AGREEMENT DOCUMENT MODEL MODIFICATIONS IN A DOCUMENT MANAGEMENT SYSTEM

Abstract

A document management system utilizes document models for querying, validating, and customizing electronic agreement documents. Document models can be a data structure including document attributes that represent an agreement document. Examples of document attributes include customizable data values, conditions related to the operation of the agreement document and satisfiable by certain values of the customized data values, and rendering parameters for the appearance of the electronic agreement document. The document management system enables a user to create custom document models for generating electronic agreement documents that can be queried, validated, and customized through querying, validating, and customizing the corresponding document models.

Description

Claims

1. A method comprising: receiving, by a document management system, a definition of a target document model corresponding to a type of agreement document, the definition received from a user, the target document model comprising a set of target document objects, the set of target document objects each corresponding to a characteristic of an agreement document;accessing, by the document management system, a set of historical agreement documents corresponding to the type of agreement document, each historical agreement document associated with a corresponding historical document model;identifying, by the document management system, one or more document objects within the historical document models and not included in the target document model;presenting, by the document management system, the identified one or more document objects to the user; andin response to the user selecting one or more of the presented document objects, modifying, by the document management system, the target document model to include the one or more of the presented document objects.

2. The method of claim 1, wherein identifying the one or more document objects within the historical document models and not included in the target document model comprises: accessing a statistical model of document objects included within the historical document models; andfiltering a set of document objects from the document objects included within the historical document models using the statistical model,wherein the one or more document objects are included in the filtered set of document objects and not included in the target document model.

3. The method of claim 2, further comprising generating the statistical model of document objects.

4. The method of claim 3, wherein generating the statistical model of document objects comprises determining a correlation between the document objects included within the historical document models and the type of agreement document.

5. The method of claim 2, wherein the statistical model comprises a histogram of the document objects included within the historical document models, and wherein filtering the set of document objects comprises determining histogram bins meeting a threshold object count.

6. The method of claim 1, wherein the historical document models further comprise respective historical object requirements, a given object requirement comprising a condition that must be satisfied by a given document object, further comprising: determining, by the document management system, one or more historical object requirements within the historical document models for inclusion within the target document model.

7. The method of claim 6, wherein the target document model further comprises a set of target object requirements, and wherein determining the one or more historical object requirements comprises: identifying, by the document management system, that the one or more historical object requirements are included in the historical document models and not included in the target document model.

8. The method of claim 6, wherein determining the one or more object requirements comprises: applying a machine-learned model to the set of target document objects, the machine-learned model configured to determine a score representative of a similarity between the target document model and the historical document models; andin response to determining that the score does not meet a threshold score, determine a historical object requirement that is not included within target object requirements of the target document model.

9. The method of claim 8, further comprising training the machine-learned model using the historical document models and the historical object requirements satisfied by one or more historical document objects.

10. The method of claim 1, further comprising: identifying a target document object of the set of target document objects that is not included in the historical document models; andpresenting the target document object to the user.

11. The method of claim 10, further comprising: in response to the user selecting the presented target document object, modifying, by the document management system, the target document model to exclude the selected target document object.

12. The method of claim 1, further comprising: filtering the set of historical agreement documents from a database of historical agreement documents, wherein the filtering comprises: identifying a characteristic of an organization to which the user belongs;determining a plurality of organizations having the characteristic; andidentifying a plurality of historical agreement documents generated by the plurality of organizations and corresponding to the type of agreement document.

13. The method of claim 1, further comprising: receiving a request from a signing entity to electronically sign the agreement document;determining a location of the signing entity;modifying the target document model based on the location of the signing entity; andgenerating, by the document management system, the agreement document based on the modified target document model.

14. A non-transitory computer-readable storage medium storing executable instructions that, when executed by one or more processors, cause the processor to perform operations, the instructions comprising instructions to: receive a definition of a target document model corresponding to a type of agreement document, the definition received from a user, the target document model comprising a set of target document objects, the set of target document objects each corresponding to a characteristic of an agreement document;access a set of historical agreement documents corresponding to the type of agreement document, each historical agreement document associated with a corresponding historical document model;identify one or more document objects within the historical document models and not included in the target document model;present the identified one or more document objects to the user; andin response to the user selecting one or more of the presented document objects, modify the target document model to include the one or more of the presented document objects.

15. The non-transitory computer-readable storage medium of claim 14, wherein instructions to identify the one or more document objects within the historical document models and not included in the target document model comprises instructions to: access a statistical model of document objects included within the historical document models; andfilter a set of document objects from the document objects included within the historical document models using the statistical model,wherein the one or more document objects are included in the filtered set of document objects and not included in the target document model.

16. The non-transitory computer-readable storage medium of claim 15, wherein the instructions further comprise instructions to generate the statistical model of document objects, wherein instructions to generate the statistical model of document objects comprises instructions to determine a correlation between the document objects included within the historical document models and the type of agreement document.

17. The non-transitory computer-readable storage medium of claim 14, wherein the historical document models further comprise respective historical object requirements, the target document model further comprises a set of target object requirements, and a given object requirement comprises a condition that must be satisfied by a given document object, wherein the instructions further comprise instructions to: determine one or more object requirements within the historical document models for inclusion within the target document model by: applying a machine-learned model to the set of target document objects, the machine-learned model configured to determine a score representative of a similarity between the target document model and the historical document models; andin response to determining that the score does not meet a threshold score, determine a historical object requirement that is not included within target object requirements of the target document model.

18. A document management system comprising one or more processors and a non-transitory computer-readable storage medium storing instructions that, when executed by the one or more processors, cause the document management system to perform operations, the instructions comprising instructions to: receive a definition of a target document model corresponding to a type of agreement document, the definition received from a user, the target document model comprising a set of target document objects, the set of target document objects each corresponding to a characteristic of an agreement document;access a set of historical agreement documents corresponding to the type of agreement document, each historical agreement document associated with a corresponding historical document model;identify one or more document objects within the historical document models and not included in the target document model;present the identified one or more document objects to the user; andin response to the user selecting one or more of the presented document objects, modify the target document model to include the one or more of the presented document objects.

19. The document management system of claim 18, wherein instructions to identify the one or more document objects within the historical document models and not included in the target document model comprises instructions to: access a statistical model of document objects included within the historical document models; andfilter a set of document objects from the document objects included within the historical document models using the statistical model,wherein the one or more document objects are included in the filtered set of document objects and not included in the target document model.

20. The document management system of claim 19, wherein the instructions further comprise instructions to generate the statistical model of document objects, wherein instructions to generate the statistical model of document objects comprises instructions to determine a correlation between the document objects included within the historical document models and the type of agreement document.