DETAILED ACTION
Priority
This action is in response to the original filing dated 13 May 2024 which claims priority to U.S. provisional applications, dated 13 May 2023 and 11 June 2023. Claims 1-18 are pending and have been considered below.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Allowable Subject Matter
Claim 15 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-14 and 16-18 are rejected under 35 U.S.C. 103 as being unpatentable over Jin (US 2024/0289536 A1) in view of Heller et al. (US 12,067,366 B1).
As for independent claim 1, Jin teaches an apparatus comprising:
at least one memory; a component collection stored in the at least one memory; any of at least one processor disposed in communication with the at least one memory, the any of the at least one processor executing processor-executable instructions from the component collection, the component collection storage structured with processor-executable instructions comprising: [(e.g. see Jin paragraph 0050) ”Any of the steps, operations, or processes described herein may be performed or implemented with one or more hardware or software modules, alone or in combination with other devices. In one embodiment, a software module is implemented with a computer program product comprising a computer-readable medium containing computer program code, which can be executed by a computer processor for performing any or all of the steps, operations, or processes described”].
obtain, via any of at least one processor, a matter milestone interaction request datastructure, in which the matter milestone interaction request datastructure is structured as specifying a milestone document associated with a matter [(e.g. see Jin paragraphs 0028, 0039) ”When a user seeks to generate a new document … A user 410, Paula Smith of XYZ Inc., is logged into the document management system 110, and provides input 420 that initiates a workflow for generating a licensing agreement (e.g., the electronic document 120)”].
determine, via any of at least one processor, milestone document details associated with the milestone document via a natural language processing engine [(e.g. see Jin paragraph 0039 and Fig. 4) ”The input 420 may be natural language text, as is shown in FIG. 4”]. Examiner notes that, as depicted in Fig. 4, the natural language text describing the document “Generate a licensing agreement for Tanya Li of ABC Properties to sign”.
evaluate, via any of at least one processor, via a first machine learning prediction logic datastructure, the milestone document details with respect to matter data associated with the matter to determine relevant matter data [(e.g. see Jin paragraphs 0018, 0027) ”Examples of documents that may be stored, analyzed, and/or managed by the document management system 110 include contracts, press releases, technical specifications, employment agreements, purchase agreements, services agreements, financial agreements, and so on … The document management system 110 may use machine learning to identify one or more workflows applicable to a generated document. For example, the user specified workflows (e.g., as described above) may be used as labeled training data for a machine learning model that is configured to output a workflow for a document of a specific type, created by a specific user, and so on”].
determine, via any of at least one processor, a set of similar prior matters that are similar to the matter [(e.g. see Jin paragraphs 0032, 0039) ”the machine learning model 300 may learn that one particular user generates real estate agreements (e.g., from a historical workflow 315) and that user's email address and phone number always comprise the contact information in the real estate agreements. Similarly, the machine learning model 300 may learn that all real estate agreements generated by the user are governed by the laws of California … Based on past historical workflows 425. In this example, the document management system 110 analyzed past historical workflows 425 that generated agreements sent to ABC Properties for execution”].
evaluate, via any of the at least one processor, via a second machine learning prediction logic datastructure, the milestone document details, the relevant matter data and similar prior matters data associated with a set of similar prior matters with respect to resolution document templates to determine a first best matching resolution document template for the milestone document [(e.g. see Jin paragraphs 0024, 0028, 0031, 0035) ”The machine learning module 230 trains and applies machine learning models within the document management system 110. The machine learning module 230 trains a machine learning model on historical workflows for generating the historical electronic documents 125. When a user seeks to generate a new document, the machine learning model suggests content for the new document, which the user can review, edit, and/or confirm. The machine learning module 230 may also include a model store, which stores various versions of the machine learning model as it is updated over time … The machine learning module 230 uses a training set 310 to train the machine learning model 300. The training set 310 includes a number of historical workflows 315 configured to generate at least one of the historical electronic documents 125. Each historical electronic document 125 includes content, specifically fields 320 and values 330. The fields 320 are terms requiring definition, such as party names, authorized representatives of each party, dates, and/or jurisdiction. The generated historical electronic document 125 includes values 330 for each of the fields 320. In some embodiments, the training set 310 includes characteristics associated with each historical electronic document 125. These characteristics include, but are not limited to, a type of the document, users and/or entities associated with the document, characteristics of the entities associated with the document, parties to the document, and a jurisdiction associated with the document. Accordingly, the training set 310 may include historical workflows 315 specific to a type of document, a user and/or entity associated with the document, a party to the document, and so on … The data stored by the database 205 may include … document templates … The input includes signals corresponding to a first set of fields 350 (e.g., fields whose values the document management system 110 can confidently predict because of consistencies in historical electronic documents 125)”].
to generate a set of template placeholder values for a template placeholder of the first best matching resolution document template [(e.g. see Jin paragraphs 0024, 0039) ” The data stored by the database 205 may include … document templates … the document management system 110 analyzed past historical workflows 425 that generated agreements sent to ABC Properties for execution. The interface 400 includes a first set of fields and corresponding predicted values 430. For example, the document management system 110 may determine with near certainty (e.g., likelihood above a predefined high threshold (e.g., 95%+likely)) that the field 435, “Party 1,” corresponds to the value 440 “XYZ Inc.” The user 410, however, may edit, change, and/or override any of the first set of fields and corresponding predicted values 430. The interface 400 also includes a second set of fields and a number of corresponding predicted values 450. For the field 455, “Choice of Law,” the interface 400 displays the values 460 of “California” and “Washington,” which the user 410 can select from”].
obtain, via any of at least one processor, user selection of a template placeholder value to utilize from the set of template placeholder values [(e.g. see Jin paragraph 0039) ”the document management system 110 analyzed past historical workflows 425 that generated agreements sent to ABC Properties for execution. The interface 400 includes a first set of fields and corresponding predicted values 430. For example, the document management system 110 may determine with near certainty (e.g., likelihood above a predefined high threshold (e.g., 95%+likely)) that the field 435, “Party 1,” corresponds to the value 440 “XYZ Inc.” The user 410, however, may edit, change, and/or override any of the first set of fields and corresponding predicted values 430. The interface 400 also includes a second set of fields and a number of corresponding predicted values 450. For the field 455, “Choice of Law,” the interface 400 displays the values 460 of “California” and “Washington,” which the user 410 can select from. The user 410 may, in some embodiments, revise the presented values 450. The interface 400 may also include representations of confidence scores associated with each of the predicted values 450”].
and composite, via any of the at least one processor, content of the first best matching resolution document template and the selected template placeholder value to utilize to generate a resolution document [(e.g. see Jin paragraph 0046) ”The document management system generates 660 the electronic document in response to receiving the user's confirmation of the predicted values for the second set of the fields. The generated electronic document includes the confirmed values for each of the fields”].
Jin does not specifically teach similar to the matter by executing a search query or provide, via any of at least one processor, a prompt to a large language model to instruct the large language model. However, in the same field of invention or solving similar problems, Heller teaches:
similar to the matter by executing a search query [(e.g. see Heller col 10 lines 3-11, col 31 lines 22-27) ”determining input text may involve executing a search query. For example, a search of a database, set of documents, or other data source may be executed base at least in part on one or more search parameters determined based on a request received from a client machine. For instance, the request may identify one or more search terms and a set of documents to be searched using the one or more search terms … a relevancy prompt may include a request to provide an indication as to the relevancy of a particular document or documents to a search query or queries. Accordingly, the relevancy prompt may include all or a portion of a search query as well as one or more search results”].
provide, via any of at least one processor, a prompt to a large language model to instruct the large language model [(e.g. see Heller col 2 lines 53-63, col 4 lines 19-23, col 5 lines 6-11) ”search results are provided to an artificial intelligence system. The artificial intelligence system then further processes the search results to produce an answer based on those search results. In this context, a large language model may be used to determine the search query, apply one or more filters and/or tags, and/or synthesize potentially many different types of search … techniques and mechanisms described herein may be used to link a large language model with a legal research database, allowing the large language model to automatically determine appropriate searches to perform … the text generation flow may define a procedure for interacting with a large language model to generate output text based on the original input text. For instance, the text generation flow may define one or more prompts or instructions to provide to the large language model”].
Therefore, considering the teachings of Jin and Heller, it would have been obvious to one having ordinary skill in the art before the effective filing date of the claimed invention to add similar to the matter by executing a search query and provide, via any of at least one processor, a prompt to a large language model to instruct the large language model, as taught by Heller, to the teachings of Jin because it improves the quality of text provided by the system (e.g. see Heller col 3 lines 2-3).
As for dependent claim 2, Jin and Heller teach the apparatus as described in claim 1 and Jin further teaches:
in which the matter milestone interaction request datastructure is generated via a large language model chatbot [(e.g. see Jin paragraph 0039 and Fig. 4 numeral 420) ”The document management system 110 generates the interface 400 via the user interface module 240 … The input 420 may be natural language text”]. Examiner notes that, as depicted in Fig. 4, the user is prompted by the machine learning system with “What would you like to generate?”. Examiner additionally notes that Heller also teaches a large language model (see Heller col 2 lines 35-51).
As for dependent claim 3, Jin and Heller teach the apparatus as described in claim 1 and Jin further teaches:
in which the milestone document details comprise at least one of: a source of the milestone document, a date associated with the milestone document, subject matter discussed in the milestone document, sentiment of the milestone document, a document reference, a venue reference [(e.g. see Jin paragraph 0036) ”characteristics of the user who initiated the workflow to generate the electronic document 120, the type of the electronic document 120, an intended recipient of the electronic document 120, a jurisdiction associated with the electronic document 120, and so on”].
As for dependent claim 4, Jin and Heller teach the apparatus as described in claim 1 and Jin further teaches:
in which the first machine learning prediction logic datastructure and the second machine learning prediction logic datastructure are implemented via any of: Bayesian network, classification prediction logic datastructure, decision tree, neural network, regression prediction logic datastructure [(e.g. see Jin paragraph 0034) ”The machine learning module 230 may use different versions of supervised or unsupervised machine learning, or another training technique to generate and update the machine learned model 300. In some embodiments, other training techniques may be linear support vector machines (linear SVM), boosting for other algorithms (e.g., AdaBoost), neural networks, logistic regression, naïve Bayes, memory based learning, random forests, bagged trees, decision trees, boosted trees, boosted stumps, and so on”].
As for dependent claim 5, Jin and Heller teach the apparatus as described in claim 1 and Jin further teaches:
in which the search query specifies a matter type of the matter as a search query parameter [(e.g. see Jin paragraphs 0018, 0024, 0026, 0027) ”include contracts, press releases, technical specifications, employment agreements, purchase agreements, services agreements, financial agreements, and so on … different workflows for different types of documents … machine learning model that is configured to output a workflow for a document of a specific type … the database 205 stores metadata information associated with workflows, documents or clauses, and fields and values within the documents and clauses”].
As for dependent claim 6, Jin and Heller teach the apparatus as described in claim 1 and Jin further teaches;
in which the search query specifies a venue associated with the matter as a search query parameter [(e.g. see Jin paragraphs 0024, 0032, 0036) ”the machine learning model 300 may learn that all real estate agreements generated by the user are governed by the laws of California. In contrast, the machine learning model 300 may learn that the property addresses and closing dates in these generated real estate agreements vary. Accordingly, the fields for contact information and jurisdiction correspond to the first set of fields 320 and values 330, whereas the fields for property addresses and closing dates correspond to the second set of fields 320 and values 330 … characteristics of the user who initiated the workflow to generate the electronic document 120, the type of the electronic document 120, an intended recipient of the electronic document 120, a jurisdiction associated with the electronic document 120 … the database 205 stores metadata information associated with workflows, documents or clauses, and fields and values within the documents and clauses”].
As for dependent claim 7, Jin and Heller teach the apparatus as described in claim 1 and Jin further teaches:
in which the search query specifies at least some of the relevant matter data as a search query parameter [(e.g. see Jin paragraph 0024, 0027, 0039) ”the database 205 stores metadata information associated with workflows, documents or clauses, and fields and values within the documents and clauses … and provides input 420 that initiates a workflow for generating a licensing agreement (e.g., the electronic document 120) … use machine learning to identify one or more workflows applicable to a generated document … workflow for a document of a specific type”].
As for dependent claim 8, Jin and Heller teach the apparatus as described in claim 1, but Jin does not specifically teach the following limitation. However, Heller teaches:
in which the search query is executed via a large language model search [(e.g. see Heller col 4 lines 19-25) ”techniques and mechanisms described herein may be used to link a large language model with a legal research database, allowing the large language model to automatically determine appropriate searches to perform and then ground its responses to a source of truth (e.g., in actual law) so that it does not “hallucinate” a response that is inaccurate”].
The motivation to combine is the same as that used for claim 1.
As for dependent claim 9, Jin and Heller teach the apparatus as described in claim 1 and Jin further teaches:
in which the first best matching resolution document template is calculated to have a high likelihood of producing a successful outcome with regard to the milestone document [(e.g. see Jin paragraphs 0024, 0036, 0039) ”The data stored by the database 205 may include … document template … the machine learning model 300 determines a confidence score reflecting the likelihood that the user would accept the predicted value 380 in the generated electronic document 120 … the document management system 110 may determine with near certainty (e.g., likelihood above a predefined high threshold (e.g., 95%+likely))”].
As for dependent claim 10, Jin and Heller teach the apparatus as described in claim 1 and Jin further teaches:
in which the prompt is structured to comprise instructions to construct template placeholder values that maximize likelihood of producing a successful outcome with regard to the milestone document [(e.g. see Jin paragraph 0036, 0039) ”the machine learning model 300 determines a confidence score reflecting the likelihood that the user would accept the predicted value 380 in the generated electronic document 120 … the document management system 110 may determine with near certainty (e.g., likelihood above a predefined high threshold (e.g., 95%+likely)) that the field 435, “Party 1,” corresponds to the value 440 “XYZ Inc.””].
As for dependent claim 11, Jin and Heller teach the apparatus as described in claim 1 and Jin further teaches:
in which the user selection of the template placeholder value to utilize is obtained via a large language model chatbot [(e.g. see Jin paragraph 0039 and Fig. 4) ”The interface 400 also includes a second set of fields and a number of corresponding predicted values 450. For the field 455, “Choice of Law,” the interface 400 displays the values 460 of “California” and “Washington,” which the user 410 can select from. The user 410 may, in some embodiments, revise the presented values 450”].
As for dependent claim 12, Jin and Heller teach the apparatus as described in claim 1 and Jin further teaches:
in which the component collection storage is further structured with processor-executable instructions comprising: provide, via any of at least one processor, the generated resolution document [(e.g. see Jin paragraph 0046) ”The document management system generates 660 the electronic document in response to receiving the user's confirmation of the predicted values for the second set of the fields. The generated electronic document includes the confirmed values for each of the fields”].
As for dependent claim 13, Jin and Heller teach the apparatus as described in claim 12 and Jin further teaches:
in which the instructions to provide the generated resolution document are structured as instructions to file the generated resolution document with a venue [(e.g. see Jin paragraphs 0021, 0026, 0040) ”the users 130A-B may be employed by an entity that uses the document management system 110 to generate and send contracts to various counterparties … a user may define a workflow such that the document management system 110 sends all legal documents associated with one entity to the entity's general counsel … the workflow may instruct the document management system 110 to automatically send the generated electronic document 120 to ABC Properties for execution”].
As for dependent claim 14, Jin and Heller teach the apparatus as described in claim 12 and Jin further teaches:
in which the component collection storage is further structured with processor-executable instructions comprising: obtain, via any of at least one processor, feedback with regard to the provided resolution document and update, via any of at least one processor, the second machine learning prediction logic datastructure via training data comprising the feedback [(e.g. see Jin paragraphs 0016, 0037) ”The user provides feedback on the content suggestions, based on which the document management system retrains the machine learning model. The document management system, accordingly, provides the user with an increasingly efficient and accurate document generation and workflow process … The user may provide feedback, for example, by confirming the predicted values 380, rewriting the predicted values 380, and/or requesting the machine learning model 300 to provide a new set of predicted values 380. The confirmed set of predicted values 380 is added to the training set 310, which the machine learning module 230 uses to retrain the machine learning model 300”].
As for independent claim 16, Jin and Heller teach a non-transient medium. Claim 16 discloses substantially the same limitations as claim 1. Therefore, it is rejected with the same rational as claim 1.
As for independent claim 17, Jin and Heller teach a system. Claim 17 discloses substantially the same limitations as claim 1. Therefore, it is rejected with the same rational as claim 1.
As for independent claim 18, Jin and Heller teach a method. Claim 18 discloses substantially the same limitations as claim 1. Therefore, it is rejected with the same rational as claim 1.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
U.S. PGPub 2024/0354436 A1 issued to Mukherjee et al. on 24 October 2024. The subject matter disclosed therein is pertinent to that of claims 1-18 (e.g. using a LLM to retrieve text from similar documents).
U.S. Patent 11,030,516 B1 issued to Klein et al. on 08 June 2021. The subject matter disclosed therein is pertinent to that of claims 1-18 (e.g. calculating the likelihood of success at particular court venues).
Contact Information
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHRISTOPHER J FIBBI whose telephone number is (571)-270-3358. The examiner can normally be reached Monday - Thursday (8am-6pm).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, William Bashore can be reached at (571)-272-4088. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/CHRISTOPHER J FIBBI/Primary Examiner, Art Unit 2174
Prosecution Insights