Intuitive data retrieval and visualization with large language models and logic programming
The present disclosure is directed to automatically generating estimation reports of an online audience. In particular, the system can include a server having a first dataset with a plurality of dimensions. Additionally, the system can receive, from a client device, a query request to estimate the online audience of the content item. The system can process, using a first machine-learned model, the query request to generate a configuration file associated with the first dataset. Moreover, the system can present, on a user interface of a client device, the configuration file. Furthermore, the system can receive a user input in response to the presentation of the configuration file and retrieve data from the first dataset based on the configuration file and the user input. Subsequently, the system can generate, using the first machine-learned model, the report based on the retrieved data from the first dataset.
1. A computing system configured to generate a report estimating an online audience of a content item, the computing system comprising:
one or more processors; and
a server having a first dataset, the first dataset having a plurality of dimensions;
one or more computer-readable media that store computer-readable instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:
receiving, from a client device, a query request to estimate the online audience of the content item;
processing, using a first machine-learned model, the query request to generate a configuration file associated with the first dataset, the configuration file having a first dimension from the plurality of dimensions;
presenting, on a user interface of the client device, the configuration file;
processing, using the first machine-learned model, the configuration file to generate the report concurrently while presenting the configuration file on the user interface of the client device;
receiving a user input in response to the presentation of the configuration file;
retrieving data from the first dataset based on the configuration file and the user input; and
generating, using the first machine-learned model, the report based on the retrieved data from the first dataset.
2. The computing system of claim 1 , wherein the user input changes the configuration file, the operations further comprising:
updating the configuration file based on the user input;
compiling the updated configuration file into a logic programming rule, the logic programming rule having a predicate, the predicate being associated with the first dimension; and
compiling the logic programming rule into a database query of the server, wherein the report is generated based on data retrieved from the first dataset using the database query, and wherein the data retrieved is filtered based on the first dimension.
3. The computing system of claim 2 , wherein the user input changes a parameter of the first dimension in the configuration file.
4. The computing system of claim 1 , wherein the user input changes the first dimension in the configuration file to a second dimension.
5. The computing system of claim 1 , wherein the user input is a confirmation that the configuration file is accurate, the operations further comprising:
compiling the configuration file into a logic programming rule, the logic programming rule having a predicate, the predicate being associated with the first dimension; and
compiling the logic programming rule into a database query of the server, wherein the report is generated based on data retrieved from the first dataset using the database query.
6. The computing system of claim 5 , wherein the data retrieved is filtered based on the first dimension.
7. The computing system of claim 1 , wherein the first dimension is a date.
8. The computing system of claim 1 , wherein the first dimension is a device type.
9. The computing system of claim 1 , wherein the first dimension is a country.
10. The computing system of claim 1 , wherein the configuration file includes a predicate associated with the first dimension and a measure.
11. The computing system of claim 10 , wherein the measure is an impression of a content item.
12. The computing system of claim 10 , wherein the measure is a reach associated with a content item.
13. The computing system of claim 1 , wherein the report is a line chart, a pie chart, or a table.
14. The computing system of claim 1 , wherein the server includes a plurality of datasets, the operations further comprising:
determining, using the first machine-learned model, to retrieve data from the first dataset in the plurality of dataset based on the query request.
15. The computing system of claim 1 , wherein the computing system includes a plurality of machine-learned models, the operations further comprising:
selecting the first machine-learned model from the plurality of machine-learned models based on the query request.
16. The computing system of claim 15 , the operations further comprising:
selecting a second machine-learned model from the plurality of machine-learned models based on the query request;
generating, using the second machine-learned model, a second report based on the retrieved data; and
presenting, on the user interface of the client device, a comparison of the report and the second report.
17. The computing system of claim 1 , wherein the configuration file includes a parameter associated with the first dimension, wherein the data retrieved from the first dataset is filtered based on the parameter associated with the first dimension.
18. The computing system of claim 1 , wherein the configuration file is different based on different datasets.
19. A computer-implemented method for generating a report, the method comprising:
receiving, by one or more computing devices, a query request from a client device;
processing, using a first machine-learned model, the query request to generate a configuration file associated with a first dataset, the configuration file having a first dimension from a plurality of dimensions;
presenting, on a user interface of the client device, the configuration file;
processing, using the first machine-learned model, the configuration file to generate the report concurrently while presenting the configuration file on the user interface of the client device;
receiving a user input in response to the presentation of the configuration file;
retrieving data from the first dataset based on the configuration file and the user input; and
generating, using the first machine-learned model, the report based on the retrieved data from the first dataset.
20. One or more non-transitory computer-readable media comprising instructions that when executed by one or more computing devices cause the one or more computing devices to perform operations comprising:
receiving a query request from a client device;
processing, using a first machine-learned model, the query request to generate a configuration file associated with a first dataset, the configuration file having a first dimension from a plurality of dimensions;
presenting, on a user interface of the client device, the configuration file;
processing, using the first machine-learned model, the configuration file to generate the report concurrently while presenting the configuration file on the user interface of the client device;
receiving a user input in response to the presentation of the configuration file;
retrieving data from the first dataset based on the configuration file and the user input; and
generating, using the first machine-learned model, a report based on the retrieved data from the first dataset.