# US 11,907,955 B2 · System and method for blockchain automatic tracing of money flow using artificial intelligence

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

- Number: US 11,907,955 B2
- Document ID: US11907955B2
- Status: Granted
- Kind: B2
- Application number: 17/357,029
- Filed: 2021-06-24
- Published: 2022-03-03
- Granted: 2024-02-20
- Earliest claimed: 2020-08-28
- Assignees: Anchain.ai Inc.
- Applicants: Anchain.ai Inc.
- Inventors: Chunsheng Victor Fang; Wei Quan; Han Xu; Shuling He
- Web page: https://patentgrep.com/patent/US11907955B2

## CPC

- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G06Q 20/0655: {e-cash managed centrally}
- G06Q 20/38215: {Use of certificates or encrypted proofs of transaction rights}
- G06Q 20/389: {Keeping log of transactions for guaranteeing non-repudiation of a transaction}
- G06Q 20/405: {Establishing or using transaction specific rules}
- G06Q 20/407: {Cancellation of a transaction}
- G06Q 40/02: Banking, e.g. interest calculation or account maintenance (credit or loans G06Q40/03)
- H04L 9/3247: {involving digital signatures}
- H04L 9/3297: {involving time stamps, e.g. generation of time stamps}
- H04L 9/50: {using hash chains, e.g. blockchains or hash trees}
- H04L 2209/56: Financial cryptography, e.g. electronic payment or e-cash
- 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
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method and apparatus that receive blockchain transaction data from a blockchain ledger to a transaction database, receive intelligence labels from a blockchain ecosystem intelligence database, select a blockchain transaction flow comprising blockchain transactions associated with a digital account source address, digital account intermediate addresses, a digital account destination address, and intermediate transactions, receive input trace parameters, where the input trace parameters include at least one of an objective directional setting, a tracing constraint, and a transaction filter, the transaction filter based on the transaction timestamps and the digital assets transferred, apply the intelligence labels to the digital account source address, the digital account intermediate addresses, and the digital account destination address, apply an artificial intelligence graph search algorithm to the blockchain transaction flow based on the input trace parameters, and generate a report including tracing destination summary statistics of the auto-traced path.

## Claims

### Claim 1

A method of generating an action for an illicit digital asset transaction, the method comprising:
receiving blockchain transaction data from a blockchain ledger to a transaction database, the blockchain transaction data including blockchain addresses, transaction identifications, transaction timestamps, and digital assets transferred;
receiving intelligence labels from a blockchain ecosystem intelligence database, wherein the intelligence labels include known behavioral characteristics of entities associated with the blockchain addresses;
selecting a blockchain transaction flow comprising the blockchain transaction data associated with a digital account source address, digital account intermediate addresses, a digital account destination address, and intermediate transactions, wherein the intermediate transactions transfer the digital assets between the digital account source address and the digital account destination address;
receiving input trace parameters, wherein the input trace parameters include at least one of an objective directional setting, a tracing constraint, and a transaction filter, the transaction filter based on the transaction timestamps and the digital assets transferred;
applying the intelligence labels to the digital account source address, the digital account intermediate addresses, and the digital account destination address, thereby creating labeled account addresses;
applying an artificial intelligence graph search algorithm to the blockchain transaction flow based on the input trace parameters, to determine an auto-traced path of the digital assets in the blockchain transaction flow; and
generating a report including tracing destination summary statistics of the auto-traced path, the report including suspicious blockchain addresses; and
on condition that the report includes a suspicious blockchain address:
generating an action including at least one of alerting a user of the suspicious blockchain address, alerting the user to the illicit digital asset transaction associated with the suspicious blockchain address, and suspending transactions by the suspicious blockchain address.

### Claim 2 (depends on 1)

The method of claim 1, further comprising applying machine learning based behavior prediction labels, based on the input trace parameters, to at least one of the digital account source address, the digital account intermediate addresses, and the digital account destination address, wherein the machine learning based behavior prediction label is based in part on the behavior of entities associated with at least one of crypto exchanges, crypto mixers, bots, hackers, and terrorists.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
adding address clustering labels to the blockchain addresses, wherein the address clustering labels are based on identifying similar addresses using an address transaction behavior analysis; and
grouping the similar addresses into cluster IDs.

### Claim 4 (depends on 3)

The method of claim 3, wherein the address transaction behavior analysis includes:
collecting address history blockchain transactions;
collecting real world entity information, the real world entity information including office geolocation, phone number, and email associated with the traced address;
creating address similarity features for the collected address history blockchain transactions;
calculating address similarities;
merging addresses, based on the address similarities, into an existing cluster ID or a new cluster ID; and
applying the cluster IDs to the blockchain transaction flow.

### Claim 5 (depends on 1)

The method of claim 1, wherein the artificial intelligence graph search algorithm is a heuristic based graph search algorithm.

### Claim 6 (depends on 5)

The method of claim 5, wherein the heuristic based graph search algorithms include at least one of:
a Greedy Breadth First Search algorithm;
a Dijkstra search algorithm;
an A* search algorithm;
a D* search algorithm; and
an IDA* algorithm.

### Claim 7 (depends on 1)

The method of claim 1, further comprising constructing a user interface with interactive visualization of a trace path, the interactive visualization including at least one of:
topological sorting to graph layout by the intermediate transactions from the digital account source address to the digital account destination address;
time-bound tracing, wherein the trace path is restricted by at least time and a number of intermediate transactions after a specific transaction;
value-bound tracing, wherein the trace path is based on values of digital assets transferred in the blockchain transaction flow; and
highlighting of at least a portion of the trace path.

### Claim 8 (depends on 1)

The method of claim 1, wherein the report includes at least one of:
a percentage of funding by labeled account address; and
visualization of the auto-traced path from the digital account source address to the digital account destination address, in an expandable interactive view.

### Claim 9 (depends on 1)

The method of claim 1, wherein the report includes visualization of all digital asset paths from the digital account source address to the digital account destination address, in an expandable interactive view, and wherein the transaction filter includes a time range, a number of intermediate transactions, and a minimum amount of transferred assets.

### Claim 10 (depends on 1)

The method of claim 1, further comprising creating an alert timeline, wherein in the alert timeline:
monitors the suspicious blockchain addresses, based on the intelligence labels, with wallets containing funds that have not been transferred; and
alerts the user requesting further investigation of the suspicious blockchain addresses with un-transferred funds.

### Claim 11 (depends on 1)

The method of claim 1, wherein the entities associated with the blockchain addresses include cryptocurrency addresses, cryptocurrency address clusters, accounts comprising Central Bank Digital Currency (CBDC), and fiat bank accounts.

### Claim 12

A method comprising:
receiving blockchain transaction data from a blockchain ledger to a transaction database, the blockchain transaction data including blockchain addresses, transaction identifications, transaction timestamps, and digital assets transferred;
receiving intelligence labels from a blockchain ecosystem intelligence database, wherein the intelligence labels include known behavioral characteristics of entities associated with the blockchain addresses;
selecting a blockchain transaction flow comprising the blockchain transaction data associated with a digital account source address, digital account intermediate addresses, a digital account destination address, and intermediate transactions, wherein the intermediate transactions transfer the digital assets between the digital account source address and the digital account destination address;
receiving input trace parameters, wherein the input trace parameters include at least one of an objective directional setting, a tracing constraint, and a transaction filter based on the transaction timestamps and the digital assets transferred;
applying the intelligence labels to the digital account source address, the digital account intermediate addresses, and the digital account destination address, thereby creating labeled account addresses;
generating an interactive journey board of the blockchain transaction flow based on the input trace parameters, including paths of the digital assets in the blockchain transaction flow between the blockchain addresses, wherein at least one of one or more of the paths, and portions of paths, may be selected for the journey board by a user.

### Claim 13 (depends on 12)

The method of claim 12, further comprising applying machine learning based behavior prediction labels, based on the input trace parameters, to at least one of the digital account source address, the digital account intermediate addresses, and the digital account destination address, wherein the machine learning based behavior prediction label is based in part on the behavior of entities associated with at least one of crypto exchanges, crypto mixers, bots, hackers, and terrorists.

### Claim 14 (depends on 12)

The method of claim 12, further comprising constructing a user interface with interactive visualization of the journey board.

### Claim 15

A computing apparatus comprising:
a processor; and
a memory storing instructions that, when executed by the processor, configure the apparatus to:
receive blockchain transaction data from a blockchain ledger to a transaction database, the blockchain transaction data including blockchain addresses, transaction identifications, transaction timestamps, and digital assets transferred;
receive intelligence labels from a blockchain ecosystem intelligence database, wherein the intelligence labels include known behavioral characteristics of entities associated with the blockchain addresses;
select a blockchain transaction flow comprising blockchain transaction data associated with a digital account source address, digital account intermediate addresses, a digital account destination address, and intermediate transactions, wherein the intermediate transactions transfer the digital assets between the digital account source address and the digital account destination address;
receive input trace parameters, wherein the input trace parameters include at least one of an objective directional setting, a tracing constraint, and a transaction filter, the transaction filter based on the transaction timestamps and the digital assets transferred;
apply the intelligence labels to the digital account source address, the digital account intermediate addresses, and the digital account destination address, thereby creating labeled account addresses;
apply an artificial intelligence graph search algorithm to the blockchain transaction flow based on the input trace parameters, to determine an auto-traced path of the digital assets in the blockchain transaction flow;
generate a report including tracing destination summary statistics of the auto-traced path, the report including suspicious blockchain addresses; and
on condition that the report includes a suspicious blockchain address:
generate an action including at least one of alerting a user of the suspicious blockchain address, alerting the user to an illicit digital asset transaction associated with the suspicious blockchain address, and suspending transactions by the suspicious blockchain address.

### Claim 16 (depends on 15)

The computing apparatus of claim 15, wherein the memory includes at least one of server memory, cloud storage, key value stores, and distributed columnar databases.

### Claim 17 (depends on 15)

The computing apparatus of claim 15, wherein the instructions further configure the apparatus to construct a user interface with interactive visualization of a trace path, the interactive visualization including at least one of:
topological sort to graph layout by the intermediate transactions from the digital account source address to the digital account destination address;
time-bound trace, wherein the trace path is restricted by at least time and a number of intermediate transactions after a specific transaction;
value-bound trace, wherein the trace path is based on is based on values of digital assets transferred in the blockchain transaction flow; and
highlighting of at least a portion of the trace path.

### Claim 18 (depends on 15)

The computing apparatus of claim 15, wherein the report includes at least one of:
a percentage of funding by labeled account address; and
visualization of the auto-traced path from the digital account source address to the digital account destination address, in an expandable interactive view.

### Claim 19 (depends on 15)

The computing apparatus of claim 15, wherein the instructions further configure the apparatus to create an alert timeline, wherein in the alert timeline:
monitors the suspicious blockchain addresses, based on the intelligence labels, with wallets contain funds that have not been transferred; and
creates an alert requesting further investigation of the suspicious blockchain addresses with un-transferred funds.

### Claim 20 (depends on 15)

The computing apparatus of claim 15, wherein the report includes visualization of all digital asset paths from the digital account source address to the digital account destination address, in an expandable interactive view.