DETAILED ACTION
This Office Action is responsive to Request for Continued Examination filed on February 13th, 2026. Claims 1, 9 and 16 are amended, claims 1-20 are pending and have been examined.
Any objections/rejections not mentioned in this Office Action have been withdrawn by the Examiner.
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 .
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) is invoked.As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f). The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f). The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one of more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) because the claim limitations use a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function, and the generic placeholder is not receded by a structural modifier. Such claim limitations are “an extractor to receive…” “a graph builder to build…” and “a sentence builder to create…” in claim 9.Because these claim limitations are being interpreted under 35 U.S.C. 112(f), they are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof. Corresponding structure for performing the claimed functions is described in paragraphs [0033] and [0060] of the specification.If Applicant does not intend to have these limitations interpreted under 35 U.S.C. 112(f), Applicant may:
Amend the claim limitations to avoid interpretation under 35 U.S.C. 112(f) by reciting sufficient structure to perform the claimed function;
Present a sufficient showing that the claim limitations recite sufficient structure to perform the claimed function so as to avoid interpretation under 35 U.S.C. 112(f).
Response to Amendments and Arguments
35 U.S.C. 101:
Regarding rejection made under 35 U.S.C. 101, Applicant argues, “that the present claims are clearly directed to a practical application under Prong Two, at least because the claims are directed to a technical improvement,” (starting on page 8 of Remarks) and with citation to Specification paragraphs [0004], [0018], [0036]-[0038], [0041] and [0046]-[0047], “In view of the foregoing, Applicant respectfully submits that the claims do not recite an abstract idea and, even if determined to recite an abstract idea, clearly integrate the abstract idea into a practical application. Accordingly, the claims are not directed to an abstract idea and are eligible under § 101,” (page 9 of Remarks).
Applicant’s arguments are not persuasive. The claims as amended include steps that may be performed by a human actor, and only require generic hardware in the form of a Large Language Model and a display device, each of which may be embodied on a general-purpose computer. The operative method steps may be performed by an individual, either in their mind or with the aid of pen and paper. The steps performed with a general-purpose computer do not indicate any unexpected results or technical improvement beyond what is known in the art. Accordingly, the rejections under 35 U.S.C. 101 are maintained, further detail is provided below.
35 U.S.C. 103:
Regarding rejection made under 35 U.S.C. 103, Applicant argues, “that Liu recites, ‘[t]he acquisition module is used to acquire raw data, the raw data includes structured data, semi-structured data and unstructured data’. [Liu English translation, P. 1; emphasis added.] Applicant notes that Liu only generally refers to ‘structured data,’ but fails to describe or suggest what the structured data comprises, such as format of the structured data. For example. Liu does not show or suggest that the structured data file comprises structured data stored in a standardized tabular format, a feature added to independent claim 1 in the present response,” (page 11 of Remarks) and, “none of Erwin, Ekmekci, nor Liu, whether considered alone and/or in combination, show or suggest (a) receiving a structured data file, the structured data file comprising structured data stored in a standardized tabular format; (b) identifying tags embedded within source code for the structured data file; or (c) extracting object information from the structured data stored in the standardized tabular format of the structured data file, wherein the object information is determined at least partially based on the identified tags,” (page 12 of Applicant’s Remarks).
Applicant’s arguments are not persuasive. Liu repeatedly states that the original data used in the method comprises structured data, further indicating that the original data may be collected from database systems, wherein any person having ordinary skill in the art would reasonably expect that data to be represented in a table or otherwise standardized format. The recitation of tabular or standardized data formatting does not describe a method input outside the considerations of Liu, nor does it incorporate any unexpected or novel outcome. Accordingly, the rejections under 35 U.S.C. 103 are maintained, further detail is provided below.
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. This judicial exception is not integrated into a practical application because the recited generic computer elements do not add a meaningful limitation to the practice of the abstract idea, and amount to simply applying the abstract idea on a computer. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the recited elements beyond the generic computer elements are well-understood and routine in the art.
Regarding claim 1, the claim recites “A method, comprising:receiving a structured data file, the structured data file comprising structured data stored in a standardized tabular format;identifying tags embedded within source code for the structured data file;extracting object information from the structured data stored in the standardized tabular format of the structured data file, wherein the object information is determined at least partially based on the identified tags;building a directed graph structure based, at least in part, on the extracted object information, the directed graph structure comprising a plurality of nodes;creating two or more sentences by traversing paths of the graph structure in directions between adjacent nodes specified by the directed graph between a designated start node and the adjacent nodes until reaching a designated end node, one or more of the adjacent nodes comprising at least two direction options between other adjacent nodes;providing the two or more sentences to a Large Language Model (LLM) processor to generate two or more enhanced sentences; andoutputting the two or more enhanced sentences via at least a display device.”
The limitations of “receiving a structured data file…” “identifying tags embedded within source code…” “extracting object information from the structured data…” “building a directed graph…” and “creating two or more sentences by traversing paths of the graph structure,” as drafted cover mental activities which can be performed in the mind or with the aid of pen and paper. Taken individually, or as a whole, these limitations describe acts which are equivalent to human mental work of summarizing technical information. For example, these limitations could be embodied by an individual receiving a bill of materials or connection chart for a circuit board, drawing a circuit diagram based on that information, then creating written descriptions of the represented circuit based on the connections between elements of the diagram.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because the additional limitations of “provide the one or more created sentences to a Large Language Model (LLM) processor to generate one or more enhanced sentences,” and “output the one or more enhanced sentences,” describe acts which are well-understood and routine in the art. A processor implementing a large language model, wherein a user may prompt the model with a sentence to receive an output sentence, is commonplace and readily available to a person having ordinary skill in the art of language processing. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 2, the claim depends from claim 1, and thus recites the limitations of claim 1, “wherein the structured data file comprises an Extensible Markup Language (XML) file or a JavaScript Object Notation (JSON) file.”
The limitation of “the structured data file comprises an Extensible Markup Language (XML) file or a JavaScript Object Notation (JSON) file,” as drafted covers activity that is well-understood and routine in the art. The recited file types are commonplace and readily available to a person having ordinary skill in the art of computer science and structured data processing. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 3, the claim depends from claim 1, and thus recites the limitations of claim 1, “wherein the LLM processor employs one or more transformers.”
The limitation of “the LLM processor employs one or more transformers,” as drafted covers activity that is well-understood and routine in the art. The recited transformers are commonplace and readily available to a person having ordinary skill in the art of language processing. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 4, the claim depends from claim 1, and thus recites the limitations of claim 1, “wherein the object information comprises one or more of object labels, process pathways, or decision points.”
Taken individually, or as a whole with claim 1, these limitations describe acts which are equivalent to human mental work of summarizing data using a particular format. Referring to the example given for claim 1, these limitations could be embodied by an individual using standard component drawings when creating a description of a circuit diagram. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 5, the claim depends from claim 1, and thus recites the limitations of claim 1, “wherein the structured data file comprises a directed graph.”
Taken individually, or as a whole with claim 1, these limitations describe acts which are equivalent to human mental work of summarizing pre-selected data. Referring to the example given for claim 1, these limitations could be embodied by an individual writing a description of circuit diagram based on a provided diagram. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 6, the claim depends from claim 1, and thus recites the limitations of claim 1, “further comprising saving the one or more enhanced sentences as an unstructured data file.”
Taken individually, or as a whole with claim 1, these limitations describe acts which are equivalent to human mental work of summarizing data using a particular format. Referring to the example given for claim 1, these limitations could be embodied by an individual using a word processing file or even a notebook to store a description of a circuit diagram. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 7, the claim depends from claim 1, and thus recites the limitations of claim 1, “wherein the one or more enhanced sentences comprise textual data.”
Taken individually, or as a whole with claim 1, these limitations describe acts which are equivalent to human mental work of summarizing data using a particular format. Referring to the example given for claim 1, these limitations could be embodied by an individual using words to describe a circuit diagram. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claim 8, the claim depends from claim 1, and thus recites the limitations of claim 1, “further comprising the LLM processor performing Natural Language Processing on the one or more created sentences.”
The limitation of “the LLM processor performing Natural Language Processing on the one or more created sentences,” as drafted covers activity that is well-understood and routine in the art. The recited natural language processing is commonplace and readily available to a person having ordinary skill in the art of large language models. Accordingly, the claim is directed to an abstract idea without significantly more. The claim is not patent eligible.
Regarding claims 9-15, system claims 9-15 and method claims 1-5 and 7-8 are related as a method and system of using the same, with each system element’s function corresponding to the method step. Accordingly, claims 9-15 are similarly rejected under the same rationale as applied to claims 1-5 and 7-8.
Regarding claims 16-20, computer-readable medium claims 16-20 and method claims 1-2, 4-5 and 8 are related as method and computer-readable medium for performing the same, with each computer-readable medium element’s function corresponding to the method step. Accordingly, claims 16-20 are similarly rejected under the same rationale as applied to claims 1-2, 4-5 and 8.
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 1-2, 6-10 and 14-15 are rejected under 35 U.S.C. 103 as being unpatentable over China Invention Application 116150283 to Liu et al. (hereinafter, "Liu") in view of U.S. Patent Application Publication 2007/0198247 to Erwin et al. (hereinafter, "Erwin") and U.S. Patent Application Publication 2020/0242299 to Ekmekci et al. (hereinafter, "Ekmekci").
Regarding claim 1, Liu teaches a method comprising receiving a structured data file, the structured data file comprising structured data stored in a standardized tabular format (page 4 of included document, section "Embodiment 1”, “wherein the obtaining module 10 can be used for obtaining the original data module. The original data may be a data set that is not processed or simplified, and the original data may be acquired from a database or a middle station, or may be obtained in other ways. The original data may include structured data, semi-structured data and unstructured data, that is, the original data can be multi-source heterogeneous data, multi-source heterogeneous data from a plurality of data sources, comprising different database systems and data set collected in the work of different devices. In this embodiment, the type of the original data is not limited, for example, the original data can be power data in the power field, also can be hydraulic data in the hydraulic field.wherein the structured data can be stored and arranged is a regular data, it can use relational database to represent and store. semi-structured data can be data of the data format is not fixed data, namely the same entity can have different attributes, semi-structured data can be adjusted by flexible key value to obtain the corresponding information.");
identifying tags embedded within source code for the structured data file (page 4 of included document, section "Embodiment 1", "wherein the knowledge extraction is from different sources, knowledge extraction is performed in the data with different structures, forming knowledge (structured data) is stored in the knowledge graph Knowledge merging refers to obtaining knowledge input from the third party knowledge base product or the existing structured data when constructing the knowledge graph there are two common knowledge combining requirements, one is combining the external knowledge base, the other one is the combined relation database. combining the external knowledge base, the external knowledge base is fused to the local knowledge base needs to process 2 layers of the problem: fusion of the data layer, comprising an entity of the name, attribute, relation and the category and so on, the main problem is how to avoid the conflict problem of the instance and relation, causing unnecessary redundancy;");
extracting object information from the structured data stored in the standardized tabular format of the structured data file, wherein the object information is determined at least partially based on the identified tags (page 4 of included document, section "Embodiment 1”, "In this embodiment, after obtaining the original data, because the data in the original data is too multivariate, so for structured data in the original data, semi-structured data and unstructured data, it can adopt automatic or semi-automatic method to process, so as to finish the task of extracting information from the original data. for semi-structured data and unstructured data, can be extracted by the extracting module 20 using the preset model for knowledge extraction, to obtain semi-structured data and data information in the unstructured data aiming at the structured data, using knowledge combination to process the redundant information, the combining module 30 combines the structured data with the third party database knowledge to obtain the data set, so as to obtain more complete data.");
building a directed graph structure based, at least in part, on the extracted object information, the directed graph structure comprising a plurality of nodes (page 4 of included document, section "Embodiment 1”, "a constructing module 50, used for based on the knowledge base to construct main body model of generating knowledge graph").
Liu does not explicitly teach “creating two or more sentences by traversing paths of the graph structure in directions between adjacent nodes specified by the directed graph between a designated start node and the adjacent nodes until reaching a designated end node, one or more of the adjacent nodes comprising at least two direction options between other adjacent nodes,” and thus, Erwin is introduced.
Erwin teaches creating two or more sentences by traversing paths of the graph structure in directions between adjacent nodes specified by the directed graph between a designated start node and the adjacent nodes until reaching a designated end node, one or more of the adjacent nodes comprising at least two direction options between other adjacent nodes (paragraph [0007], "In an embodiment, a sentence is created that describes a walk of a graph. The graph includes a set of nodes and a set of edges that are incident to the nodes. The sentence includes label words that describe the nodes and relationship words that describe the edges. The walk is an alternating sequence of a subset of the nodes and of the edges. Each of the edges in the walk is incident to two of the nodes that precede and follow the respective edge. The sentence is created by determining a parent node associated with a selected label word, determining the child nodes of the parent node, determining the edges that are incident to the parent nodes and the child nodes, determining relationship words that describe the edges that are incident to the parent nodes and the child nodes, and determining child label words that describe the child nodes," paragraph [0030], "A walk is an alternating sequence of a subset of the nodes 170 and edges 174 of the graph 155, beginning with a first-node and ending with a last-node, in which each node 170 in the walk is incident to the two edges 174 that precede and follow it in the sequence, and the nodes 170 that precede and follow an edge 174 are the end-nodes of that edge." and paragraph [0019], "An edge 174 connects two nodes 170; these two nodes are referred to as incident to that edge, or, equivalently, that edge is incident to those two nodes. The edges 174 may have a direction, in which case the edges 174 are called directed edges. If a direction of an edge 174 is away from a first node and toward a second node, the first node is said to be the parent node of the second node, which is the child node of the first node.").
Liu and Erwin are considered analogous because they are each concerned with processing graph representations of data. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified the graph creation of Liu with the graph traversal of Erwin for the purpose of improving data graph accessibility. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
The combination of Liu and Erwin does not teach “provide the one or more created sentences to a Large Language Model (LLM) processor to generate one or more enhanced sentences; and output the one or more enhanced sentences via at least a display device,” and thus, Ekmekci is introduced.
Ekmekci teaches provide the one or more created sentences to a Large Language Model (LLM) processor to generate one or more enhanced sentences (paragraph [0062], "Once extracts are selected for inclusion in summaries, techniques may be applied to improve the overall quality of the summary. Improvement on the sentence level includes compression and sentence fusion. Improvement on the discourse (e.g., summary) level includes lexical chains, WordNet-based concepts, and discourse relation and graph representations."); and output the one or more enhanced sentences via at least a display device (paragraph [0035], "Output generator 124 may be configured to output the extracted summary. For example, output generator 124 may store the extracted summary, may output the extracted summary to a display device, or may output the extracted summary to another device, such as user terminal 160, as non-limiting examples.").
Liu, Erwin and Ekmekci are considered analogous because they are each concerned with natural language processing. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Liu and Erwin with the teachings of Ekmekci for the purpose of improving data graph summarization quality. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Claim 9 is a system claim with limitations similar to those of method claim 1, and is rejected under the same rationale. Additionally, Liu teaches a system, comprising an extractor to receive a structured data file and extract object information from the structured data file (page 2 of included document, section “Contents of the Invention”, "According to one aspect of the present invention, there is knowledge graph a body building system, comprising an obtaining module, an extracting module, a combining module, a fusion module and a constructing module;");a graph builder to build a graph structure based, at least in part, on the extracted object information (page 2 of included document, section “Contents of the Invention”, "According to one aspect of the present invention, there is knowledge graph a body building system, comprising an obtaining module, an extracting module, a combining module, a fusion module and a constructing module;").
The combination of Liu and Erwin teaches a system comprising a sentence builder to create one or more sentences by traversing paths of the graph structure (Erwin, paragraph [0018], “The controller 150 creates the sentence 160 from a selected subset of the graph 155.”) and the combination of Liu, Erwin and Ekmekci teaches a system comprising a Large Language Model (LLM) processor to generate one or more enhanced sentences based, at least in part, on the one or more created sentences (Ekmekci, paragraph [0075], “A system of the present disclosure is a custom NLP processing pipeline capable of the ingesting and analyzing hundreds of thousands of text documents relative to an initial manually-curated (e.g., user defined) seed taxonomy, such as a first keyword set.”).
Liu, Erwin and Ekmekci are considered analogous because they are each concerned with natural language processing. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Liu and Erwin with the teachings of Ekmekci for the purpose of improving data graph summarization usability. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Regarding claims 2 and 10, Liu further teaches a method and system wherein the structured data file comprises an Extensible Markup Language (XML) file or a JavaScript Object Notation (JSON) file (page 4 of included document, section “Embodiment 1”, "As json, the information stored under the same key value may be numerical type, may be text type, also may be a dictionary or list. can unstructured data data [sic] without fixed structure, can unstructured data office document of all format, text, picture, XML, HTML, various types of report, image and audio/video information and so on.").
Regarding claim 6, the combination of Liu and Erwin does not teach “The method of claim 1, further comprising saving the one or more enhanced sentences as an unstructured data file,” however, Ekmekci teaches saving the one or more enhanced sentences as an unstructured data file (paragraph [0096], "Summarization processes 316 may output one or more extracted summaries as risk summarization output file 318.").
Liu, Erwin and Ekmekci are considered analogous because they are each concerned with natural language processing. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Liu and Erwin with the teachings of Ekmekci for the purpose of improving data graph summarization usability. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Regarding claims 7 and 14, Liu does not explicitly teach a method or system “wherein the one or more enhanced sentences comprise textual data,” however, Ekmekci teaches the one or more enhanced sentences comprise textual data (paragraph [0004], “To improve the information provided by the text extractions, the text extractions may be used to generate summaries. Two categories of automatic text summarization include abstractive summarization and extractive summarization. Abstractive summarization techniques identify relevant phrases or sentences, then rewrite the identified phrases or sentences to form a summary.”).
Liu and Erwin are considered analogous because they are each concerned with processing graph representations of data. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Liu with the teachings of Erwin for the purpose of improving data graph usability. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Regarding claims 8 and 15, the combination of Liu and Erwin does not teach a method or system “comprising the LLM processor performing Natural Language Processing on the one or more created sentences,” however, Ekmekci teaches the LLM processor performing Natural Language Processing on the one or more created sentences (paragraph [0005], "For example, data including text from a data source, such as a streaming data source, news data, a database, or a combination thereof, may be received and natural language processing (NLP) performed on the data.").
Liu, Erwin and Ekmekci are considered analogous because they are each concerned with natural language processing. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Liu and Erwin with the teachings of Ekmekci for the purpose of improving data graph summarization usability. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Claims 3, 5, 11 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Liu, Erwin and Ekmekci as applied to claims 1 and 9 above, and further in view of U.S. Patent 11,727,210 to Wang et al. (hereinafter, "Wang").
Regarding claims 3 and 11, the combination of Liu, Erwin and Ekmekci does not explicitly teach a method or system “wherein the LLM processor employs one or more transformers,” and thus, Wang is introduced.
Wang teaches the LLM processor employs one or more transformers (column 6, lines 26-30, “The pre-trained generative language models included in data-to-text module 170 may be the BART-base model, the BART-xsum-12-6 model or the T5-base model trained using training module 160 to include token embeddings and position aware embeddings.”).” Though not explicitly stated in the disclosure, a person having ordinary skill in the art would recognize that the recited “BART-based model” represents “Bidirectional and Auto-Regressive Transformer” and the recited “T5-based model” represents “Text-to-Text Transfer Transformer”.
Liu, Erwin, Ekmekci and Wang are considered analogous because they are each concerned with language processing of data. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Liu with the teachings of Wang for the purpose of improving data graph quality. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Regarding claims 5 and 13, the combination of Liu, Erwin and Ekmekci does not explicitly teach a method, system or storage medium “wherein the structured data file comprises a directed graph,” however, Wang teaches the structured data file comprises a directed graph (column 4, lines 1-2, “Computing device 100 may receive input 140, which may be structured data, such as an RDF graph,”).
Liu, Erwin, Ekmekci and Wang are considered analogous because they are each concerned with language processing of data. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Liu with the teachings of Wang for the purpose of improving data graph quality. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Claims 4, 12 and 16-18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Liu, Erwin and Ekmekci as applied to claims 1 and 9 above, and further in view of China Invention Application 107526717 to Zeng et al. (hereinafter, "Zeng").
Claim 16 is a computer program product claim with limitations similar to method claim 1, and is rejected under the same rationale. Additionally, Liu teaches non-transitory storage medium comprising machine-readable instructions executable by a processor (page 2 of included document, section “Contents of the Invention”, "According to another aspect of the present invention, there is provided a computer-readable storage medium, the computer-readable storage medium stores a computer instruction, the computer instructions for causing the processor to implement any one embodiment of the invention the method for constructing the knowledge graph").
Liu does not explicitly teach the Business Process Model and Notation file recited by the claim, and thus Zeng is introduced. Zeng teaches receiving a Business Process Model and Notation (BPMN) file; extracting object information from the BPMN file (page 2 of included document, section “invention content”, "label text information analyzing module which is used for obtaining and analyzing the BPMN (Business Process Model and Notation, business process model and labeling) the process model in the tag model elements, obtained text information including nodes, edges and lane of the text information, and then analyzing the text using semantic role labelling information;").
Liu and Zeng are considered analogous because they are each concerned with processing structured data. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have replaced the structured data of Liu with the BPMN file of Zeng for the purpose of extracting structured information, given that the substitution of one known element for another yields predictable results.
Regarding claims 4, 12 and 18, the combination of Liu, Erwin and Ekmekci does not explicitly teach a method, system or storage medium “wherein the object information comprises one or more of object labels, process pathways, or decision points,” however, Zeng teaches the object information comprises one or more of object labels, process pathways, or decision points (page 2 of included document, section “invention content”, "label text information analyzing module which is used for obtaining and analyzing the BPMN (Business Process Model and Notation, business process model and labeling) the process model in the tag model elements, obtained text information including nodes, edges and lane of the text information, and then analyzing the text using semantic role labelling information;").
Liu, Erwin, Ekmekci and Zeng are considered analogous because they are each concerned with natural language processing. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Liu ,Erwin and Ekmekci with the teachings of Zeng for the purpose of improving data graph summarization usability. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Regarding claim 17, Liu further teaches a storage medium wherein the structured data file comprises an Extensible Markup Language (XML) file or a JavaScript Object Notation (JSON) file (page 4 of included document, section “Embodiment 1”, "As json, the information stored under the same key value may be numerical type, may be text type, also may be a dictionary or list. can unstructured data data [sic] without fixed structure, can unstructured data office document of all format, text, picture, XML, HTML, various types of report, image and audio/video information and so on.").
Regarding claim 20, the combination of Liu and Zeng does not teach a storage medium “comprising the LLM processor performing Natural Language Processing on the one or more created sentences,” however, Ekmekci teaches the LLM processor performing Natural Language Processing on the one or more created sentences (paragraph [0005], "For example, data including text from a data source, such as a streaming data source, news data, a database, or a combination thereof, may be received and natural language processing (NLP) performed on the data.").
Liu, Erwin, Ekmekci and Zeng are considered analogous because they are each concerned with natural language processing. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Liu, Erwin and Zeng with the teachings of Ekmekci for the purpose of improving data graph summarization usability. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Claim 19 is rejected under 35 U.S.C. 103 as being unpatentable over Liu, Erwin, Ekmekci and Zeng as applied to claim 16 above, and further in view of Wang.
Regarding claim 19, the combination of Liu, Erwin and Ekmekci does not explicitly teach a method, system or storage medium “wherein the structured data file comprises a directed graph,” however, Wang teaches the structured data file comprises a directed graph (column 4, lines 1-2, “Computing device 100 may receive input 140, which may be structured data, such as an RDF graph,”).
Liu, Erwin, Ekmekci, Zeng and Wang are considered analogous because they are each concerned with language processing of data. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to have modified Liu with the teachings of Wang for the purpose of improving data graph quality. Given that all the claimed elements were known in the prior art, one skilled in the art could have combined the elements by known methods with no change in their respective functions, and the combination would have yielded nothing more than predictable results.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
“JarviX: A LLM No Code Platform for Tabular Data Analysis and Optimization” by Liu et al.
“TableGPT: Towards Unifying Tables, Nature Language and Commands into Onge GPT” by Zha et al.
“TabText: A Flexible and Contextual Approach to Tabular Data Representation” by Carballo et al.
International Publication WO 2011/103040 to Choudhary et al.
China Invention Application 115618006 to Yin.
China Invention Application 112732643 to Jiang and Sun.
U.S. Patent 8,417,513 to Prompt et al.
U.S. Patent Application Publication 2023/0418856 to Cai et al.
U.S. Patent Application Publication 2020/0142957 to Patra et al.
German Patent Disclosure DE 102019000294 to Srinivasan et al.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SEAN T SMITH whose telephone number is (571)272-6643. The examiner can normally be reached Monday - Friday 8:00am - 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, PIERRE-LOUIS DESIR can be reached at (571) 272-7799. 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.
/SEAN THOMAS SMITH/Examiner, Art Unit 2659
/PIERRE LOUIS DESIR/Supervisory Patent Examiner, Art Unit 2659
Prosecution Insights