Systems, methods, and graphical user interfaces for secure execution of analytical tasks using natural language
A computer-implemented method includes receiving a natural language input including a natural language request for executing an analytical task and processing the natural language input by a language model, where the processing may include translating the natural language input to an analytical function call for calling an analytical function of a set of distinct analytical functions of an analytics computing server. Additionally, the computer-implemented method includes calling the analytical function at the analytics computing server using the analytical function call, receiving a technical output in response to calling the analytical function, and outputting a response to the natural language input that includes the technical analytical output.
1. A computer-program product embodied in a non-transitory machine-readable storage medium storing computer instructions that, when executed by one or more processors, perform operations comprising:
initializing an analytics digital assistant that is implemented using a large language model that interfaces with an analytics compute service, wherein initializing the analytics digital assistant includes:
defining a plurality of distinct resource-forecasting prompts that provides the large language model with instructions for responding to natural language inputs associated with resource forecasting-type analytical tasks, wherein:
each distinct resource-forecasting prompt of the plurality of distinct resource-forecasting prompts associates a distinct resource demand forecasting task to a corresponding resource optimization compute function, and
each distinct resource-forecasting prompt of the plurality of distinct resource-forecasting prompts includes a set of prompt instructions that specifies one or more parameters required to execute the corresponding resource optimization compute function;
receiving, via a graphical user interface associated with the analytics digital assistant, user input that includes a request to execute a target resource demand forecasting task, wherein the graphical user interface includes a dual-panel interface, including:
a first panel configured to display a chatbot-type interface for receiving optimization requests from a user and displaying responses from the analytics digital assistant during a current session, and
a second panel configured to display a summary table of optimization scenarios executed during the current session, wherein each distinct row of the summary table represents a distinct optimization scenario executed during the current session;
identifying, using the large language model associated with the analytics digital assistant, a resource-forecasting prompt of the plurality of distinct resource-forecasting prompts that corresponds to the target resource demand forecasting task;
transmitting, to the analytics compute service associated with the analytics digital assistant, a request to execute a target resource optimization compute function based on the set of prompt instructions and the corresponding resource optimization compute function of the resource-forecasting prompt;
executing, via the analytics compute service, the target resource optimization compute function based on the analytics compute service receiving the request; and
returning, via the graphical user interface of the analytics digital assistant, a response to the user input that includes resource optimization results computed by the analytics compute service for the target resource optimization compute function, wherein returning, via the graphical user interface of the analytics digital assistant, the response to the user input includes:
returning a natural language response to the user input in the chatbot-type interface of the first panel of the dual-panel interface, and
adding, in real-time or near real-time, a new row to the summary table of optimization scenarios based on the resource optimization results computed by the analytics compute service for the target resource optimization compute function.
2. The computer-program product according to claim 1 , wherein:
the target resource demand forecasting task relates to optimizing a utilization rate of a target physical location,
the user input does not include a user-specified utilization rate of the target physical location,
the target resource optimization compute function relates to a utilization optimization compute function that requires a utilization parameter value to be set before executing the utilization optimization compute function, and
executing the target resource optimization compute function includes executing the utilization optimization compute function with a default utilization parameter value based on the user input that does not include the user-specified utilization rate of the target physical location.
3. The computer-program product according to claim 2 , wherein:
the resource optimization results include:
a first proposed resource transfer that specifies a total number of items to transfer from the target physical location to a second physical location,
a second proposed resource transfer that specifies a total number of items to transfer from the second physical location to the target physical location, and
an expected utilization rate of the target physical location after the first proposed resource transfer and the second proposed resource transfer are completed.
4. The computer-program product according to claim 1 , wherein:
the target resource demand forecasting task relates to optimizing a utilization rate of a target physical location,
the user input includes a user-specified utilization rate of the target physical location,
the target resource optimization compute function relates to a utilization optimization compute function that requires a utilization parameter value to be set before executing the utilization optimization compute function,
the computer-program product further comprises computer instructions for performing operations including:
extracting, from the user input, the user-specified utilization rate of the target physical location using the large language model, and
executing the target resource optimization compute function includes executing the utilization optimization compute function with the user-specified utilization rate of the target physical location based on the user input having the user-specified utilization rate of the target physical location.
5. The computer-program product according to claim 1 , wherein:
the target resource demand forecasting task relates to identifying items for transportation from a primary physical storage site to a secondary physical storage site,
the target resource optimization compute function relates to an item transport optimization compute function that determines a set of items to transport from the primary physical storage site to the secondary physical storage site to satisfy a predetermined storage utilization rate of the primary physical storage site,
executing the target resource optimization compute function includes executing, using an optimization model, the item transport optimization compute function, wherein an output of the optimization model includes an outbound item transfer list that specifies one or more item identification numbers and respective item quantities to be transported, and
returning, via the graphical user interface of the analytics digital assistant, the response to the user input further includes presenting the outbound item transfer list in a tabular format.
6. The computer-program product according to claim 1 , wherein:
the target resource demand forecasting task relates to identifying items for transportation from a secondary physical storage site to a primary physical storage site,
the target resource optimization compute function relates to an item transport optimization compute function that determines a set of items to transport from the secondary physical storage site to the primary physical storage site to satisfy a predetermined storage utilization rate of the primary physical storage site,
executing the target resource optimization compute function includes executing, using an optimization model, the item transport optimization compute function, wherein an output of the optimization model includes an inbound item transfer list that specifies one or more item identification numbers and respective item quantities to be transported, and
returning, via the graphical user interface of the analytics digital assistant, the response to the user input further includes presenting the inbound item transfer list in a tabular format.
7. The computer-program product according to claim 1 , wherein:
the target resource demand forecasting task relates to simulating a scenario where future demand increases or decreases by a user-specified demand adjustment value,
the target resource optimization compute function relates to a resource demand forecasting optimization compute function that requires a demand direction parameter and a demand adjustment parameter,
the computer-program product further comprises computer instructions for performing operations including:
identifying, using the large language model, a user-specified demand adjustment value and a user-specified demand direction value from the user input,
converting, using the large language model, the user-specified demand adjustment value into a standardized format compatible with the resource demand forecasting optimization compute function, and
converting, using the large language model, the user-specified demand direction value into the standardized format compatible with the resource demand forecasting optimization compute function; and
executing the target resource optimization compute function includes executing, using an optimization model, the resource demand forecasting optimization compute function with (i) the converted user-specified demand direction value as the demand direction parameter and (ii) the converted user-specified demand adjustment value as the demand adjustment parameter.
8. The computer-program product according to claim 7 , wherein:
the response to the user input includes:
one or more recommended item movement actions based on the scenario simulated, and
an expected utilization rate of a target physical location after the one or more recommended item movement actions are completed.
9. The computer-program product according to claim 1 , wherein:
each distinct row of the summary table of optimization scenarios includes:
an optimization scenario name or optimization scenario identifier for the distinct optimization scenario,
a utilization rate of a target physical storage site before the distinct optimization scenario was executed,
a utilization rate of the target physical storage site after the distinct optimization scenario was executed,
a total quantity of items to transport from the target physical storage site to a secondary physical storage site as determined by the distinct optimization scenario, and
a total quantity of items to transport from the secondary physical storage site to the target physical storage site as determined by the distinct optimization scenario.
10. The computer-program product according to claim 1 , wherein:
each of the plurality of distinct resource-forecasting prompts are associated with a prompt name and a prompt description, and
identifying the resource forecasting prompt of the plurality of distinct resource forecasting-prompts that corresponds to the target resource demand forecasting task includes:
assessing, via the large language model, the user input against the prompt name and the prompt description of the plurality of distinct resource-forecasting prompts, and
detecting, via the large language model, that the prompt name and the prompt description of the resource-forecasting prompt of the plurality of distinct resource-forecasting prompts that corresponds to the target resource demand forecasting task matches the user input with a greater amount of confidence than the prompt name and the prompt description of a remainder of the plurality of distinct resource-forecasting prompts.
11. The computer-program product according to claim 1 , wherein:
the analytics digital assistant uses a first programmatic interface to interact with the large language model,
the analytics digital assistant uses a second programmatic interface to interact with the analytics compute service, and
the large language model and the analytics compute service are separate components that the analytics digital assistant uses to generate the response to the user input.
12. A computer-implemented method comprising:
initializing an analytics digital assistant that is implemented using a large language model that interfaces with an analytics compute service, wherein initializing the analytics digital assistant includes:
defining a plurality of distinct resource-forecasting prompts that provides the large language model with instructions for responding to natural language inputs associated with resource forecasting-type analytical tasks, wherein:
each distinct resource-forecasting prompt of the plurality of distinct resource-forecasting prompts associates a distinct resource demand forecasting task to a corresponding resource optimization compute function, and
each distinct resource-forecasting prompt of the plurality of distinct resource-forecasting prompts includes a set of prompt instructions that specifies one or more parameters required to execute the corresponding resource optimization compute function;
receiving, via a graphical user interface associated with the analytics digital assistant, user input that includes a request to execute a target resource demand forecasting task, wherein the graphical user interface includes a dual-panel interface, including:
a first panel configured to display a chatbot-type interface for receiving optimization requests from a user and displaying responses from the analytics digital assistant during a current session, and
a second panel configured to display a summary table of optimization scenarios executed during the current session, wherein each distinct row of the summary table represents a distinct optimization scenario executed during the current session and includes:
an optimization scenario name or optimization scenario identifier for the distinct optimization scenario,
a utilization rate of a target physical storage site before the distinct optimization scenario was executed,
a utilization rate of the target physical storage site after the distinct optimization scenario was executed,
a total quantity of items to transport from the target physical storage site to a secondary physical storage site as determined by the distinct optimization scenario, and
a total quantity of items to transport from the secondary physical storage site to the target physical storage site as determined by the distinct optimization scenario;
identifying, using the large language model associated with the analytics digital assistant, a resource-forecasting prompt of the plurality of distinct resource-forecasting prompts that corresponds to the target resource demand forecasting task;
transmitting, to the analytics compute service associated with the analytics digital assistant, a request to execute a target resource optimization compute function based on the set of prompt instructions and the corresponding resource optimization compute function of the resource-forecasting prompt;
executing, via the analytics compute service, the target resource optimization compute function based on the analytics compute service receiving the request; and
returning, via the graphical user interface of the analytics digital assistant, a response to the user input that includes resource optimization results computed by the analytics compute service for the target resource optimization compute function.
13. The computer-implemented method according to claim 12 , wherein:
the target resource demand forecasting task relates to optimizing a utilization rate of a target physical location,
the user input does not include a user-specified utilization rate of the target physical location,
the target resource optimization compute function relates to a utilization optimization compute function that requires a utilization parameter value to be set before executing the utilization optimization compute function, and
executing the target resource optimization compute function includes executing the utilization optimization compute function with a default utilization parameter value based on the user input that does not include the user-specified utilization rate of the target physical location.
14. The computer-implemented method according to claim 13 , wherein:
the resource optimization results include:
a first proposed resource transfer that specifies a total number of items to transfer from the target physical location to a second physical location,
a second proposed resource transfer that specifies a total number of items to transfer from the second physical location to the target physical location, and
an expected utilization rate of the target physical location after the first proposed resource transfer and the second proposed resource transfer are completed.
15. The computer-implemented method according to claim 12 , wherein:
the target resource demand forecasting task relates to optimizing a utilization rate of a target physical location,
the user input includes a user-specified utilization rate of the target physical location,
the target resource optimization compute function relates to a utilization optimization compute function that requires a utilization parameter value to be set before executing the utilization optimization compute function,
the computer-implemented method further comprises:
extracting, from the user input, the user-specified utilization rate of the target physical location using the large language model, and
executing the target resource optimization compute function includes executing the utilization optimization compute function with the user-specified utilization rate of the target physical location based on the user input having the user-specified utilization rate of the target physical location.
16. The computer-implemented method according to claim 12 , wherein:
the target resource demand forecasting task relates to identifying items for transportation from a primary physical storage site to a secondary physical storage site,
the target resource optimization compute function relates to an item transport optimization compute function that determines a set of items to transport from the primary physical storage site to the secondary physical storage site to satisfy a predetermined storage utilization rate of the primary physical storage site,
executing the target resource optimization compute function includes executing, using an optimization model, the item transport optimization compute function, wherein an output of the optimization model includes an outbound item transfer list that specifies one or more item identification numbers and respective item quantities to be transported, and
returning, via the graphical user interface of the analytics digital assistant, the response to the user input further includes presenting the outbound item transfer list in a tabular format.
17. The computer-implemented method according to claim 12 , wherein:
the target resource demand forecasting task relates to identifying items for transportation from a secondary physical storage site to a primary physical storage site,
the target resource optimization compute function relates to an item transport optimization compute function that determines a set of items to transport from the secondary physical storage site to the primary physical storage site to satisfy a predetermined storage utilization rate of the primary physical storage site,
executing the target resource optimization compute function includes executing, using an optimization model, the item transport optimization compute function, wherein an output of the optimization model includes an inbound item transfer list that specifies one or more item identification numbers and respective item quantities to be transported, and
returning, via the graphical user interface of the analytics digital assistant, the response to the user input further includes presenting the inbound item transfer list in a tabular format.
18. The computer-implemented method according to claim 12 , wherein:
the target resource demand forecasting task relates to simulating a scenario where future demand increases or decreases by a user-specified demand adjustment value,
the target resource optimization compute function relates to a resource demand forecasting optimization compute function that requires a demand direction parameter and a demand adjustment parameter,
the computer-implemented method further comprises:
identifying, using the large language model, a user-specified demand adjustment value and a user-specified demand direction value from the user input,
converting, using the large language model, the user-specified demand adjustment value into a standardized format compatible with the resource demand forecasting optimization compute function, and
converting, using the large language model, the user-specified demand direction value into the standardized format compatible with the resource demand forecasting optimization compute function; and
executing the target resource optimization compute function includes executing, using an optimization model, the resource demand forecasting optimization compute function with (i) the converted user-specified demand direction value as the demand direction parameter and (ii) the converted user-specified demand adjustment value as the demand adjustment parameter.
19. The computer-implemented method according to claim 18 , wherein:
the response to the user input includes:
one or more recommended item movement actions based on the scenario simulated, and
an expected utilization rate of a target physical location after the one or more recommended item movement actions are completed.
20. The computer-implemented method according to claim 12 , wherein:
returning, via the graphical user interface of the analytics digital assistant, the response to the user input includes:
returning a natural language response to the user input in the chatbot-type interface of the first panel of the dual-panel interface, and
adding, in real-time or near real-time, a new row to the summary table of optimization scenarios based on the resource optimization results computed by the analytics compute service for the target resource optimization compute function.
21. The computer-implemented method according to claim 12 , wherein:
each of the plurality of distinct resource-forecasting prompts are associated with a prompt name and a prompt description, and
identifying the resource forecasting prompt of the plurality of distinct resource forecasting-prompts that corresponds to the target resource demand forecasting task includes:
assessing, via the large language model, the user input against the prompt name and the prompt description of the plurality of distinct resource-forecasting prompts, and
detecting, via the large language model, that the prompt name and the prompt description of the resource-forecasting prompt of the plurality of distinct resource-forecasting prompts that corresponds to the target resource demand forecasting task matches the user input with a greater amount of confidence than the prompt name and the prompt description of a remainder of the plurality of distinct resource-forecasting prompts.
22. The computer-implemented method according to claim 12 , wherein:
the analytics digital assistant uses a first programmatic interface to interact with the large language model,
the analytics digital assistant uses a second programmatic interface to interact with the analytics compute service, and
the large language model and the analytics compute service are separate components that the analytics digital assistant uses to generate the response to the user input.
23. A computer-implemented system comprising:
one or more processors;
a memory;
a computer-readable medium operably coupled to the one or more processors, the computer-readable medium having computer-readable instructions stored thereon that, when executed by the one or more processors, cause a computing device to perform operations comprising:
initializing an analytics digital assistant that is implemented using a large language model that interfaces with an analytics compute service, wherein initializing the analytics digital assistant includes:
defining a plurality of distinct resource-forecasting prompts that provides the large language model with instructions for responding to natural language inputs associated with resource forecasting-type analytical tasks, wherein:
each distinct resource-forecasting prompt of the plurality of distinct resource-forecasting prompts associates a distinct resource demand forecasting task to a corresponding resource optimization compute function, and
each distinct resource-forecasting prompt of the plurality of distinct resource-forecasting prompts includes a set of prompt instructions that specifies one or more parameters required to execute the corresponding resource optimization compute function;
receiving, via a graphical user interface associated with the analytics digital assistant, user input that includes a request to execute a target resource demand forecasting task, wherein:
the target resource demand forecasting task relates to optimizing a utilization rate of a target physical location, and
the user input does not include a user-specified utilization rate of the target physical location;
identifying, using the large language model associated with the analytics digital assistant, a resource-forecasting prompt of the plurality of distinct resource-forecasting prompts that corresponds to the target resource demand forecasting task;
transmitting, to the analytics compute service associated with the analytics digital assistant, a request to execute a target resource optimization compute function based on the set of prompt instructions and the corresponding resource optimization compute function of the resource-forecasting prompt, wherein the target resource optimization compute function relates to a utilization optimization compute function that requires a utilization parameter value to be set before executing the utilization optimization compute function;
executing, via the analytics compute service, the target resource optimization compute function based on the analytics compute service receiving the request, wherein executing the target resource optimization compute function includes executing the utilization optimization compute function with a default utilization parameter value based on the user input that does not include the user-specified utilization rate of the target physical location; and
returning, via the graphical user interface of the analytics digital assistant, a response to the user input that includes resource optimization results computed by the analytics compute service for the target resource optimization compute function.
24. The computer-implemented system according to claim 23 , wherein:
the resource optimization results include:
a first proposed resource transfer that specifies a total number of items to transfer from the target physical location to a second physical location,
a second proposed resource transfer that specifies a total number of items to transfer from the second physical location to the target physical location, and
an expected utilization rate of the target physical location after the first proposed resource transfer and the second proposed resource transfer are completed.
25. A computer-program product embodied in a non-transitory machine-readable storage medium storing computer instructions that, when executed by one or more processors, perform operations comprising:
initializing an analytics digital assistant that is implemented using a large language model that interfaces with an analytics compute service, wherein initializing the analytics digital assistant includes:
defining a plurality of distinct resource-forecasting prompts that provides the large language model with instructions for responding to natural language inputs associated with resource forecasting-type analytical tasks, wherein:
each distinct resource-forecasting prompt of the plurality of distinct resource-forecasting prompts associates a distinct resource demand forecasting task to a corresponding resource optimization compute function, and
each distinct resource-forecasting prompt of the plurality of distinct resource-forecasting prompts includes a set of prompt instructions that specifies one or more parameters required to execute the corresponding resource optimization compute function;
receiving, via a graphical user interface associated with the analytics digital assistant, user input that includes a request to execute a target resource demand forecasting task, wherein the target resource demand forecasting task relates to simulating a scenario where future demand increases or decreases by a user-specified demand adjustment value;
identifying, using the large language model associated with the analytics digital assistant, a resource-forecasting prompt of the plurality of distinct resource-forecasting prompts that corresponds to the target resource demand forecasting task;
transmitting, to the analytics compute service associated with the analytics digital assistant, a request to execute a target resource optimization compute function based on the set of prompt instructions and the corresponding resource optimization compute function of the resource-forecasting prompt, wherein the target resource optimization compute function relates to a resource demand forecasting optimization compute function that requires a demand direction parameter and a demand adjustment parameter;
identifying, using the large language model, a user-specified demand adjustment value and a user-specified demand direction value from the user input;
converting, using the large language model, the user-specified demand adjustment value into a standardized format compatible with the resource demand forecasting optimization compute function;
converting, using the large language model, the user-specified demand direction value into the standardized format compatible with the resource demand forecasting optimization compute function;
executing, via the analytics compute service, the target resource optimization compute function based on the analytics compute service receiving the request, wherein executing the target resource optimization compute function includes executing, using an optimization model, the resource demand forecasting optimization compute function with (i) the converted user-specified demand direction value as the demand direction parameter and (ii) the converted user-specified demand adjustment value as the demand adjustment parameter; and
returning, via the graphical user interface of the analytics digital assistant, a response to the user input that includes resource optimization results computed by the analytics compute service for the target resource optimization compute function.
26. The computer-program product according to claim 25 , wherein:
the response to the user input includes:
one or more recommended item movement actions based on the scenario simulated, and
an expected utilization rate of a target physical location after the one or more recommended item movement actions are completed.
27. The computer-program product according to claim 25 , wherein:
the graphical user interface includes a dual-panel interface, including:
a first panel configured to display a chatbot-type interface for receiving optimization requests from a user and displaying responses from the analytics digital assistant during a current session, and
a second panel configured to display a summary table of optimization scenarios executed during the current session, wherein each distinct row of the summary table represents a distinct optimization scenario executed during the current session.
28. The computer-program product according to claim 27 , wherein:
each distinct row of the summary table of optimization scenarios includes:
an optimization scenario name or optimization scenario identifier for the distinct optimization scenario,
a utilization rate of a target physical storage site before the distinct optimization scenario was executed,
a utilization rate of the target physical storage site after the distinct optimization scenario was executed,
a total quantity of items to transport from the target physical storage site to a secondary physical storage site as determined by the distinct optimization scenario, and
a total quantity of items to transport from the secondary physical storage site to the target physical storage site as determined by the distinct optimization scenario.
29. The computer-program product according to claim 27 , wherein:
returning, via the graphical user interface of the analytics digital assistant, the response to the user input includes:
returning a natural language response to the user input in the chatbot-type interface of the first panel of the dual-panel interface, and
adding, in real-time or near real-time, a new row to the summary table of optimization scenarios based on the resource optimization results computed by the analytics compute service for the target resource optimization compute function.
30. The computer-program product according to claim 25 , wherein:
each of the plurality of distinct resource-forecasting prompts are associated with a prompt name and a prompt description, and
identifying the resource-forecasting prompt of the plurality of distinct resource forecasting-prompts that corresponds to the target resource demand forecasting task includes:
assessing, via the large language model, the user input against the prompt name and the prompt description of the plurality of distinct resource-forecasting prompts, and
detecting, via the large language model, that the prompt name and the prompt description of the resource-forecasting prompt of the plurality of distinct resource-forecasting prompts that corresponds to the target resource demand forecasting task matches the user input with a greater amount of confidence than the prompt name and the prompt description of a remainder of the plurality of distinct resource-forecasting prompts.