Techniques for automatic generation of reports based on organizational data
Techniques for automatically generating reports based on organizational data. For example, a computer system can include a database of organizational data associated with the organization. The organizational data includes a plurality of employee data objects and a plurality of previously generated report configuration files. The system can include a machine-learned model configured to generate a report configuration file based on a prompt. The machine-learned model can be trained using the plurality of previously generated report configuration files. The system can receive a user query requesting a report associated with the organizational data. Additionally, the system can process, using a natural language processing model, the user query and the employee data objects to generate a prompt. Moreover, the system can process, by the machine-learned model, the prompt and the organizational data to generate a report configuration file. Furthermore, the system can generate the report based on the report configuration file.
1. A computer system that automatically generates an output based on organizational data of an organization, the computer system comprising:
one or more processors; and
one or more databases that collectively store the organizational data associated with the organization, wherein the organizational data comprising a plurality of employee data objects that respectively correspond to a plurality of employees of the organization, and a plurality of previously generated report configuration files; and
a machine-learned model, wherein the machine-learned model is configured to generate a report configuration file based on a prompt, the machine-learned model being trained using the plurality of previously generated report configuration files;
one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computer system to perform operations, the operations comprising:
receiving a user query requesting a report associated with the organizational data;
processing, using a natural language processing model, the user query and the employee data objects to generate a prompt;
processing, by the machine-learned model, the prompt and the organizational data to generate a first report configuration file;
determining that a parameter of the first report configuration file is incorrect based on the comparison of the first report configuration file with the plurality of previously generated report configuration files;
updating the parameter of the first report configuration file prior to the processing of the first report configuration file to generate the report; and
generating the report based on the first report configuration file.
2. The system of claim 1 , wherein the operations further comprise:
determining whether the first report configuration file is validated by comparing the first report configuration file with the plurality of previously generated report configuration files.
3. The system of claim 2 , wherein the operations further comprise:
processing the first report configuration file to generate the report when determined that the first report configuration file is validated.
4. The system of claim 2 , wherein the operations further comprise:
selecting, from a plurality of template configuration files, a second report configuration file to generate the report when determined that the first report configuration is not validated.
5. The system of claim 4 , wherein the plurality of template configuration files has been previously generated and stored a database of the organizational management platform.
6. The system of claim 1 , wherein the first report configuration file has a parameter that is associated with an attribute of the employee data objects.
7. The system of claim 1 , wherein the report is a chart.
8. The system of claim 1 , wherein the operations further comprise:
presenting the report on a graphical user interface;
receiving user feedback in response to the presentation of the report;
updating the first report configuration file based on the user feedback; and
presenting an updated report on the graphical user interface, the updated report being generated based on the updated first report configuration file.
9. The system of claim 1 , wherein the operations further comprise:
presenting the report on a graphical user interface;
receiving user feedback in response to the presentation of the report; and
updating one or more parameters of the machine-learned model based on the user feedback.
10. A computer-implemented method, comprising:
storing organizational data associated with the organization, wherein the organizational data comprising a plurality of employee data objects that respectively correspond to a plurality of employees of an organization, and a plurality of previously generated report configuration files; and
accessing a machine-learned model, wherein the machine-learned model is configured to generate a report configuration file based on a prompt, the machine-learned model being trained using the plurality of previously generated report configuration files;
receiving a user query requesting a report associated with the organizational data;
processing, using a natural language processing model, the user query and the employee data objects to generate a prompt;
processing, by the machine-learned model, the prompt and the organizational data to generate a first report configuration file;
determining that a parameter of the first report configuration file is incorrect based on the comparison of the first report configuration file with the plurality of previously generated report configuration files;
updating the parameter of the first report configuration file prior to the processing of the first report configuration file to generate the report; and
generating the report based on the first report configuration file.
11. The method of claim 10 , further comprising:
determining whether the first report configuration file is validated by comparing the first report configuration file with the plurality of previously generated report configuration files.
12. The method of claim 11 , wherein the operations further comprise:
processing the first report configuration file to generate the report when determined that the first report configuration file is validated.
13. The method of claim 11 , further comprising:
selecting, from a plurality of template configuration files, a second report configuration file to generate the report when determined that the first report configuration is not validated.
14. The method of claim 13 , wherein the plurality of template configuration files has been previously generated and stored a database of the organizational management platform.
15. The method of claim 10 , wherein the first report configuration file has a parameter that is associated with an attribute of the employee data objects.
16. The method of claim 10 , further comprising:
presenting the report on a graphical user interface;
receiving user feedback in response to the presentation of the report;
updating the first report configuration file based on the user feedback; and
presenting an updated report on the graphical user interface, the updated report being generated based on the updated first report configuration file.
17. The method of claim 10 , further comprising:
presenting the report on a graphical user interface;
receiving user feedback in response to the presentation of the report; and
updating one or more parameters of the machine-learned model based on the user feedback.
18. One or more tangible non-transitory computer-readable media storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to:
storing organizational data associated with the organization, wherein the organizational data comprising a plurality of employee data objects that respectively correspond to a plurality of employees of an organization, and a plurality of previously generated report configuration files; and
accessing a machine-learned model, wherein the machine-learned model is configured to generate a report configuration file based on a prompt, the machine-learned model being trained using the plurality of previously generated report configuration files;
receiving a user query requesting a report associated with the organizational data;
processing, using a natural language processing model, the user query and the employee data objects to generate a prompt;
processing, by the machine-learned model, the prompt and the organizational data to generate a first report configuration file;
determining that a parameter of the first report configuration file is incorrect based on the comparison of the first report configuration file with the plurality of previously generated report configuration files;
updating the parameter of the first report configuration file prior to the processing of the first report configuration file to generate the report; and
generating the report based on the first report configuration file.