SYSTEMS AND METHODS OF USING A TRANSFERRABLE TOKEN FOR GIG-ECONOMY ACTIVITY ASSESSMENT
Systems and methods relating to improving the experience of gig-economy workers are disclosed, with particular reference to gig-economy work involving vehicle use. Such systems and methods include automatically monitoring and evaluating activities such as driving during performance of gigs, as well as providing recommendations based thereupon. Transferable tokens may be used to apply information across various types of gig activities. Such a transferable token may represent one or more risk levels associated with a gig-economy worker to provide reputational information between gig-economy platforms or between types of gig-economy activities. Thus, the transferable token may enable a gig-economy worker to transfer high customer ratings across gig-economy platforms.
1 . A computer-implemented method for generating a transferable token for a gig-economy worker, the method comprising:
sending, by a data collector implemented by one or more processors, a data request message to a gig-economy data source associated with a gig-economy platform;
obtaining, by a data collector application programming interface (API) of the data collector, gig performance data comprising gig metrics indicating aspects of performance of a plurality of gig-related tasks by the gig-economy worker in response to the data request message;
providing, by the data collector, the gig performance data associated with the gig-economy worker to a token generator implemented by the one or more processors;
applying, by the token generator, a machine learning model to the gig performance data to generate one or more metrics indicative of risk levels associated with performance of gig-related tasks by the gig-economy worker;
generating, by the token generator, a transferable token comprising a plurality of structured data entries storing indications of the one or more metrics associated with the gig-economy worker;
storing, in a data store, the transferable token associated with the gig-economy worker;
receiving, by a token request API implemented by the one or more processors, a token request message identifying the gig-economy worker from a token consumer; and
sending, by the token request API, the transferable token associated with the gig-economy worker to the token consumer.
2 . The computer-implemented method of claim 1 , further comprising:
receiving, by the data collector API, an authorization message from a user device associated with the gig-economy worker indicating permission of the gig-economy worker to generate the transferable token,
wherein the data request message is sent in response to the authorization message.
3 . The computer-implemented method of claim 1 , further comprising:
sending, by the data collector, an additional data request message to an additional data source; and
obtaining, by the data collector API, non-gig data regarding the gig-economy worker from the additional data source in response to the additional data request message, wherein the non-gig data comprises general risk-related data unrelated to performance of gig tasks, and
wherein applying the machine learning model to the gig performance data includes applying the machine learning model to the non-gig data.
4 . The computer-implemented method of claim 1 , wherein the one or more metrics comprise a reputation score for the gig-economy worker based upon a plurality of ratings received by the gig-economy worker for performance of respective gig-related tasks.
5 . The computer-implemented method of claim 1 , wherein the one or more metrics comprise a plurality of risk-related scores forming a risk profile of the gig-economy worker.
6 . The computer-implemented method of claim 5 , wherein the plurality of risk-related scores comprise a first risk level associated with performance of a first type of gig-economy work by the gig-economy worker and a second risk level associated with performance of a second type of gig-economy work by the gig-economy worker.
7 . The computer-implemented method of claim 1 , wherein the one or more metrics comprise a risk modifier score indicating a relative risk level for the gig-economy worker relative to a baseline risk level associated with a plurality of other gig-economy workers.
8 . The computer-implemented method of claim 1 , wherein the gig metrics comprise telematics data metrics indicative of driving behaviors of the gig-economy worker to control operation of one or more vehicles during a plurality of vehicle trips during performance of the plurality of gig-related tasks.
9 . The computer-implemented method of claim 1 , further comprising:
sending, by the data collector, a second data request message to the gig-economy data source following generation of the transferable token;
obtaining, by the data collector API, additional gig performance data associated with the gig-economy worker in response to the second data request message;
applying, by the data collector, the machine learning model to the gig performance data and the additional gig performance data to generate one or more updated metrics indicative of updated risk levels associated with performance of gig-related tasks by the gig-economy worker;
updating, by the token generator, the plurality of structured data entries of transferable token based upon the one or more updated metrics.
10 . A computer system for generating a transferable token for a gig-economy worker, the system comprising:
one or more processors;
a program memory coupled to the one or more processors and storing executable instructions that, when executed by the one or more processors, cause the computer system to:
send, by a data collector, a data request message to a gig-economy data source associated with a gig-economy platform;
obtain, by a data collector application programming interface (API) of the data collector, gig performance data comprising gig metrics indicating aspects of performance of a plurality of gig-related tasks by the gig-economy worker in response to the data request message;
provide, by the data collector, the gig performance data associated with the gig-economy worker to a token generator;
apply, by the token generator, a machine learning model to the gig performance data to generate one or more metrics indicative of risk levels associated with performance of gig-related tasks by the gig-economy worker;
generate, by the token generator, the transferable token comprising a plurality of structured data entries storing indications of the one or more metrics associated with the gig-economy worker;
store, in a data store, the transferable token associated with the gig-economy worker;
receive, by a token request API, a token request message identifying the gig-economy worker from a token consumer; and
send, by the token request API, the transferable token associated with the gig-economy worker to the token consumer.
11 . The computer system of claim 10 , wherein the one or more metrics comprise a plurality of risk-related scores forming a risk profile of the gig-economy worker, the plurality of risk-related scores comprising a first risk level associated with performance of a first type of gig-economy work by the gig-economy worker and a second risk level associated with performance of a second type of gig-economy work by the gig-economy worker.
12 . The computer system of claim 10 , wherein the one or more metrics comprise a risk modifier score indicating a relative risk level for the gig-economy worker relative to a baseline risk level associated with a plurality of other gig-economy workers.
13 . The computer system of claim 10 , wherein the gig metrics comprise telematics data metrics indicative of driving behaviors of the gig-economy worker to control operation of one or more vehicles during a plurality of vehicle trips during performance of the plurality of gig-related tasks.
14 . A non-transitory computer-readable storage medium comprising computer-readable instructions for generating a transferable token for a gig-economy worker that, when executed by one or more processors of a computer system, cause the computer system to:
send, by a data collector, a data request message to a gig-economy data source associated with a gig-economy platform;
obtain, by a data collector application programming interface (API) of the data collector, gig performance data comprising gig metrics indicating aspects of performance of a plurality of gig-related tasks by the gig-economy worker in response to the data request message;
provide, by the data collector, the gig performance data associated with the gig-economy worker to a token generator;
apply, by the token generator, a machine learning model to the gig performance data to generate one or more metrics indicative of risk levels associated with performance of gig-related tasks by the gig-economy worker;
generate, by the token generator, the transferable token comprising a plurality of structured data entries storing indications of the one or more metrics associated with the gig-economy worker;
store, in a data store, the transferable token associated with the gig-economy worker;
receive, by a token request API, a token request message identifying the gig-economy worker from a token consumer; and
send, by the token request API, the transferable token associated with the gig-economy worker to the token consumer.
15 . The non-transitory computer-readable storage medium of claim 14 , wherein:
the computer-readable instructions, when executed by the one or more processors, cause the computer system to receive, by the data collector API, an authorization message from a user device associated with the gig-economy worker indicating permission of the gig-economy worker to generate the transferable token; and
wherein the computer-readable instructions that cause the computer system to send the data request message cause the computer system to send the data request message in response to receiving the authorization message.
16 . The non-transitory computer-readable storage medium of claim 14 , wherein:
the computer-readable instructions, when executed by the one or more processors, cause the computer system to:
send, by the data collector, an additional data request message to an additional data source; and
obtain, by the data collector API, non-gig data regarding the gig-economy worker from the additional data source in response to the additional data request message,
wherein the non-gig data comprises general risk-related data unrelated to performance of gig tasks; and
wherein the computer-readable instructions that cause the computer system to apply the machine learning model to the gig performance data cause the computer system to apply the machine learning model to the non-gig data.
17 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more metrics comprise a reputation score for the gig-economy worker based upon a plurality of ratings received by the gig-economy worker for performance of respective gig-related tasks.
18 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more metrics comprise a plurality of risk-related scores forming a risk profile of the gig-economy worker, the plurality of risk-related scores comprising a first risk level associated with performance of a first type of gig-economy work by the gig-economy worker and a second risk level associated with performance of a second type of gig-economy work by the gig-economy worker.
19 . The non-transitory computer-readable storage medium of claim 14 , wherein the one or more metrics comprise a risk modifier score indicating a relative risk level for the gig-economy worker relative to a baseline risk level associated with a plurality of other gig-economy workers.
20 . The non-transitory computer-readable storage medium of claim 14 , wherein the gig metrics comprise telematics data metrics indicative of driving behaviors of the gig-economy worker to control operation of one or more vehicles during a plurality of vehicle trips during performance of the plurality of gig-related tasks.