Target document template generation
To automatically generate a project document, a server in a computing environment receives input documents associated with a project, and extracts a set of features from each input document. The server determines a frequency of the words in each input document and stores the frequencies in relation to the words in the sets of words. The server than applies a document type machine-learned model to a set of words for each input document to infer a document type. The document machine-learned model may be trained using a bag-of-words representation. The server then applies a architecture pattern machine-learned model the set of input documents to determine a target architecture pattern. The server automatically generates a project document for the project based on the document types and inferred architecture pattern.
1. A computer system comprising:
a computer processor; and
a non-transitory computer-readable storage medium storage having instructions that when executed by the computer processor perform actions comprising:
receiving a set of two or more input documents, the set of input documents describing a project;
extracting a set of features associated with each input document;
applying, for each input document, a document type machine-learned model to the set of features associated with the input document to infer a document type of the input document;
applying an architecture pattern machine-learned model to a concatenated set of features for the set of input documents to determine a target architecture pattern for a project document associated with the project, wherein the target architecture pattern specifies a structure and organization of a project document including information from each of the set of input documents; and
generating the project document for the project based on the document types for the set of input documents and the target architecture pattern determined for the set of input documents.
2. The computer system of claim 1 , the actions further comprising:
evaluating the project document against previous project documents or input documents from the set of input documents using cosine similarity and term frequency-inverse document frequency.
3. The computer system of claim 1 , wherein the document type machine-learned model and the architecture pattern machine-learned model include random forest classifiers.
4. The computer system of claim 1 , wherein the architecture pattern machine-learned model includes a plurality of random forest classifiers.
5. The computer system of claim 1 , wherein the document type machine-learned model and the architecture pattern machine-learned model are configured to receive a bag-of-words representation as the set of features for the input document.
6. The computer system of claim 1 , wherein the set of features for each input document are a subset of words based on frequency of occurrence within the input document.
7. The computer system of claim 1 , wherein each document type specifies a functionality of an input document based on contents of the input document, wherein functionalities include one or more of data assessments, suitability assessments, or privacy assessments.
8. The computer system of claim 1 , the actions further comprising automatically populating the project document with key terms from each of the set of input documents.
9. The computer system of claim 1 , wherein the project document displays components needed to create and support a new web application.
10. A non-transitory computer-readable storage medium comprising instructions executable by a processor, the instructions comprising steps for the processor to:
receive a set of two or more input documents, the set of input documents describing a project;
extract a set of features associated with each input document;
apply, for each input document, a document type machine-learned model to the set of features associated with the input document to infer a document type of the input document;
apply an architecture pattern machine-learned model to a concatenated set of features for the set of input documents to determine a target architecture pattern for a project document associated with the project, wherein the target architecture pattern specifies a structure and organization of a project document including information from each of the set of input documents; and
generate the project document for the project based on the document types for the set of input documents and the target architecture pattern determined for the set of input documents.
11. The non-transitory computer-readable storage medium of claim 10 , the instructions further comprising:
evaluating the project document against previous project documents or input documents from the set of input documents using cosine similarity and term frequency-inverse document frequency.
12. The non-transitory computer-readable storage medium of claim 10 , wherein the document machine-learned model and the architecture pattern machine-learned model include random forest classifiers.
13. The non-transitory computer-readable storage medium of claim 10 , wherein the architecture pattern machine-learned model includes a plurality of random forest classifiers.
14. The non-transitory computer-readable storage medium of claim 10 , wherein the document type machine-learned model and the architecture pattern machine-learned model are configured to receive a bag-of-words representation as the set of features for the input documents.
15. The non-transitory computer-readable storage medium of claim 10 , wherein the set of features for each input document are a subset of words based on frequency of occurrence within the input document.
16. A computer-implemented method for automated document generation, the method comprising:
receiving a set of two or more input documents, the set of input documents describing a project;
extracting a set of features associated with each input document;
applying, for each input document, a document type machine-learned model to the set of features associated with the input document to infer a document type of the input document;
applying an architecture pattern machine-learned model to a concatenated set of features for the set of input documents to determine a target architecture pattern for a project document associated with the project, wherein the target architecture pattern specifies a structure and organization of a project document including information from each of the set of input documents; and
generating the project document for the project based on the document types for the set of input documents and the target architecture pattern determined for the set of input documents.
17. The computer-implemented method of claim 16 , further comprising:
evaluating the project document against previous project documents or input documents from the set of input documents using cosine similarity and term frequency-inverse document frequency.
18. The computer-implemented method of claim 16 , wherein the document type machine-learned model and the architecture pattern machine-learned model are random forest classifiers.
19. The computer-implemented method of claim 16 , wherein the architecture pattern machine-learned model is a plurality of random forest classifiers.
20. The computer-implemented method of claim 16 , wherein the document type machine-learned model and the architecture pattern machine-learned model are configured to receive a bag-of-words representation as the set of features for the input documents.
21. The computer-implemented method of claim 16 , wherein the set of features for each input document are a subset of words based on frequency of occurrence within the input document.