# US 12,762,883 B2 · Selective input data generation for machine learning models > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,762,883 B2 - Document ID: US12762883B2 - Status: Granted - Kind: B2 - Application number: 18/768,128 - Filed: 2024-07-10 - Published: 2026-01-15 - Granted: 2026-10-13 - Earliest claimed: 2024-07-10 - Assignees: Optum, Inc. - Applicants: Optum, Inc. - Inventors: Joel David Stremmel; Sanjit Singh Batra; Jun Han - Web page: https://patentgrep.com/patent/US12762883B2 ## CPC - G06V 30/416: Extracting the logical structure, e.g. chapters, sections or page numbers; Identifying elements of the document, e.g. authors - G06V 30/19093: {Proximity measures, i.e. similarity or distance measures} - G06V 30/19127: {Extracting features by transforming the feature space, e.g. multidimensional scaling; Mappings, e.g. subspace methods} - G06V 30/1918: {Fusion techniques, i.e. combining data from various sources, e.g. sensor fusion} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Various embodiments of the present disclosure provide a text interpretation technique. The text interpretation technique includes generating a plurality of text segment embeddings from a plurality of input text documents and identifying prompt embeddings associated with a predictive task. The technique includes generating task-specific similarity scores for the plurality of text segments based on a comparison between the plurality of text segment embeddings and the prompt embeddings, The technique includes identifying a set of task-specific text segments from the plurality of text segments based on the plurality of task-specific similarity scores and training a target machine learning model based on the set of task-specific text segments. ## Claims ### Claim 1 A computer-implemented method comprising: generating, by one or more processors and using a domain-specific language model, a plurality of text segment embeddings for a plurality of text segments of a plurality of input text documents associated with a predictive task; identifying, by the one or more processors, one or more prompt embeddings associated with the predictive task; generating, by the one or more processors, a plurality of task-specific similarity scores for the plurality of text segments based on a comparison between the plurality of text segment embeddings and the one or more prompt embeddings; identifying, by the one or more processors, a set of task-specific text segments from the plurality of text segments based on the plurality of task-specific similarity scores; and training, by the one or more processors, a target machine learning model based on the set of task-specific text segments. ### Claim 2 (depends on 1) The computer-implemented method of claim 1, further comprising: identifying an input document threshold based on a distribution of documents for a plurality of entities associated with an enterprise; and receiving the plurality of input text documents from an enterprise data source based on the input document threshold. ### Claim 3 (depends on 1) The computer-implemented method of claim 1, wherein the plurality of input text documents is respectively associated with a plurality of recordation times and generating the plurality of text segment embeddings comprises: generating an input document sequence by sequentially concatenating the plurality of input text documents based on the plurality of recordation times; and inputting the input document sequence to the domain-specific language model to generate the plurality of text segment embeddings. ### Claim 4 (depends on 1) The computer-implemented method of claim 1, wherein the one or more prompt embeddings are identified from a plurality of prompt embeddings respectively associated with a plurality of predictive tasks. ### Claim 5 (depends on 1) The computer-implemented method of claim 1, wherein the one or more prompt embeddings are generated, using the domain-specific language model, based on one or more query text segments from a populated query template. ### Claim 6 (depends on 5) The computer-implemented method of claim 5, wherein the populated query template comprises a text template with one or more modifiable template sections and one or more population instructions configured to modify the one or more modifiable template sections based on the predictive task. ### Claim 7 (depends on 6) The computer-implemented method of claim 6, wherein a query text segment of the one or more query text segments comprises a portion of the text template with an updated modifiable template section. ### Claim 8 (depends on 6) The computer-implemented method of claim 6, wherein the one or more population instructions restrict the one or more modifiable template sections to complementary data relative to a plurality of structured data entries associated with the predictive task. ### Claim 9 (depends on 6) The computer-implemented method of claim 6, wherein the one or more population instructions comprise one or more automated queries to one or more domain-specific data sources. ### Claim 10 (depends on 1) The computer-implemented method of claim 1, wherein generating the plurality of task-specific similarity scores for the plurality of text segments comprises: generating a first similarity score for a text segment based on a comparison between a text segment embedding corresponding to the text segment and a first prompt embedding of the one or more prompt embeddings; generating a second similarity score for the text segment based on a comparison between the text segment embedding and a second prompt embedding of the one or more prompt embeddings; generating a first ranked list based on a comparison between the first similarity score for the text segment and a plurality of first similarity scores for the plurality of text segments; and generating a second ranked list based on a comparison between the second similarity score for the text segment and a plurality of second similarity scores for the plurality of text segments. ### Claim 11 (depends on 10) The computer-implemented method of claim 10, wherein the first prompt embedding is associated with a first significance weight and the second prompt embedding is associated with a second significance weight and identifying the set of task-specific text segments comprises: identifying a first subset of the set of task-specific text segments from the first ranked list based on the first significance weight and a threshold evidence limit; identifying a second subset of the set of task-specific text segments from the second ranked list based on the second significance weight and the threshold evidence limit; and removing one or more duplicate task-specific text segments from the set of task-specific text segments. ### Claim 12 (depends on 1) The computer-implemented method of claim 1, wherein the set of task-specific text segments are associated with a training entity and training the target machine learning model comprises: receiving one or more structured data entries associated with the training entity; generating a multi-modal training entry by merging the one or more structured data entries with the set of task-specific text segments; inputting the multi-modal training entry to the target machine learning model to receive a training output; and updating one or more parameters of the target machine learning model based on a comparison between the training output and a training label. ### Claim 13 A system comprising memory and one or more processors communicatively coupled to the memory, the one or more processors configured to: generate, using a domain-specific language model, a plurality of text segment embeddings for a plurality of text segments of a plurality of input text documents associated with a predictive task; identify one or more prompt embeddings associated with the predictive task; generate a plurality of task-specific similarity scores for the plurality of text segments based on a comparison between the plurality of text segment embeddings and the one or more prompt embeddings; identify a set of task-specific text segments from the plurality of text segments based on the plurality of task-specific similarity scores; and train a target machine learning model based on the set of task-specific text segments. ### Claim 14 (depends on 13) The system of claim 13, wherein the one or more processors are further configured to: identify an input document threshold based on a distribution of documents for a plurality of entities associated with an enterprise; and receive the plurality of input text documents from an enterprise data source based on the input document threshold. ### Claim 15 (depends on 13) The system of claim 13, wherein the plurality of input text documents is respectively associated with a plurality of recordation times and generating the plurality of text segment embeddings comprises: generating an input document sequence by sequentially concatenating the plurality of input text documents based on the plurality of recordation times; and inputting the input document sequence to the domain-specific language model to generate the plurality of text segment embeddings. ### Claim 16 (depends on 13) The system of claim 13, wherein the one or more prompt embeddings are identified from a plurality of prompt embeddings respectively associated with a plurality of predictive tasks. ### Claim 17 (depends on 13) The system of claim 13, wherein the one or more prompt embeddings are generated, using the domain-specific language model, based on one or more query text segments from a populated query template. ### Claim 18 (depends on 17) The system of claim 17, wherein the populated query template comprises a text template with one or more modifiable template sections and one or more population instructions configured to modify the one or more modifiable template sections based on the predictive task. ### Claim 19 (depends on 18) The system of claim 18, wherein a query text segment of the one or more query text segments comprises a portion of the text template with an updated modifiable template section. ### Claim 20 One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to: generate, using a domain-specific language model, a plurality of text segment embeddings for a plurality of text segments of a plurality of input text documents associated with a predictive task; identify one or more prompt embeddings associated with the predictive task; generate a plurality of task-specific similarity scores for the plurality of text segments based on a comparison between the plurality of text segment embeddings and the one or more prompt embeddings; identify a set of task-specific text segments from the plurality of text segments based on the plurality of task-specific similarity scores; and train a target machine learning model based on the set of task-specific text segments.