Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
2. The information disclosure statement (IDS) submitted on February 06, 2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Rejections - 35 USC § 101
3. 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.
4. Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Independent claim 1 recites “A system comprising: a processor system; and a memory that stores computer-executable instructions that are executable by the processor system to at least: receive a natural language prompt, which requests data that satisfies a search criterion from a database that stores entities; assign relevance scores to entity names of the entities, each relevance score indicating an extent to which a respective entity name corresponds to content of a respective entity; define entity name representations to represent the entities by performing the following: for each entity having an entity name that is assigned a relevance score that is less than a relevance threshold, define the entity name representation of the respective entity to be a respective replacement name, which is based at least on the content of the respective entity, rather than the entity name of the respective entity; and for each entity having an entity name that is assigned a relevance score that is greater than or equal to the relevance threshold, define the entity name representation of the respective entity to be the respective entity name; generate a first AI prompt that requests an indication of which of the entity name representations is relevant to the natural language prompt; cause an AI model to determine a first subset of the entity name representations that is relevant to the natural language prompt and a second subset of the entity name representations that is not relevant to the natural language prompt by providing the first AI prompt together with first contextual information as first inputs to the AI model, the first contextual information including the natural language prompt and the entity name representations, wherein the natural language prompt and the entity name representations include context regarding the first AI prompt; generate a second AI prompt that requests conversion of the natural language prompt to a system-specific segment definition that conforms to a system-specific segment definition format that is specific to a customer data platform system; and based at least on receipt of a response to the first AI prompt from the AI model that indicates the first and second subsets of the entity name representations, cause the AI model to convert the natural language prompt to the system-specific segment definition by providing the second AI prompt together with second contextual information as second inputs to the AI model, the second contextual information including the natural language prompt and information regarding the system-specific segment definition format and the first subset of the entity name representations and not including the second subset of the entity name representations, wherein the natural language prompt, the information regarding the system-specific segment definition format, and the first subset of the entity name representations include context regarding the second AI prompt”.
The limitations “receive a natural language prompt, which requests data that satisfies a search criterion from a database that stores entities; assign relevance scores to entity names of the entities, each relevance score indicating an extent to which a respective entity name corresponds to content of a respective entity; define entity name representations to represent the entities by performing the following: for each entity having an entity name that is assigned a relevance score that is less than a relevance threshold, define the entity name representation of the respective entity to be a respective replacement name, which is based at least on the content of the respective entity, rather than the entity name of the respective entity; and for each entity having an entity name that is assigned a relevance score that is greater than or equal to the relevance threshold, define the entity name representation of the respective entity to be the respective entity name; generate a first AI prompt that requests an indication of which of the entity name representations is relevant to the natural language prompt; cause an AI model to determine a first subset of the entity name representations that is relevant to the natural language prompt and a second subset of the entity name representations that is not relevant to the natural language prompt by providing the first AI prompt together with first contextual information as first inputs to the AI model, the first contextual information including the natural language prompt and the entity name representations, wherein the natural language prompt and the entity name representations include context regarding the first AI prompt; generate a second AI prompt that requests conversion of the natural language prompt to a system-specific segment definition that conforms to a system-specific segment definition format that is specific to a customer data platform system; and based at least on receipt of a response to the first AI prompt from the AI model that indicates the first and second subsets of the entity name representations, cause the AI model to convert the natural language prompt to the system-specific segment definition by providing the second AI prompt together with second contextual information as second inputs to the AI model, the second contextual information including the natural language prompt and information regarding the system-specific segment definition format and the first subset of the entity name representations and not including the second subset of the entity name representations, wherein the natural language prompt, the information regarding the system-specific segment definition format, and the first subset of the entity name representations include context regarding the second AI prompt” as drafted, covers a mental process, as this could be done by mentally or by hand with pen and paper.
This judicial exception is not integrated into a practical application. Claim 1 recites “A system comprising: a processor system; and a memory that stores computer-executable instructions that are executable by the processor system to at least:…”.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The addition of the generic computer components recited above with regard to claim 1 do not amount to more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Claim 1 does not recite any additional limitations. The claim as drafted, is not patent eligible.
Independent claim 12 recites “A method implemented by a computing system, the method comprising: receiving a natural language prompt, which requests data that satisfies a search criterion from a database that stores entities; assigning relevance scores to entity names of the entities, each relevance score indicating an extent to which a respective entity name corresponds to content of a respective entity; defining entity name representations to represent the entities by performing the following: for each entity having an entity name that is assigned a relevance score that is less than a relevance threshold, defining the entity name representation of the respective entity to be a respective replacement name, which is based at least on the content of the respective entity, rather than the entity name of the respective entity; and for each entity having an entity name that is assigned a relevance score that is greater than or equal to the relevance threshold, defining the entity name representation of the respective entity to be the respective entity name; generating a first AI prompt that requests an indication of which of the entity name representations is relevant to the natural language prompt; causing an AI model to determine a first subset of the entity name representations that is relevant to the natural language prompt and a second subset of the entity name representations that is not relevant to the natural language prompt by providing the first AI prompt together with first contextual information as first inputs to the AI model, the first contextual information including the natural language prompt and the entity name representations, wherein the natural language prompt and the entity name representations include context regarding the first AI prompt; generating a second AI prompt that requests conversion of the natural language prompt to a system-specific segment definition that conforms to a system-specific segment definition format that is specific to a customer data platform system; and based at least on receipt of a response to the first AI prompt from the AI model that indicates the first and second subsets of the entity name representations, causing the AI model to convert the natural language prompt to the system-specific segment definition by providing the second AI prompt together with second contextual information as second inputs to the AI model, the second contextual information including the natural language prompt and information regarding the system-specific segment definition format and the first subset of the entity name representations and not including the second subset of the entity name representations, wherein the natural language prompt, the information regarding the system-specific segment definition format, and the first subset of the entity name representations include context regarding the second AI prompt”.
The limitations “receiving a natural language prompt, which requests data that satisfies a search criterion from a database that stores entities; assigning relevance scores to entity names of the entities, each relevance score indicating an extent to which a respective entity name corresponds to content of a respective entity; defining entity name representations to represent the entities by performing the following: for each entity having an entity name that is assigned a relevance score that is less than a relevance threshold, defining the entity name representation of the respective entity to be a respective replacement name, which is based at least on the content of the respective entity, rather than the entity name of the respective entity; and for each entity having an entity name that is assigned a relevance score that is greater than or equal to the relevance threshold, defining the entity name representation of the respective entity to be the respective entity name; generating a first AI prompt that requests an indication of which of the entity name representations is relevant to the natural language prompt; causing an AI model to determine a first subset of the entity name representations that is relevant to the natural language prompt and a second subset of the entity name representations that is not relevant to the natural language prompt by providing the first AI prompt together with first contextual information as first inputs to the AI model, the first contextual information including the natural language prompt and the entity name representations, wherein the natural language prompt and the entity name representations include context regarding the first AI prompt; generating a second AI prompt that requests conversion of the natural language prompt to a system-specific segment definition that conforms to a system-specific segment definition format that is specific to a customer data platform system; and based at least on receipt of a response to the first AI prompt from the AI model that indicates the first and second subsets of the entity name representations, causing the AI model to convert the natural language prompt to the system-specific segment definition by providing the second AI prompt together with second contextual information as second inputs to the AI model, the second contextual information including the natural language prompt and information regarding the system-specific segment definition format and the first subset of the entity name representations and not including the second subset of the entity name representations, wherein the natural language prompt, the information regarding the system-specific segment definition format, and the first subset of the entity name representations include context regarding the second AI prompt” as drafted, covers a mental process, as this could be done by mentally or by hand with pen and paper.
This judicial exception is not integrated into a practical application. Claim 8 recites “A method implemented by a computing system, the method comprising:…”.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The addition of the generic computer components recited above with regard to claim 12 do not amount to more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Claim 12 does not recite any additional limitations. The claim as drafted, is not patent eligible.
Independent claim 20 recites “A computer program product comprising a computer-readable storage medium having instructions recorded thereon for enabling a processor-based system to perform operations, the operations comprising: receiving a natural language prompt, which requests data that satisfies a search criterion from a database that stores entities; assigning relevance scores to entity names of the entities, each relevance score indicating an extent to which a respective entity name corresponds to content of a respective entity; defining entity name representations to represent the entities by performing the following: for each entity having an entity name that is assigned a relevance score that is less than a relevance threshold, defining the entity name representation of the respective entity to be a respective replacement name, which is based at least on the content of the respective entity, rather than the entity name of the respective entity; and for each entity having an entity name that is assigned a relevance score that is greater than or equal to the relevance threshold, defining the entity name representation of the respective entity to be the respective entity name; generating a first AI prompt that requests an indication of which of the entity name representations is relevant to the natural language prompt; causing an AI model to determine a first subset of the entity name representations that is relevant to the natural language prompt and a second subset of the entity name representations that is not relevant to the natural language prompt by providing the first AI prompt together with first contextual information as first inputs to the AI model, the first contextual information including the natural language prompt and the entity name representations, wherein the natural language prompt and the entity name representations include context regarding the first AI prompt; generating a second AI prompt that requests conversion of the natural language prompt to a system-specific segment definition that conforms to a system-specific segment definition format that is specific to a customer data platform system; and based at least on receipt of a response to the first AI prompt from the AI model that indicates the first and second subsets of the entity name representations, causing the AI model to convert the natural language prompt to the system-specific segment definition by providing the second AI prompt together with second contextual information as second inputs to the AI model, the second contextual information including the natural language prompt and information regarding the system-specific segment definition format and the first subset of the entity name representations and not including the second subset of the entity name representations, wherein the natural language prompt, the information regarding the system-specific segment definition format, and the first subset of the entity name representations include context regarding the second AI prompt”.
The limitations “receiving a natural language prompt, which requests data that satisfies a search criterion from a database that stores entities; assigning relevance scores to entity names of the entities, each relevance score indicating an extent to which a respective entity name corresponds to content of a respective entity; defining entity name representations to represent the entities by performing the following: for each entity having an entity name that is assigned a relevance score that is less than a relevance threshold, defining the entity name representation of the respective entity to be a respective replacement name, which is based at least on the content of the respective entity, rather than the entity name of the respective entity; and for each entity having an entity name that is assigned a relevance score that is greater than or equal to the relevance threshold, defining the entity name representation of the respective entity to be the respective entity name; generating a first AI prompt that requests an indication of which of the entity name representations is relevant to the natural language prompt; causing an AI model to determine a first subset of the entity name representations that is relevant to the natural language prompt and a second subset of the entity name representations that is not relevant to the natural language prompt by providing the first AI prompt together with first contextual information as first inputs to the AI model, the first contextual information including the natural language prompt and the entity name representations, wherein the natural language prompt and the entity name representations include context regarding the first AI prompt; generating a second AI prompt that requests conversion of the natural language prompt to a system-specific segment definition that conforms to a system-specific segment definition format that is specific to a customer data platform system; and based at least on receipt of a response to the first AI prompt from the AI model that indicates the first and second subsets of the entity name representations, causing the AI model to convert the natural language prompt to the system-specific segment definition by providing the second AI prompt together with second contextual information as second inputs to the AI model, the second contextual information including the natural language prompt and information regarding the system-specific segment definition format and the first subset of the entity name representations and not including the second subset of the entity name representations, wherein the natural language prompt, the information regarding the system-specific segment definition format, and the first subset of the entity name representations include context regarding the second AI prompt” as drafted, covers a mental process, as this could be done by mentally or by hand with pen and paper.
This judicial exception is not integrated into a practical application. Claim 20 recites “A computer program product comprising a computer-readable storage medium having instructions recorded thereon for enabling a processor-based system to perform operations, the operations comprising:…”.
The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The addition of the generic computer components recited above with regard to claim 20 do not amount to more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Claim 20 does not recite any additional limitations. The claim as drafted, is not patent eligible.
Claim Rejections - 35 USC § 102
5. The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
6. Claims 1-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Sha (U.S. Publication No. 20230359826).
Regarding claim 1, Sha discloses a processor system ([0092] - Various systems, apparatus, and methods described herein may be implemented using digital circuitry, or using one or more computers using well-known computer processors, memory units, storage devices, computer software);
and a memory that stores computer-executable instructions that are executable by the processor system to at least ([0092] - Various systems, apparatus, and methods described herein may be implemented using digital circuitry, or using one or more computers using well-known computer processors, memory units, storage devices, computer software):
receive a natural language prompt, which requests data that satisfies a search criterion from a database that stores entities ([0034] - natural language processing (NLP)… entity extraction [0046] - the system 100 further generates a confirmed database configured to store confirmed attribute data and a candidate database configured to store candidate attribute data);
assign relevance scores to entity names of the entities, each relevance score indicating an extent to which a respective entity name corresponds to content of a respective entity ([0051] - the system calculates an ER score based on the ER map. In some embodiments, only candidate attribute data having similarities counts in the ER score. The system classifies the one or more candidate entities to be at least confirmed, relevant, or irrelevant based on the ER score);
define entity name representations to represent the entities by performing the following:
for each entity having an entity name that is assigned a relevance score that is less than a relevance threshold, define the entity name representation of the respective entity to be a respective replacement name, which is based at least on the content of the respective entity, rather than the entity name of the respective entity ([0051] - if an ER score of a candidate entity is lower than the threshold value, the system determines the candidate entity is not yet identified as the target entity (234). As shown in FIG. 2, content pages comprising the candidate entity are kept in the folder and will be processed in the next iteration);
and for each entity having an entity name that is assigned a relevance score that is greater than or equal to the relevance threshold, define the entity name representation of the respective entity to be the respective entity name ([0051] - the system determines whether the ER score is greater than or equal to a threshold value. Then the system classifies the one or more candidate entities to be at least confirmed, relevant, or irrelevant in response to the ER score being greater than or equal to the threshold value);
generate a first AI prompt that requests an indication of which of the entity name representations is relevant to the natural language prompt ([0071] - For candidate entities classified to be relevant entities, the system extracts corresponding candidate attribute data related to the relevant candidate entities as relevant knowledge);
cause an AI model to determine a first subset of the entity name representations that is relevant to the natural language prompt and a second subset of the entity name representations that is not relevant to the natural language prompt by providing the first AI prompt together with first contextual information as first inputs to the AI model, the first contextual information including the natural language prompt and the entity name representations, wherein the natural language prompt and the entity name representations include context regarding the first AI prompt ([0059] - the system can identify at least one of names comprising nick names, phonetic variations, typographical mistakes, contextual differences, reordered terms, prefixes and suffixes, abbreviations and initials, or truncated letters and missing as matched names. [0081] - classifying the one or more candidate entities to be at least confirmed, relevant, or irrelevant entities based on the similarities of the candidate attribute data (step 1020), classifying the corresponding candidate attribute data related to the candidate entities to be confirmed, relevant, or irrelevant attribute data (step 1030), and discarding content pages associated with candidate entities classified as irrelevant (step 1040));
generate a second AI prompt that requests conversion of the natural language prompt to a system-specific segment definition that conforms to a system-specific segment definition format that is specific to a customer data platform system ([0037] - the CAU engine 110 is a computer-implemented engine configured to obtain attribute data by digesting customer information in an indication or content pages. A customer can be an individual entity or a business entity. The customer information comprises attribute data of one or more entities);
and based at least on receipt of a response to the first AI prompt from the AI model that indicates the first and second subsets of the entity name representations, causing the AI model to convert the natural language prompt to the system-specific segment definition by providing the second AI prompt together with second contextual information as second inputs to the AI model, the second contextual information including the natural language prompt and information regarding the system-specific segment definition format and the first subset of the entity name representations and not including the second subset of the entity name representations, wherein the natural language prompt, the information regarding the system-specific segment definition format, and the first subset of the entity name representations include context regarding the second AI prompt ([0059] - the system can identify at least one of names comprising nick names, phonetic variations, typographical mistakes, contextual differences, reordered terms, prefixes and suffixes, abbreviations and initials, or truncated letters and missing as matched names. [0071] - the system converts that candidate attribute data extracted from the content pages to vectors using a BERT (Bidirectional Encoder Representations from Transformers) variant model, and performs a K-mean clustering process for the vectors In some embodiments, during the extraction, the system also records source information of the candidate attribute data. The source information identifies the sources of extracted candidate attributed data in the plurality of content pages. As shown in FIG. 8, in row 830, the source information (e.g., source_link) as well as part of the content pages are shown in summarization map 800).
Regarding claim 2, Sha discloses the system, wherein the entities includes tables ([0062] - a user interface providing ER configurations for a business entity in an ER map 700 in accordance with some embodiments. ER configuration shown in FIGS. 6 and 7 include attribute type columns (610 and 710) and columns for receiving values as user inputs for the attribute types).
Regarding claim 3, Sha discloses the system, wherein the entities include columns, which are included in tables ([0062] - a user interface providing ER configurations for a business entity in an ER map 700 in accordance with some embodiments. ER configuration shown in FIGS. 6 and 7 include attribute type columns (610 and 710) and columns for receiving values as user inputs for the attribute types).
Regarding claim 4, Sha discloses the system, wherein the second contextual information further comprises an indication of relationships between entities that are included in a subset of the entities that corresponds to the first subset of the entity name representations ([0081] - classifying the one or more candidate entities to be at least confirmed, relevant, or irrelevant entities based on the similarities of the candidate attribute data (step 1020), classifying the corresponding candidate attribute data related to the candidate entities to be confirmed, relevant, or irrelevant attribute data (step 1030), and discarding content pages associated with candidate entities classified as irrelevant (step 1040)).
Regarding claim 5, Sha discloses the system, wherein the computer-executable instructions are executable by the processor system to assign the relevance scores to the entity names by performing the following:
generate quantitative relevance scores associated with the respective entity names by using a multi-layer perception (MLP) to compare, for each entity, quantitative dimensions of the entity to the respective entity name, each of the quantitative relevance scores representing an extent to which the respective entity name corresponds to the quantitative dimensions of the respective entity ([0037] - the CAU engine 110 identifies address information by using an information extraction deep learning model. Such an information extraction deep learning model can be based on, for example, NER deep learning model, machine QA deep learning model, recurrent neural networks (RNNs) models, hidden markov models (HMM) and conditional random fields (CRF) models, universal language model fine-tuning (ULMfit), embeddings from language models (ELMo) and texts vectorization models, such as term frequency-inverse document frequency (TF-IDF) vectorizer, word2vec, GloVe, or bidirectional encoder representations from transformers (BERT) models);
generate semantic relevance scores associated with the respective entity names by using a second Al model to compare a semantic context of each entity name to the respective entity name, each semantic relevance score representing an extent to which the respective semantic context corresponds to the respective entity name ([0044] - The relevance for the candidate attribute data is predicted based on the classification of the candidate entities. In some embodiment, the CKE engine 130 predicts relevance for the candidate attribute data by performing an information similarity evaluation using a semantic similarity model. The semantic similarity model attempts to compare two texts and decide whether they are similar in meaning. may be based on, for example, Stanford natural language inference (SNLI), bidirectional encoder representations from transformers (BERT), a transformer model and using a similarity metric (e.g., cosine similarity));
and combine the quantitative relevance scores associated with the respective entity names and the semantic relevance scores associated with the respective entity names to provide the respective relevance scores that are to be assigned to the respective entity names ([0044] - the CKE engine 130 extracts most relevant attribute data for the candidate entities using at least one information extraction deep learning model, such as the machine QA deep leaning model. The machine QA deep leaning model can answer questions by extracting phrases from paragraphs, paraphrasing answers generatively, or choosing one option out from a list of given options. The CKE engine 130 summarized the most relevant attribute data for each of the candidate entities in the summarization map using an information semantic clustering model. In some embodiments, the most relevant attribute data for each of the candidate entities are highlighted in the summarization map. The summarization map is provided in a format that is friendly to review).
Regarding claim 6, Sha discloses the system, wherein the computer-executable instructions are executable by the processor system to define the entity name representation of each entity having an entity name that is assigned a relevance score that is less than the relevance threshold by performing the following:
generate a composite dimension vector for the respective entity using a dimension analyzer based at least on a weighted average of quantitative dimensions of the respective entity ([0071] - the system converts that candidate attribute data extracted from the content pages to vectors using a BERT (Bidirectional Encoder Representations from Transformers) variant model, and performs a K-mean clustering process for the vectors);
and cause a long short-term memory (LSTM) network to generate the respective entity name representation by providing the composite dimension vector for the respective entity as an input to the LSTM network ([0037] - the CAU engine 110 identifies address information by using an information extraction deep learning model. Such an information extraction deep learning model can be based on, for example, NER deep learning model, machine QA deep learning model, recurrent neural networks (RNNs) models, hidden markov models (HMM) and conditional random fields (CRF) models, universal language model fine-tuning (ULMfit), embeddings from language models (ELMo) and texts vectorization models, such as term frequency-inverse document frequency (TF-IDF) vectorizer, word2vec, GloVe, or bidirectional encoder representations from transformers (BERT) models).
Regarding claim 7, Sha discloses the system, wherein the computer-executable instructions are executable by the processor system further to:
generate a mapping that cross-references each entity name that is assigned a relevance score that is less than the relevance threshold to the replacement name that replaces the entity name ([0067] - cross-entity attribute data are considered in the individual entity ER map 600. The cross-entity attribute data are attribute data that are cross-linked to other entities in the content page, and the other entities may not be directly related to each other. Similar to column 620 in FIG. 6, cross-entity attribute data are considered in the business ER map 700 as shown column 720 in FIG. 7. For example, individual A's wife is named Maria Smith. The content page (or another content page) may also include descriptions that individual A has a transaction with company “Happy-ABC” as part of the alert. The content page describes both Maria Smith and Happy-ABC, then an ER score of 9 may be derived for the Happy-ABC entity resolution, even though Maria Smith and Happy-ABC are not directly related to each other. The ER score of 9 is derived based on the cross-entity link between the two entities disclosed in a same content page(s) and/or other disclosures linking the entities).
Regarding claim 8, Sha discloses the system, wherein the computer-executable instructions are executable by the processor system further to:
replace each replacement name that is included in the system-specific segment definition with the corresponding entity name that the replacement name replaced by using the mapping to cross-reference the replacement name to the corresponding entity name ([0067] - cross-entity attribute data are considered in the individual entity ER map 600. The cross-entity attribute data are attribute data that are cross-linked to other entities in the content page, and the other entities may not be directly related to each other. Similar to column 620 in FIG. 6, cross-entity attribute data are considered in the business ER map 700 as shown column 720 in FIG. 7. For example, individual A's wife is named Maria Smith. The content page (or another content page) may also include descriptions that individual A has a transaction with company “Happy-ABC” as part of the alert. The content page describes both Maria Smith and Happy-ABC, then an ER score of 9 may be derived for the Happy-ABC entity resolution, even though Maria Smith and Happy-ABC are not directly related to each other. The ER score of 9 is derived based on the cross-entity link between the two entities disclosed in a same content page(s) and/or other disclosures linking the entities);
and based at least on each replacement name that is included in the system-specific segment definition being replaced with the corresponding entity name, execute the system-specific segment definition against the database ([0071] - the system converts that candidate attribute data extracted from the content pages to vectors using a BERT (Bidirectional Encoder Representations from Transformers) variant model, and performs a K-mean clustering process for the vectors In some embodiments, during the extraction, the system also records source information of the candidate attribute data. The source information identifies the sources of extracted candidate attributed data in the plurality of content pages. As shown in FIG. 8, in row 830, the source information (e.g., source_link) as well as part of the content pages are shown in summarization map 800).
Regarding claim 9, Sha discloses the system, wherein the computer-executable instructions are executable by the processor system further to:
receive, from the AI model, a second response to the second AI prompt, the second response including the system-specific segment definition ([0071] - the system converts that candidate attribute data extracted from the content pages to vectors using a BERT (Bidirectional Encoder Representations from Transformers) variant model, and performs a K-mean clustering process for the vectors In some embodiments, during the extraction, the system also records source information of the candidate attribute data. The source information identifies the sources of extracted candidate attributed data in the plurality of content pages. As shown in FIG. 8, in row 830, the source information (e.g., source_link) as well as part of the content pages are shown in summarization map 800);
and perform an action using the system-specific segment definition that is received from the AI model ([0071] - the system converts that candidate attribute data extracted from the content pages to vectors using a BERT (Bidirectional Encoder Representations from Transformers) variant model, and performs a K-mean clustering process for the vectors In some embodiments, during the extraction, the system also records source information of the candidate attribute data. The source information identifies the sources of extracted candidate attributed data in the plurality of content pages. As shown in FIG. 8, in row 830, the source information (e.g., source_link) as well as part of the content pages are shown in summarization map 800).
Regarding claim 10, Sha discloses the system, wherein the computer-executable instructions are executable by the processor system to
cause the database to provide the data that satisfies the criterion by executing the system- specific segment definition against the database ([0071] - the system converts that candidate attribute data extracted from the content pages to vectors using a BERT (Bidirectional Encoder Representations from Transformers) variant model, and performs a K-mean clustering process for the vectors In some embodiments, during the extraction, the system also records source information of the candidate attribute data. The source information identifies the sources of extracted candidate attributed data in the plurality of content pages. As shown in FIG. 8, in row 830, the source information (e.g., source_link) as well as part of the content pages are shown in summarization map 800).
Regarding claim 11, Sha discloses the system, wherein the computer-executable instructions are executable by the processor system to:
provide an update inquiry to an entity that initiated the natural language prompt, the update inquiry requesting whether a change is to be made to the system-specific segment definition ([0055] - the user interface 400 facilitates analyzing similarities of the candidate attribute data with respect to the confirmed attribute data based on the latitude-longitude coordinate data. In the user interface 400, the system can receive inputs such as the number of entries and/or a search inquiry via the drop down menu (e.g., “Show 10 entries”) and the search box. With the received inputs, in block 410, user interface 400 displays the address information in the confirmed attribute data (e.g., “123 Main Street, San Francisco, CA”). In block 420, user interface 400 displays the address information of the candidate attribute data (e.g., “San Rafael, California”). On its face, the address information in the confirmed attribute data and the address information in the candidate attribute data are different from each other. The system disclosed herein can perform further analysis to determine the similarities of the candidate attribute data with respect to the confirmed attribute data. [0071] - the system converts that candidate attribute data extracted from the content pages to vectors using a BERT (Bidirectional Encoder Representations from Transformers) variant model, and performs a K-mean clustering process for the vectors In some embodiments, during the extraction, the system also records source information of the candidate attribute data. The source information identifies the sources of extracted candidate attributed data in the plurality of content pages. As shown in FIG. 8, in row 830, the source information (e.g., source_link) as well as part of the content pages are shown in summarization map 800)).
Regarding claim 12, Sha discloses a method implemented by a computing system, the method comprising:
receiving a natural language prompt, which requests data that satisfies a search criterion from a database that stores entities ([0034] - natural language processing (NLP)… entity extraction [0046] - the system 100 further generates a confirmed database configured to store confirmed attribute data and a candidate database configured to store candidate attribute data);
assigning relevance scores to entity names of the entities, each relevance score indicating an extent to which a respective entity name corresponds to content of a respective entity ([0051] - the system calculates an ER score based on the ER map. In some embodiments, only candidate attribute data having similarities counts in the ER score. The system classifies the one or more candidate entities to be at least confirmed, relevant, or irrelevant based on the ER score);
defining entity name representations to represent the entities by performing the following:
for each entity having an entity name that is assigned a relevance score that is less than a relevance threshold, defining the entity name representation of the respective entity to be a respective replacement name, which is based at least on the content of the respective entity, rather than the entity name of the respective entity ([0051] - if an ER score of a candidate entity is lower than the threshold value, the system determines the candidate entity is not yet identified as the target entity (234). As shown in FIG. 2, content pages comprising the candidate entity are kept in the folder and will be processed in the next iteration);
and for each entity having an entity name that is assigned a relevance score that is greater than or equal to the relevance threshold, defining the entity name representation of the respective entity to be the respective entity name ([0051] - the system determines whether the ER score is greater than or equal to a threshold value. Then the system classifies the one or more candidate entities to be at least confirmed, relevant, or irrelevant in response to the ER score being greater than or equal to the threshold value);
generating a first AI prompt that requests an indication of which of the entity name representations is relevant to the natural language prompt ([0071] - For candidate entities classified to be relevant entities, the system extracts corresponding candidate attribute data related to the relevant candidate entities as relevant knowledge);
causing an AI model to determine a first subset of the entity name representations that is relevant to the natural language prompt and a second subset of the entity name representations that is not relevant to the natural language prompt by providing the first AI prompt together with first contextual information as first inputs to the AI model, the first contextual information including the natural language prompt and the entity name representations, wherein the natural language prompt and the entity name representations include context regarding the first AI prompt ([0059] - the system can identify at least one of names comprising nick names, phonetic variations, typographical mistakes, contextual differences, reordered terms, prefixes and suffixes, abbreviations and initials, or truncated letters and missing as matched names. [0081] - classifying the one or more candidate entities to be at least confirmed, relevant, or irrelevant entities based on the similarities of the candidate attribute data (step 1020), classifying the corresponding candidate attribute data related to the candidate entities to be confirmed, relevant, or irrelevant attribute data (step 1030), and discarding content pages associated with candidate entities classified as irrelevant (step 1040));
generating a second AI prompt that requests conversion of the natural language prompt to a system-specific segment definition that conforms to a system-specific segment definition format that is specific to a customer data platform system ([0037] - the CAU engine 110 is a computer-implemented engine configured to obtain attribute data by digesting customer information in an indication or content pages. A customer can be an individual entity or a business entity. The customer information comprises attribute data of one or more entities);
and based at least on receipt of a response to the first AI prompt from the AI model that indicates the first and second subsets of the entity name representations, causing the AI model to convert the natural language prompt to the system-specific segment definition by providing the second AI prompt together with second contextual information as second inputs to the AI model, the second contextual information including the natural language prompt and information regarding the system-specific segment definition format and the first subset of the entity name representations and not including the second subset of the entity name representations, wherein the natural language prompt, the information regarding the system-specific segment definition format, and the first subset of the entity name representations include context regarding the second AI prompt ([0059] - the system can identify at least one of names comprising nick names, phonetic variations, typographical mistakes, contextual differences, reordered terms, prefixes and suffixes, abbreviations and initials, or truncated letters and missing as matched names. [0071] - the system converts that candidate attribute data extracted from the content pages to vectors using a BERT (Bidirectional Encoder Representations from Transformers) variant model, and performs a K-mean clustering process for the vectors In some embodiments, during the extraction, the system also records source information of the candidate attribute data. The source information identifies the sources of extracted candidate attributed data in the plurality of content pages. As shown in FIG. 8, in row 830, the source information (e.g., source_link) as well as part of the content pages are shown in summarization map 800).
Dependent claims 13-19 are analogous in scope to claims 4-10, and are rejected according to the same reasoning.
Regarding claim 20, Sha discloses a computer program product comprising a computer-readable storage medium having instructions recorded thereon for enabling a processor-based system to perform operations, the operations comprising:
receiving a natural language prompt, which requests data that satisfies a search criterion from a database that stores entities ([0034] - natural language processing (NLP)… entity extraction [0046] - the system 100 further generates a confirmed database configured to store confirmed attribute data and a candidate database configured to store candidate attribute data);
assigning relevance scores to entity names of the entities, each relevance score indicating an extent to which a respective entity name corresponds to content of a respective entity ([0051] - the system calculates an ER score based on the ER map. In some embodiments, only candidate attribute data having similarities counts in the ER score. The system classifies the one or more candidate entities to be at least confirmed, relevant, or irrelevant based on the ER score);
defining entity name representations to represent the entities by performing the following:
for each entity having an entity name that is assigned a relevance score that is less than a relevance threshold, defining the entity name representation of the respective entity to be a respective replacement name, which is based at least on the content of the respective entity, rather than the entity name of the respective entity ([0051] - if an ER score of a candidate entity is lower than the threshold value, the system determines the candidate entity is not yet identified as the target entity (234). As shown in FIG. 2, content pages comprising the candidate entity are kept in the folder and will be processed in the next iteration);
and for each entity having an entity name that is assigned a relevance score that is greater than or equal to the relevance threshold, defining the entity name representation of the respective entity to be the respective entity name ([0051] - the system determines whether the ER score is greater than or equal to a threshold value. Then the system classifies the one or more candidate entities to be at least confirmed, relevant, or irrelevant in response to the ER score being greater than or equal to the threshold value);
generating a first AI prompt that requests an indication of which of the entity name representations is relevant to the natural language prompt ([0071] - For candidate entities classified to be relevant entities, the system extracts corresponding candidate attribute data related to the relevant candidate entities as relevant knowledge);
causing an AI model to determine a first subset of the entity name representations that is relevant to the natural language prompt and a second subset of the entity name representations that is not relevant to the natural language prompt by providing the first AI prompt together with first contextual information as first inputs to the AI model, the first contextual information including the natural language prompt and the entity name representations, wherein the natural language prompt and the entity name representations include context regarding the first AI prompt ([0059] - the system can identify at least one of names comprising nick names, phonetic variations, typographical mistakes, contextual differences, reordered terms, prefixes and suffixes, abbreviations and initials, or truncated letters and missing as matched names. [0081] - classifying the one or more candidate entities to be at least confirmed, relevant, or irrelevant entities based on the similarities of the candidate attribute data (step 1020), classifying the corresponding candidate attribute data related to the candidate entities to be confirmed, relevant, or irrelevant attribute data (step 1030), and discarding content pages associated with candidate entities classified as irrelevant (step 1040));
generating a second AI prompt that requests conversion of the natural language prompt to a system-specific segment definition that conforms to a system-specific segment definition format that is specific to a customer data platform system ([0037] - the CAU engine 110 is a computer-implemented engine configured to obtain attribute data by digesting customer information in an indication or content pages. A customer can be an individual entity or a business entity. The customer information comprises attribute data of one or more entities);
and based at least on receipt of a response to the first AI prompt from the AI model that indicates the first and second subsets of the entity name representations, causing the AI model to convert the natural language prompt to the system-specific segment definition by providing the second AI prompt together with second contextual information as second inputs to the AI model, the second contextual information including the natural language prompt and information regarding the system-specific segment definition format and the first subset of the entity name representations and not including the second subset of the entity name representations, wherein the natural language prompt, the information regarding the system-specific segment definition format, and the first subset of the entity name representations include context regarding the second AI prompt ([0059] - the system can identify at least one of names comprising nick names, phonetic variations, typographical mistakes, contextual differences, reordered terms, prefixes and suffixes, abbreviations and initials, or truncated letters and missing as matched names. [0071] - the system converts that candidate attribute data extracted from the content pages to vectors using a BERT (Bidirectional Encoder Representations from Transformers) variant model, and performs a K-mean clustering process for the vectors In some embodiments, during the extraction, the system also records source information of the candidate attribute data. The source information identifies the sources of extracted candidate attributed data in the plurality of content pages. As shown in FIG. 8, in row 830, the source information (e.g., source_link) as well as part of the content pages are shown in summarization map 800).
Conclusion
5. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Farenden (U.S. Publication No. 20160283525) discloses schema generation using natural language processing. Sun (U.S. Patent No. 12488184) discloses alternative input representations.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ETHAN DANIEL KIM whose telephone number is (571) 272-1405. The examiner can normally be reached on Monday - Friday 9:00 - 5:00.
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, Richemond Dorvil can be reached on (571) 272-7602. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see https://ppair-my.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ETHAN DANIEL KIM/
Examiner, Art Unit 2658
/RICHEMOND DORVIL/Supervisory Patent Examiner, Art Unit 2658