the query request; and
performing a restriction measure to the driver based on the NFT image.

### Claim 2 (depends on 1)

The driving record authentication method according to claim 1, wherein minting the NFT image corresponding to the level of the driver comprises:
minting a NFT image template corresponding each of a plurality of levels;
invoking the NFT image template corresponding to the level of the driver in response that the level of the driver is determined; and
minting the NFT image corresponding to the level of the driver based on a current time and personal information of the driver using the invoked NFT image template.

### Claim 3 (depends on 1)

The driving record authentication method according to claim 1, wherein determining the level of the driver based on the historical driving records and the associated records comprises:
invoking a level recognition model; and obtaining the level of the driver by inputting the historical driving records and the associated records in the level recognition model.

### Claim 4 (depends on 3)

The driving record authentication method according to claim 3, further comprising:
training the level recognition model by:
obtaining a preset number of sample data corresponding to different levels, each sample data comprising driving records and associated records; labeling each sample data corresponding to each level with a category, making the sample data corresponding to each level comprising a category label; determining the preset number of sample data comprising the category labels as training samples;
randomly dividing the training samples into a training set and a verification set, the training set comprising a first preset ratio of the preset number of sample data, and the verification set comprising a second preset ratio of the preset number of sample data; obtaining the level recognition model by training a deep neural network using the training set, and verifying an accuracy rate of the level recognition model by using the verification set; and
ending a training in response that the accuracy rate is greater than or equal to a preset accuracy rate; increasing, in response that the accuracy rate is less than the preset accuracy rate, a number of the training samples to retrain the deep neural network until the accuracy rate of the level recognition model is greater than or equal to the preset accuracy rate.

### Claim 5 (depends on 1)

The driving record authentication method according to claim 1, wherein determining the level of the driver based on the historical driving records and the associated records comprises:
obtaining an analysis result of each record in the historical driving records and the associated records;
obtaining quantitative data by quantifying the analysis result of each record; and
determining the level of the driver based on the quantitative data.

### Claim 6 (depends on 5)

The driving record authentication method according to claim 5, wherein quantifying the analysis result of each record comprises:
assigning different scores to different analysis results;
wherein determining the level of the driver based on the quantitative data comprises:
pre-determining different scores corresponding to different levels; and
calculating an average value of the quantified data, and determining the level of the driver based on the average value.

### Claim 7 (depends on 1)

The driving record authentication method according to claim 1,
wherein performing the restriction measure comprises restricting a drive-able area and/or a driving mode of the driver, and comprising at least one of following:
obtaining a percentage ranking of driving mileage of the driver in a mountainous area, and in response to the percentage ranking being less than or equal to a first preset threshold, restricting the driver from driving to the mountainous area;
obtaining a total driving mileage of the driver, and in response to the total driving mileage being less than a second preset threshold, restricting the driver from driving the vehicle to a highway;
obtaining a total driving mileage of the driver, and in response to the total driving mileage being less than a third preset threshold, limiting a driving speed of the driver to be less than a preset speed value.

### Claim 8

An electronic device serving as a node of a blockchain, comprising:
a storage device;
at least one processor; and
the storage device storing one or more programs, which when executed by the at least one processor, cause the at least one processor to:
receive a login request from a vehicle, the login request being generated based on personal information of a driver of the vehicle in response that the driver is detected to be in a driving position of the vehicle;
in response that the login request is a valid request, receive real-time driving record of the driver, associating the real-time driving record with a current time, and store the real-time driving record associated with the current time to the blockchain according to personal information of the driver;
periodically acquire historical driving records of the driver and acquire associated records of the driver, the historical driving records comprising driving records of the driver within a preset time period;
determine a level of the driver based on the historical driving records and the associated records;
mint a non-fungible token (NFT) image corresponding to the level of the driver;
in response to a query request associated with the driver, transmit the NFT image to a user terminal that sent the query request; and
perform a restriction measure to the driver based on the NFT image.

### Claim 9 (depends on 8)

The driving record authentication method according to claim 8, wherein the at least one processor mints the NFT image corresponding to the level of the driver by:
minting a NFT image template corresponding each of a plurality of levels;
invoking the NFT image template corresponding to the level of the driver in response that the level of the driver is determined; and
minting the NFT image corresponding to the level of the driver based on a current time and personal information of the driver using the invoked NFT image template.

### Claim 10 (depends on 8)

The driving record authentication method according to claim 8, wherein the at least one processor determines the level of the driver based on the historical driving records and the associated records by:
invoking a level recognition model; and obtaining the level of the driver by inputting the historical driving records and the associated records in the level recognition model.

### Claim 11 (depends on 10)

The driving record authentication method according to claim 10, wherein the at least one processor is further caused to:
train the level recognition model by:
obtaining a preset number of sample data corresponding to different levels, each sample data comprising driving records and associated records; labeling each sample data corresponding to each level with a category, making the sample data corresponding to each level comprising a category label; determining the preset number of sample data comprising the category labels as training samples;
randomly dividing the training samples into a training set and a verification set, the training set comprising a first preset ratio of the preset number of sample data, and the verification set comprising a second preset ratio of the preset number of sample data; obtaining the level recognition model by training a deep neural network using the training set, and verifying an accuracy rate of the level recognition model by using the verification set; and
ending a training in response that the accuracy rate is greater than or equal to a preset accuracy rate; increasing, in response that the accuracy rate is less than the preset accuracy rate, a number of the training samples to retrain the deep neural network until the accuracy rate of the level recognition model is greater than or equal to the preset accuracy rate.

### Claim 12 (depends on 8)

The driving record authentication method according to claim 8, wherein the at least one processor determines the level of the driver based on the historical driving records and the associated records by:
obtaining an analysis result of each record in the historical driving records and the associated records;
obtaining quantitative data by quantifying the analysis result of each record; and
determining the level of the driver based on the quantitative data.

### Claim 13 (depends on 12)

The driving record authentication method according to claim 12, wherein the at least one processor quantifies the analysis result of each record by:
assigning different scores to different analysis results;
wherein the at least one processor determines the level of the driver based on the quantitative data by:
pre-determining different scores corresponding to different levels; and
calculating an average value of the quantified data, and determining the level of the driver based on the average value.

### Claim 14 (depends on 8)

The driving record authentication method according to claim 8, wherein the at least one processor is further caused to:
wherein the at least one processor performs the restriction measure comprises restricting a drive-able area and/or a driving mode of the driver, and comprising at least one of following:
obtaining a percentage ranking of driving mileage of the driver in a mountainous area, and in response to the percentage ranking being less than or equal to a first preset threshold, restricting the driver from driving to the mountainous area;
obtaining a total driving mileage of the driver, and in response to the total driving mileage being less than a second preset threshold, restricting the driver from driving the vehicle to a highway;
obtaining a total driving mileage of the driver, and in response to the total driving mileage being less than a third preset threshold, limiting a driving speed of the driver to be less than a preset speed value.

### Claim 15

A non-transitory storage medium having instructions stored thereon, when the instructions are executed by a processor of an electronic device serving as a node of a blockchain, the processor is caused to perform a driving record authentication method, wherein the driving record authentication method comprises:
receiving a login request from a vehicle, the login request being generated based on personal information of a driver of the vehicle in response that the driver is detected to be in a driving position of the vehicle;
in response that the login request is a valid request, receiving real-time driving record of the driver, associating the real-time driving record with a current time, and storing the real-time driving record associated with the current time to the blockchain according to personal information of the driver;
periodically acquiring historical driving records of a driver and acquiring associated records of the driver, the historical driving records comprising driving records of the driver within a preset time period;
determining a level of the driver based on the historical driving records and the associated records;
minting a non-fungible token (NFT) image corresponding to the level of the driver;
in response to a query request associated with the driver, transmitting the NFT image to a user terminal that sent the query request; and
performing a restriction measure to the driver based on the NFT image.

### Claim 16 (depends on 15)

The non-transitory storage medium according to claim 15, wherein minting the NFT image corresponding to the level of the driver comprises:
minting a NFT image template corresponding each of a plurality of levels;
invoking the NFT image template corresponding to the level of the driver in response that the level of the driver is determined; and
minting the NFT image corresponding to the level of the driver based on a current time and personal information of the driver using the invoked NFT image template.

### Claim 17 (depends on 15)

The non-transitory storage medium according to claim 15, wherein determining the level of the driver based on the historical driving records and the associated records comprises:
invoking a level recognition model; and obtaining the level of the driver by inputting the historical driving records and the associated records in the level recognition model.

### Claim 18 (depends on 17)

The non-transitory storage medium according to claim 17, wherein the method further comprises:
training the level recognition model by:
obtaining a preset number of sample data corresponding to different levels, each sample data comprising driving records and associated records; labeling each sample data corresponding to each level with a category, making the sample data corresponding to each level comprising a category label; determining the preset number of sample data comprising the category labels as training samples;
randomly dividing the training samples into a training set and a verification set, the training set comprising a first preset ratio of the preset number of sample data, and the verification set comprising a second preset ratio of the preset number of sample data; obtaining the level recognition model by training a deep neural network using the training set, and verifying an accuracy rate of the level recognition model by using the verification set; and
ending a training in response that the accuracy rate is greater than or equal to a preset accuracy rate; increasing, in response that the accuracy rate is less than the preset accuracy rate, a number of the training samples to retrain the deep neural network until the accuracy rate of the level recognition model is greater than or equal to the preset accuracy rate.

### Claim 19 (depends on 15)

The non-transitory storage medium according to claim 15, wherein determining the level of the driver based on the historical driving records and the associated records comprises:
obtaining an analysis result of each record in the historical driving records and the associated records;
obtaining quantitative data by quantifying the analysis result of each record; and
determining the level of the driver based on the quantitative data.

### Claim 20 (depends on 19)

The non-transitory storage medium according to claim 19, wherein quantifying the analysis result of each record comprises:
assigning different scores to different analysis results;
wherein determining the level of the driver based on the quantitative data comprises:
pre-determining different scores corresponding to different levels; and
calculating an average value of the quantified data, and determining the level of the driver based on the average value.