SYSTEMS AND METHODS FOR IDENTIFYING PATTERNS IN BLOCKCHAIN ACTIVITIES

1 . A system for identifying patterns in blockchain activities based on multi-modal data using artificial intelligence models that compensate for training data featuring a high proportion of missing data points, the system comprising:

one or more processors; and

one or more non-transitory, computer-readable media comprising instructions that when executed by the one or more processors cause operations comprising:

receiving a target blockchain activity and blockchain activity record data for a plurality of blockchain activities involving a plurality of blockchain accounts;

generating for display, in a user interface, a visualization of the target blockchain activity using an artificial intelligence model, wherein the artificial intelligence model is trained to identify serial relationships of related blockchain activities corresponding to inputted target blockchain activities based on proportions of digital assets at subsets of blockchain accounts of the plurality of blockchain accounts, and wherein the visualization comprises a subset of serial blockchain activities that correspond to the target blockchain activity;

determining that a first blockchain activity in the subset of serial blockchain activities corresponds to a first type of a plurality of types of blockchain activities;

retrieving a filtering criterion for the visualization;

applying the filtering criterion to the first type; and

in response to determining that the first type does not corresponds to the filtering criterion, generating for display, in the visualization, a first icon corresponding to the first blockchain activity.

2 . A method for identifying patterns in blockchain activities based on multi-modal data using artificial intelligence models that compensate for training data featuring a high proportion of missing data points, the method comprising:

receiving a target blockchain activity and blockchain activity record data for a plurality of blockchain activities involving a plurality of blockchain accounts;

generating for display, in a user interface, a visualization of the target blockchain activity using an artificial intelligence model, wherein the artificial intelligence model is trained to identify serial relationships of related blockchain activities corresponding to inputted target blockchain activities based on proportions of digital assets at subsets of blockchain accounts of the plurality of blockchain accounts, and wherein the visualization comprises a subset of serial blockchain activities that correspond to the target blockchain activity;

determining that a first blockchain activity in the subset of serial blockchain activities corresponds to a first type of a plurality of types of blockchain activities;

retrieving a filtering criterion for the visualization;

applying the filtering criterion to the first type; and

in response to determining that the first type does not corresponds to the filtering criterion, generating for display, in the visualization, a first icon corresponding to the first blockchain activity.

3 . The method of claim 2 , further comprising:

determining, using the artificial intelligence model, a respective proportion of digital assets corresponding to each blockchain activity in the plurality of blockchain activities; and

based on the respective proportion, determining, using the artificial intelligence model, that the first blockchain activity is included in the subset of serial blockchain activities.

4 . The method of claim 2 , further comprising:

generating a feature input based on the blockchain activity record data and the target blockchain activity; and

inputting the feature input into the artificial intelligence model to generate an output.

5 . The method of claim 3 , wherein determining that the first blockchain activity is included in the subset of serial blockchain activities further comprising:

determining that the first blockchain activity corresponds to a first blockchain account;

determining that the first blockchain account corresponds to a first type of a plurality of types of blockchain accounts;

in response to determining that the first blockchain account corresponds to the first type of the plurality of types of blockchain accounts, retrieving a second filtering criterion for the visualization;

applying the second filtering criterion to the first type of the plurality of types of blockchain accounts; and

in response to determining that the first type does not correspond to the filtering criterion, generating for display, in the visualization, a second icon corresponding to the first blockchain activity.

6 . The method of claim 2 , further comprising:

determining, using the artificial intelligence model, a subset of blockchain accounts of the plurality of blockchain accounts corresponding to the target blockchain activity;

determining, using the artificial intelligence model, a respective proportion of digital assets corresponding to each blockchain account in the subset of blockchain accounts; and

based on the respective proportion, determining, using the artificial intelligence model, that a first blockchain account in the subset of blockchain accounts corresponds to the target blockchain activity.

7 . The method of claim 6 , further comprising:

in response to determining that the first blockchain account in the subset of blockchain accounts corresponds to the target blockchain activity, retrieving a filtering criterion for the visualization;

applying the filtering criterion to a characteristic of the first blockchain account; and

in response to determining that the characteristic does not correspond to the filtering criterion, generating for display, in the visualization, a first icon corresponding to the first blockchain account.

8 . The method of claim 7 , further comprising:

determining an amount of a digital asset corresponding to the target blockchain activity; and

determining the filtering criterion based on a percentage of the amount.

9 . The method of claim 2 , wherein the artificial intelligence model is further trained based on non-blockchain record data for a plurality of entities linked to one or more of the plurality of blockchain accounts, and wherein a feature input for the artificial intelligence model comprises information retrieved from a third party source.

10 . The method of claim 2 , wherein generating the visualization further comprises:

generating for display, in the user interface, a plurality of icons corresponding to blockchain accounts corresponding to the subset of serial blockchain activities; and

generating a plurality of lines connecting the plurality of icons, wherein the plurality of lines represent characteristics of the subset of serial blockchain activities.

11 . The method of claim 2 , wherein the subset of serial blockchain activities comprise a first subset of blockchain activities on a first blockchain network, and a second subset of blockchain activities on a second blockchain network.

12 . A non-transitory, computer-readable medium, comprising instructions that, when executed by one or more processors, cause operations comprising:

receiving a target blockchain activity and blockchain activity record data for a plurality of blockchain activities involving a plurality of blockchain accounts;

generating for display, in a user interface, a visualization of the target blockchain activity using an artificial intelligence model, wherein the artificial intelligence model is trained to identify serial relationships of related blockchain activities corresponding to inputted target blockchain activities based on proportions of digital assets at subsets of blockchain accounts of the plurality of blockchain accounts, and wherein the visualization comprises a subset of serial blockchain activities that correspond to the target blockchain activity;

determining that a first blockchain activity in the subset of serial blockchain activities corresponds to a first type of a plurality of types of blockchain activities;

retrieving a filtering criterion for the visualization;

applying the filtering criterion to the first type; and

in response to determining that the first type does not corresponds to the filtering criterion, generating for display, in the visualization, a first icon corresponding to the first blockchain activity.

13 . The non-transitory, computer-readable medium of claim 12 , wherein the instructions further cause operations comprising:

determining, using the artificial intelligence model, a respective proportion of digital assets corresponding to each blockchain activity in the plurality of blockchain activities; and

based on the respective proportion, determining, using the artificial intelligence model, that the first blockchain activity is included in the subset of serial blockchain activities.

14 . The non-transitory, computer-readable medium of claim 12 , wherein the instructions further cause operations comprising:

generating a feature input based on the blockchain activity record data and the target blockchain activity; and

inputting the feature input into the artificial intelligence model to generate an output.

15 . The non-transitory, computer-readable medium of claim 13 , wherein determining that the first blockchain activity is included in the subset of serial blockchain activities further comprises:

determining that the first blockchain activity corresponds to a first blockchain account;

determining that the first blockchain account corresponds to a first type of a plurality of types of blockchain accounts;

in response to determining that the first blockchain account corresponds to the first type of the plurality of types of blockchain accounts, retrieving a second filtering criterion for the visualization;

applying the second filtering criterion to the first type of the plurality of types of blockchain accounts; and

in response to determining that the first type of the plurality of types of blockchain accounts does not corresponds to the second filtering criterion, generating for display, in the visualization, a second icon corresponding to the first blockchain activity.

16 . The non-transitory, computer-readable medium of claim 12 , wherein the instructions further cause operations comprising:

determining, using the artificial intelligence model, a subset of blockchain accounts of the plurality of blockchain accounts corresponding to the target blockchain activity;

determining, using the artificial intelligence model, a respective proportion of digital assets corresponding to each blockchain account in the subset of blockchain accounts; and

based on the respective proportion, determining, using the artificial intelligence model, that a first blockchain account in the subset of blockchain accounts corresponds to the target blockchain activity.

17 . The non-transitory, computer-readable medium of claim 16 , wherein the instructions further cause operations comprising:

in response to determining that the first blockchain account in the subset of blockchain accounts corresponds to the target blockchain activity, retrieving a filtering criterion for the visualization;

applying the filtering criterion to a characteristic of the first blockchain account; and

in response to determining that the characteristic does not correspond to the filtering criterion, generating for display, in the visualization, a first icon corresponding to the first blockchain account.

18 . The non-transitory, computer-readable medium of claim 17 , wherein the instructions further cause operations comprising:

determining an amount of a digital asset corresponding to the target blockchain activity; and

determining the filtering criterion based on a percentage of the amount.

19 . The non-transitory, computer-readable medium of claim 12 , wherein the artificial intelligence model is further trained based on non-blockchain record data for a plurality of entities linked to one or more of the plurality of blockchain accounts, and wherein a feature input for the artificial intelligence model comprises information retrieved from a third party source.

20 . The non-transitory, computer-readable medium of claim 12 , wherein generating the visualization further comprises:

generating for display, in the user interface, a plurality of icons corresponding to blockchain accounts corresponding to the subset of serial blockchain activities; and

generating a plurality of lines connecting the plurality of icons, wherein the plurality of lines represent characteristics of the subset of serial blockchain activities.