DETAILED ACTION
Notice of 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 .
Drawings
The drawings are objected to:
under 37 CFR 1.83(a) because they fail to show the connection between the basis generation module 216 and response generation module 214 in Fig. 2, as described in the specification, in para.[0051],[0057], which states “the response generation module 214 generates a response to a query by prompting the LLM with the custom context, wherein the response is indicative of either a negative answer or a positive answer to the query, or a specific entity. The basis generation module 216 combines the response with the extractive QA model to obtain relevant text extracts from an unstructured data source that provide basis for the response”. Any structural detail that is essential for a proper understanding of the disclosed invention should be shown in the drawing. MPEP § 608.02(d).
Figs. 1,2 shows “respnose and basis generator server 108” which should be “response and basis generator server 108” as described in specification, in para.[0040],[0042]. Appropriate correction is required.
Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. The figure or figure number of an amended drawing should not be labeled as “amended.” If a drawing figure is to be canceled, the appropriate figure must be removed from the replacement sheet, and where necessary, the remaining figures must be renumbered and appropriate changes made to the brief description of the several views of the drawings for consistency. Additional replacement sheets may be necessary to show the renumbering of the remaining figures. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an
abstract idea without significantly more.
The Independent claims 1, 8 and 15 recite “extracting text from the unstructured data source to obtain at least one machine-searchable document”; “anonymizing the at least one machine-searchable document by replacing personally identifiable information (PII) and personal health information (PHI) with entity types using an entity extraction model to obtain an anonymized machine-searchable document having entity types and entity attributes, wherein the entity extraction model is pre-trained based on entities and identifiable information of the entities”; “determining text extracts that indicate the criterion from the anonymized machine-searchable document using an extractive question-answer (QA) machine learning model, wherein the extractive QA machine learning model is pre-trained based on specific questions related to the criterion and characteristic language patterns associated with criterion”; “performing, using a small-scale machine learning model, a text search in the anonymized machine-searchable document to find text strings that are conceptually associated with the text extracts that indicate the criterion”; “generating a custom context for a large language model (LLM) using (a) the text extracts that indicate the criterion and (b) selecting a predetermined number of text-characters before and after the text strings that are conceptually associated with the text extracts”; “generating a response to a query by prompting the LLM with the custom context, wherein the response is indicative of either a negative answer or a positive answer to the query”; “and combining the response with the extractive QA machine learning model to obtain relevant text extracts from the unstructured data source that provide basis for the response”. The limitations above as drafted, is a process that, under its broadest reasonable interpretation, covers a mental process, as this could be performed in the human mind or with the aid of pen and paper.
The limitations of " extracting ... ", "anonymizing ... ", "determining ... ",”performing…”, “generating…,”combining…” as drafted covers mental activities. More specifically, a person can obtain an unstructured document like email or any free form text, can anonymize the sensitive information/entities with a predetermined rules, can extract text from that document based on predetermined criteria, performing text search of similar concept from the same document, generate context and based on the context and concept, generate a response of a query and determine the basis or source of the response. The above steps, as drafted, is a process that under its broadest reasonable interpretation, covers performance of the limitation in the mind. There is, nothing in the claim element precludes the step from practically being performed in the human mind or with pen and paper. Additionally, the mere nominal recitation of a generic computer appliance does not take the claim limitation out of the mental processes grouping. Thus, the claims recite a mental process.
The claims recite the additional limitation of “entity extraction model”, “extractive question-answer (QA) machine learning model”, “small-scale machine learning model”, “large language model”, “memory”, “processor”, “non-transitory computer readable storage medium”, for performing the method, which are recited at a high level of generality and are recited as performing generic computer functions routinely used in computer applications. Throughout the specification, there is no additional information about any of the additional elements and are recited in a generic way which are not sufficient to amount to significantly more than the judicial exception. All those are recited at a high level of generality and are recited as performing generic computer functions routinely used in computer applications. This is no more than mere instructions to apply the exception using a generic computer component. Accordingly, this additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea.
Thus, taken alone, the additional elements do not amount to significantly more than the above identified judicial exception (the abstract idea). Looking at the limitations as an ordered combination adds
nothing that is not already present when looking at the elements taken individually. There is no indication
that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation. Claims 1, 8 and 15 are therefore not drawn to eligible subject matter as these are directed to an abstract idea without
significantly more than the abstract idea.
Claims 2, 9 and 16 recite “evaluating a criterion category for each text extract and a probability of each criterion category, and combining probabilities for each criterion category associated with each text extract to generate an overall risk level for the at least one machine-searchable document”, to determine a risk label for the document by evaluating the criteria category of each text and probability of each criteria category of each text extract, could be performed in the human mind or with the aid of pen and paper. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception, as claims 2, 9 and 16 do not recite any additional limitations. The claims as drafted, are not patent eligible.
Claims 3, 10 and 17 recite “generating a next action for each criterion category by: performing, using the LLM, a classification task on the at least one machine-searchable document and the criterion category to automatically infer (a) a resolution path and (b) a current state within the resolution path; and automatically selecting the next action from a set of pre-determined actions based on the current state by analyzing known outcomes of historical documents corresponding to similar resolution paths and current states”, performing a classification task on the document to determine the next action for each criteria category, a resolution and based on the previous documentation could be an evaluation, observation and could be performed in the human mind or with the aid of pen and paper. The claims recite additional limitation of LLM, which in the specification recited in a generic way and as performing generic computer functions, which is not sufficient to amount to significantly more than the judicial exception. The claims 3, 10 and 17 as drafted, are not patent eligible.
Claims 4, 11 recite “displaying, on a graphical user interface (GUI), next best actions for a manually selected resolution path or an automatically recommended choice of resolution path”, to display or present the next actions of resolution from different choices could be an evaluation, observation and could be performed in the human mind or with the aid of pen and paper. The claims recite additional limitation of graphical user interface, which in the specification recited in a generic way and as performing generic computer functions, which is not sufficient to amount to significantly more than the judicial exception. The claims 4, 11 as drafted, are not patent eligible.
Claims 5, 12 and 18 recite “generating a risk profile for the entity based on the text extracts that indicate the criterion by: determining an absolute risk and a relative risk for the text extracts using a knowledge data source and the extractive QA machine learning model; and assigning ratings to the text extracts based on the absolute risk and the relative risk”, to generate a risk profile for the entity based on the extracted text and different sources and assigning ratings of the risks, could be performed in the human mind or with the aid of pen and paper. The claims recite additional limitation of extractive QA machine learning model, which in the specification recited in a generic way and as performing generic computer functions, which is not sufficient to amount to significantly more than the judicial exception. The claims 5, 12 and 18 as drafted, are not patent eligible.
Claims 6, 13 and 19 recite “fine-tuning the extractive QA machine learning model using at least one of example text extracts, a conceptual relationship graph, a semantic search based on vector embeddings, and keyword-based text searches for identifying relevant text snippets”, the predetermined sets of question answers could be fine-tuned or optimized with example text strings from multiple sources, such as conceptual relationship graph ,keyword based search, semantic based search and could be performed in the human mind or with the aid of pen and paper. The claims recite additional limitation of extractive QA machine learning model, which in the specification recited in a generic way and as performing generic computer functions, which is not sufficient to amount to significantly more than the judicial exception. The claims 6, 13 and 19 as drafted, are not patent eligible.
Claims 7, 14 and 20 recite “determining, using a custom machine learning model, if an identified text extract is favorable or unfavorable to a user by analyzing the context of the text extract and when available, comparing the identified text extract to a preferred text extract”, to determine whether the extracted text is favorable or unfavorable to the user by analyzing the context of the text extract, could be performed in the human mind or with the aid of pen and paper. The claims recite additional limitation of custom machine learning model, which in the specification recited in a generic way and as performing generic computer functions, which is not sufficient to amount to significantly more than the judicial exception. The claims 7, 14 and 20 as drafted, are not patent eligible.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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 of this title, 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, 6-8, 13-15, 19 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Mukherjee et al. ( US 20240354436 A1), hereinafter referenced as Mukherjee, in view of Sahu et al. (US 20230128136 A1), hereinafter referenced as Sahu.
Regarding Claim 1, Mukherjee teaches a processor-implemented method for generating a response that indicates a criterion and a text extract from an unstructured data source that provides basis for the response using artificial intelligence models, the method comprising:
determining text extracts that indicate the criterion from the [anonymized] machine-searchable document using an extractive question-answer (QA) machine learning model, wherein the extractive QA machine learning model is pre-trained based on specific questions related to the criterion and characteristic language patterns associated with criterion ( Mukherjee: Para. [0118], [0123]-[0126], Figs. 1B, 4, method 400 is implemented by the document search system 102 to enable natural language searching and response, utilizing one or more LLMs, with references to a large set of documents. At block 402, the document search system 102 may receive, a first user input including a natural language query. At block 404, the document search module 106 ( extractive question answer machine learning model) may vectorize the first user input into a query vector. The document search module 106 may employ a language model such as a LLM that is trained to generate answers from user queries. At block 406, the document search module 106 may execute, using the query vector generated at block 404, a similarity search in a document search model to identify one or more similar document portions. Para.[0102], data and/or documents that may be queried by the user can be obtained from the document source 120 (e.g., a third-party or data source external to the document search system 102) and stored in the database module 108 of the document search system 102 using the ontology 205, which may define document/data types and associated properties, and relationships among documents/data types, properties, and/or the like);
performing, using a small-scale machine learning model, a text search in the [anonymized] machine-searchable document to find text strings that are conceptually associated with the text extracts that indicate the criterion ( Mukherjee: Para.[0113], Fig. 3B, the prompt generation module 114 ( as a small-scale machine learning model, using less data) may further retrieve/obtain extended portions of the set of documents from the database module 108 and/or the document source 120that are adjacent to the portions of the set of documents similar to the user query. For example, the extended portions of the set of documents may include sentences immediately before and/or after sentences of the set of documents that match to the user query, and/or paragraphs in which the sentences of the set of documents that match to the user query are found. Para.[0127], Fig. 4, at block 407 in method 400, the extended document portions which include sentences immediately before and/or after sentences of a set of documents that match to the user query, may obtained ) ;
generating a custom context for a large language model (LLM) using (a) the text extracts that indicate the criterion and (b) selecting a predetermined number of text-characters before and after the text strings that are conceptually associated with the text extracts ( Mukherjee: Para.[0113], [0115],[0117], Fig. 3B, the prompt generation module 114 may generate a prompt for the LLM 130 further based on a context associated with the user query. The context associated with the user input may be generated by the context module 112 and may include any information associated with the user 150, a user session, or some other characteristics. The prompt generation module 114 may generate the prompt based on the extended portions of the set of documents which may include sentences immediately before and/or after sentences of the set of documents that match to the user query, and/or paragraphs in which the sentences of the set of documents that match to the user query are found. Para.[0128], [0129], Fig. 4, at block 408, 410, context was generated and obtained );
generating a response to a query by prompting the LLM with the custom context, wherein the response is indicative of either a negative answer or a positive answer to the query ( Mukherjee: Para.[0117],[0119], Fig. 3B, the document search system 102 may receive an output from the LLM 130 in response to the prompt generated based on the user query, the portions of the set of documents similar to the user query, the context, and the extended portions of the set of documents that are adjacent to the portions of the set of documents similar to the user query. Para.[0130]-[0132], Fig.4, at block 412, 414 prompt was generated and transmitted to LLM 130. At 416, the document search system 102 may receive a output from the LLM 130 in response to the prompt) ;
and combining the response with the extractive QA machine learning model to obtain relevant text extracts from the unstructured data source that provide basis for the response ( Mukherjee: Para.[0133],[0144], Fig. 4, At block 418, the user interface module 104 may provide the similar document portions to the user 150 for preview such that the user may have a better understanding about the basis of the output from the LLM 130, and may provide a graphical representation of the output ).
Mukherjee while teaching the method of claim 1, fails to explicitly teach the claimed, extracting text from the unstructured data source to obtain at least one machine-searchable document; anonymizing the at least one machine-searchable document by replacing personally identifiable information (PII) and personal health information (PHI) with entity types using an entity extraction model to obtain an anonymized machine-searchable document having entity types and entity attributes, wherein the entity extraction model is pre-trained based on entities and identifiable information of the entities;
However, Sahu does teach the claimed, extracting text from the unstructured data source to obtain at least one machine-searchable document ( Sahu: Para.[0088], Fig. 1, the data extractor and smart parsing module 110 extracts data based on attributes such as keywords from text documents, data entities from the tables, text and image from the presentations, emails etc. from various sources such as structured tables, unstructured sources including the PDFs, DOCs, Text files, email interactions, conversational chat platforms and also from web logs. The data extractor and smart parsing module 110 classifies the extracted information and pushes that to the storage layer after indexing the information) ;
anonymizing the at least one machine-searchable document by replacing personally identifiable information (PII) and personal health information (PHI) with entity types using an entity extraction model to obtain an anonymized machine-searchable document having entity types and entity attributes, wherein the entity extraction model is pre-trained based on entities and identifiable information of the entities ( Sahu: Para.[0120], Figs. 1, 15, an exemplary method of redaction begins with using the CCE 101 to identify sensitive data in block 1502. In block 1504, an optimal masking ruleset is selected. In block 1506, sensitive data is masked. Para.[0101]-[0104], Figs. 4-6, illustrates training of AI/ML model training for context based classification and context prediction using named entity recognition (NER) extraction to detect different types of sensitive data (e.g., PII (personally identifiable information), PHI (protected health information), NPI (Non-public personal information), SPI (Sensitive personal information) ,PAI (Publicly available Information), etc.)).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Sahu’s teaching of a computer-implemented apparatus, system, and method for protecting sensitive data, into the system and method of searching a large corpus of data by utilizing language models , taught by Mukherjee, because, by systematically parsing the incoming data in any form, detecting the relevant information, identifying and classifying the information, and by masking or redacting the sensitive data to comply with data privacy and security standards, would support fraud detection and prevention. (Sahu, Para.[0012]).
Claim 8 is a system claim comprising: a memory that stores a set of instructions ; and a processor that is configured to execute the set of instructions for ( Mukherjee: Para.[0174], [0175],Fig. 12, Computer system 1200 includes a main memory 1206, such as a random-access memory (RAM), cache and/or other dynamic storage devices, coupled to bus 1202 for storing information and instructions to be executed by processor 1204): performing the steps in method claim 1 above and as such, claim 8 is similar in scope and content to claim 1 and therefore, claim 8 is rejected under similar rationale as presented against claim 1 above.
Claim 15 is a non-transitory computer readable storage medium claim storing a sequence of instructions, which when executed by one or more processors, causes a method ( Mukherjee: Para.[0165],[0166], [0175],Fig. 12, non-transitory computer-readable storage medium can retain and store data and/or instructions to be executed by processor 1204) of performing the steps in method claim 1 above and as such, claim 15 is similar in scope and content to claim 1 and therefore, claim 15 is rejected under similar rationale as presented against claim 1 above.
Regarding Claim 6, Mukherjee in view of Sahu teach the processor-implemented method of claim 1, further comprising fine-tuning the extractive QA machine learning model using at least one of example text extracts, a conceptual relationship graph, a semantic search based on vector embeddings, and keyword-based text searches for identifying relevant text snippets ( Mukherjee: Para.[0088], the document search module 106 ( extractive QA machine learning model) may vectorize chunked portions of the set of documents into mathematical representations of the semantic contents of the chunked portions of the set of documents. As such, the document search module 106 may then execute similarity search to identify portions of the set of documents most similar in meaning to the user query. Advantageously, using portions of the set of documents most similar to the user query semantically to generate a prompt to the LLM 130 may enable the document search system 102 to receive more accurate or desired response from the LLM 130 for the document search system 102 to responding to the user input from the user 150).
Claim 13 is a system claim performing the steps in method claim 6 above and as such, claim 13 is similar in scope and content to claim 6 and therefore, claim 13 is rejected under similar rationale as presented against claim 6 above.
Claim 19 is a non-transitory computer readable storage medium claim performing the steps in method claim 6 above and as such, claim 19 is similar in scope and content to claim 6 and therefore, claim 19 is rejected under similar rationale as presented against claim 6 above.
Regarding Claim 7, Mukherjee in view of Sahu teach the processor-implemented method of claim 1, further comprising determining, using a custom machine learning model, if an identified text extract is favorable or unfavorable to a user by analyzing the context of the text extract and when available, comparing the identified text extract to a preferred text extract ( Mukherjee: Para.[0145],[0149], Fig.7, The user interface 700 includes a button 704 "Rate the Response", that may allow the user 150 to provide feedback to the document search system 102 and/or the LLM 130, whether the result was acceptable or not. The user interface 700 may further include a button 708 that allows the user 150 to view the document repository maintained by the document search system 102 to compare).
Claim 14 is a system claim performing the steps in method claim 7 above and as such, claim 14 is similar in scope and content to claim 7 and therefore, claim 14 is rejected under similar rationale as presented against claim 7 above.
Claim 20 is a non-transitory computer readable storage medium claim performing the steps in method claim 7 above and as such, claim 20 is similar in scope and content to claim 7 and therefore, claim 20 is rejected under similar rationale as presented against claim 7 above.
Claims 2-4, 9-11, 16 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Mukherjee et al. ( US 20240354436 A1), hereinafter referenced as Mukherjee, in view of Sahu et al. (US 20230128136 A1), hereinafter referenced as Sahu, further in view of Gupta et al. ( (US 20200226510 A1), hereinafter referenced as Gupta.
Regarding Claim 2, Mukherjee in view of Sahu teach the processor-implemented method of claim 1. Mukherjee in view of Sahu fail to explicitly teach the claimed, further comprising evaluating a criterion category for each text extract and a probability of each criterion category, and combining probabilities for each criterion category associated with each text extract to generate an overall risk level for the at least one machine-searchable document.
However Gupta does teach the claimed, further comprising evaluating a criterion category for each text extract and a probability of each criterion category, and combining probabilities for each criterion category associated with each text extract to generate an overall risk level for the at least one machine-searchable document ( Gupta: Para.[0040]-[0043], (0046], Fig. 4, at step 404 the machine learning engine 118 determines the clause category and the clause category probability associated with the clause category, from the contract document. At step 406, the machine learning engine 118 extracts metadata associated with the at least one clause based on the clause category. At step 408, the machine learning engine 118 determines the clause risk score and the clause risk probability associated with the at least one clause. At 412, the processor 120 determines a composite risk score for the contract document based on the clause category risk score and the category weightage associated with the clause category of the at least one clause in the contract document).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Gupta’s teaching of a system and method for determining risk score for a contract document, into the system and method , taught by Mukherjee in view of Sahu, because, by determining a composite risk score for a contract document before entering into the contract, can improve the understanding and relation between two parties in the contract. (Gupta, Para.[0002-[0004]]).
Claim 9 is a system claim performing the steps in method claim 2 above and as such, claim 9 is similar in scope and content to claim 2 and therefore, claim 9 is rejected under similar rationale as presented against claim 2 above.
Claim 16 is a non-transitory computer readable storage medium claim performing the steps in method claim 2 above and as such, claim 16 is similar in scope and content to claim 2 and therefore, claim 16 is rejected under similar rationale as presented against claim 2 above.
Regarding Claim 3, Mukherjee in view of Sahu, further in view of Gupta teach the processor-implemented method of claim 2. Gupta further teaches, further comprising generating a next action for each criterion category by: performing, using the LLM, a classification task on the at least one machine-searchable document and the criterion category to automatically infer (a) a resolution path and (b) a current state within the resolution path ( Gupta: Para.[0027], [0021], Fig. 2, The machine learning engine 118 may be configured to run the one or more machine learning models 122 to determine the clause category of the relevant standard clause defined in the table 200 and accordingly the clause category of the clause in the contract document, a clause category of a clause and/or a standard clause is indicative of whether the clause/standard clause classifies as one or more of a termination clause, confidentiality clause, term clause, compensation clause, compliance clause, restrictions clause, damages clause, and so on. Para.[0037], the one or more relevant standard clauses transmitted to the input data source may include clauses with clause risk score below a threshold value. Therefore, the one or more relevant standard clauses may be referred to by the user to make edits to the clauses of the contract document, for example, to reduce the level of business risk (represented by the composite risk score) associated with the contract document ( resolution path)) ;
and automatically selecting the next action from a set of pre-determined actions based on the current state by analyzing known outcomes of historical documents corresponding to similar resolution paths and current states ( Gupta: Para.[0049], the contract management system 100 utilizes the machine learning engine 118 that can easily identify trends and patterns in large volumes of data (such as training sets stored in the memory unit 116) that would otherwise not be apparent to humans. The identified trends and patterns from the large volumes of data increases the ability of the machine learning engine 118 to deliver accurate risk scores).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to incorporate Gupta’s teaching of a system and method for determining risk score for a contract document, into the system and method , taught by Mukherjee in view of Sahu, because, by determining a composite risk score for a contract document before entering into the contract, can improve the understanding and relation between two parties in the contract. (Gupta, Para.[0002-[0004]]).
Claim 10 is a system claim performing the steps in method claim 3 above and as such, claim 10 is similar in scope and content to claim 3 and therefore, claim 10 is rejected under similar rationale as presented against claim 3 above.
Claim 17 is a non-transitory computer readable storage medium claim performing the steps in method claim 3 above and as such, claim 17 is similar in scope and content to claim 3 and therefore, claim 17 is rejected under similar rationale as presented against claim 3 above.
Regarding Claim 4, Mukherjee in view of Sahu, further in view of Gupta teach the processor-implemented method of claim 3. Mukherjee further teaches, further comprising displaying, on a graphical user interface (GUI), next best actions for a manually selected resolution path or an automatically recommended choice of resolution path ( Mukherjee: Para.[0158], Fig. 11, user interface 1100 includes the menu 1132 which reads "Select an option," prompting the user 150 to select a question toward which the user 150 would like to rate an associated answer provided by the document search system 102 and/or the LLM 130. The user interface 1100 may further include the search column 1134 to allow the user 150 to key-in and search a question toward which the user 150 would like to rate an associated answer provided by the document search system 102 and/or the LLM 130).
Claim 11 is a system claim performing the steps in method claim 4 above and as such, claim 11 is similar in scope and content to claim 4 and therefore, claim 11 is rejected under similar rationale as presented against claim 4 above.
Allowable Subject Matter
Claims 5, 12 and 18 contain subject matter that is allowable over the prior art of record. They would be considered allowable if rewritten to overcome the rejection(s) under 35 U.S.C. 101, set forth in this Office action and to include all of the limitations of the base claim and any intervening claims.
Conclusion
Listed below are the prior arts made of record and not relied upon but are considered pertinent to applicant's disclosure.
Qadrud-Din et al. (US 20240289561 A1) teaches a system, method where relevance scores may be determined based on text included in a document. The text may be divided into a text portions, with the relevance scores being determined based on a comparison of a text portion of the plurality of text portions with a criterion specified in natural language. A subset of the plurality of text portions may be selected based on the plurality of relevance scores, with each of the subset of the plurality of text portions having a relevance score surpassing a threshold. A criteria evaluation prompt may be sent to a remote text generation modeling system via a communication interface. The criteria evaluation prompts may include an instruction to evaluate one or more of the subset of text portions against the criterion.
Wang et al. (US 20240412100 A1) teaches system for determination and classification of personal identifiable information in a file using machine learning is disclosed. The system includes a processing subsystem which includes a pre-processing module and a machine learning module. The preprocessing module receives a data source including a plurality of structured data, a plurality of semi-structured data, and a plurality of unstructured data from a web page, converting the data source into a machine-readable format. The machine learning module includes a feature detection module detecting personal identifiable information features from a group of a plurality of groups, a feature extraction module extracts the plurality of personal identifiable information features from the group of at least one of a static list and a stream. The context recognition module contemplates a plurality of data source-specific features to recognize the context of personal identifiable information. The classification module predicts the presence of personally identifiable information.
Perkins et al. (US 20220207229 A1) teaches a method, system, medium, and implementations for text processing. When a plurality of unstructured text strings are received, an input from a user for at least some of the plurality of unstructured text strings is received that identifies one or more structural elements. Training data are generated to include the plurality of unstructured text strings and the identified one or more structural elements associated with the at least some of the plurality of unstructured text strings. A conversion model is trained, via machine learning, based on the training data and one or more previously trained language models. The conversion model is for converting an input unstructured text string into a structured data record by identifying at least one structural data element from the raw unstructured text string.
Abraham et al. (US 20240428005 A1 ) teaches methods and systems for automatically generating documents for a specific topic using large language models. The methods and systems receive an input query that identifies a topic for the document. The methods and systems automatically generate, using the large language models, a framework for the document with sections and subsections for the document. The methods and systems write the document, using the large language models, and provide references for the data sources used to obtain the data that the large language model used to write the document.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NADIRA SULTANA whose telephone number is (571)272-4048. The examiner can normally be reached M-F,7:30 am-5:00pm.
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, Paras D. Shah can be reached on (571) 270-1650. 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.
/NADIRA SULTANA/Examiner, Art Unit 2653
Prosecution Insights