# US 11,443,119 B2 · Adapting dialog models by relevance value for concepts to complete a task > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,119 B2 - Document ID: US11443119B2 - Status: Granted - Kind: B2 - Application number: 16/860,819 - Filed: 2020-04-28 - Published: 2021-10-28 - Granted: 2022-09-13 - Earliest claimed: 2020-04-28 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Song Feng; Qingzi Liao; Luis A. Lastras-Montano; Robert G. Farrell; Ana Smith - Web page: https://patentgrep.com/patent/US11443119B2 ## CPC - G06F 40/30: Semantic analysis - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06N 5/02: Knowledge representation; Symbolic representation - G06N 5/04: Inference or reasoning models - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A computer-implemented method identifies one or more concepts from a document, wherein the document comprises information on completing a task. The method computes a relevance value of an utterance with respect to completing the task using the one or more identified concepts. The method removes the utterance from a dialog model to be used for completing the task when the relevance value of the utterance is below a given threshold value. ## Claims ### Claim 1 An apparatus comprising: at least one processor; at least one memory including computer program code; the at least one memory and the computer program code being configured to, with the at least one processor, cause the apparatus at least to: identify one or more relevant concepts from a document, the one or more relevant concepts comprising information relevant to completing a task; obtain conversation turns in association with a dialog to be included in a dialog model to be used for completing the task; compute a relevance value of one or more utterances of the conversation turns with respect to completing the task using the one or more relevant concepts; assign summary labels to the conversation turns in the dialog based on the relevance values computed for the one or more utterances of the conversation turns, the summary labels identifying conversation management turns and information management turns, the conversation management turns comprising one or more utterances that are considered non-essential with respect to completing the task, the information management turns comprising one or more utterances that are considered essential with respect to completing the task; and remove one or more utterances associated with a given conversation management turn from the dialog model when the relevance value of the one or more utterances is determined to be below a given threshold value. ### Claim 2 (depends on 1) The apparatus of claim 1, wherein identifying the one or more relevant concepts from the document comprises a graph-based decomposition process. ### Claim 3 (depends on 2) The apparatus of claim 2, wherein computing the relevance value comprises determining a measure of centrality associated with a text graph. ### Claim 4 (depends on 1) The apparatus of claim 1, wherein identifying the one or more relevant concepts from the document further comprises computation of one or more of a term frequency, an inverse document frequency, and a term frequency-inverse document frequency. ### Claim 5 (depends on 1) The apparatus of claim 1, wherein the one or more relevant concepts comprise one or more of linguistic constituents and tokens. ### Claim 6 (depends on 1) The apparatus of claim 1, wherein computing the relevance value further comprises computing one or more of a maximum marginal relevance value, an integer linear programming value, and a sequential minimal optimization value. ### Claim 7 (depends on 1) The apparatus of claim 1 wherein assigning summary labels to the conversation turns includes utilizing Boolean type labels to identify the conversation management turns and the information management turns. ### Claim 8 A computer-implemented method comprising: identifying one or more relevant concepts from a document, the one or more relevant concepts comprising information relevant to completing a task; obtaining conversation turns in association with a dialog to be included in a dialog model to be used for completing the task; computing a relevance value of one or more utterances of the conversation turns with respect to completing the task using the one or more relevant concepts; assigning summary labels to the conversation turns in the dialog based on the relevance values computed for the one or more utterances of the conversation turns, the summary labels identifying conversation management turns and information management turns, the conversation management turns comprising one or more utterances that are considered non-essential with respect to completing the task, the information management turns comprising one or more utterances that are considered essential with respect to completing the task; and removing one or more utterances associated with a given conversation management turn from the dialog model when the relevance value of the one or more utterances is determined to be below a given threshold value. ### Claim 9 (depends on 8) The method of claim 8, wherein identifying the one or more relevant concepts from the document further comprises a graph-based decomposition process. ### Claim 10 (depends on 9) The method of claim 9, wherein computing the relevance value comprises determining a measure of centrality associated with a text graph. ### Claim 11 (depends on 8) The method of claim 8, wherein identifying the one or more relevant concepts from the document further comprises computation of one or more of a term frequency, an inverse document frequency, and a term frequency-inverse document frequency. ### Claim 12 (depends on 8) The method of claim 8, wherein the one or more relevant concepts comprise one or more of linguistic constituents and tokens. ### Claim 13 (depends on 8) The method of claim 8, wherein computing the relevance value further comprises computing one or more of a maximum marginal relevance value, an integer linear programming value, and a sequential minimal optimization value. ### Claim 14 (depends on 8) The method of claim 8, wherein assigning summary labels to the conversation turns includes utilizing Boolean type labels to identify the conversation management turns and the information management turns. ### Claim 15 An article of manufacture comprising a non-transitory computer-readable storage medium having embodied therein executable program code that when executed by a processor causes the processor to perform steps of: identifying one or more relevant concepts from a document, the one or more relevant concepts comprising information relevant to completing a task; obtaining conversation turns in association with a dialog to be included in a dialog model to be used for completing the task; computing a relevance value of one or more utterances of the conversation turns with respect to completing the task using the one or more relevant concepts; assigning summary labels to the conversation turns in the dialog based on the relevance values computed for the one or more utterances of the conversation turns, the summary labels identifying conversation management turns and information management turns, the conversation management turns comprising one or more utterances that are considered non-essential with respect to completing the task, the information management turns comprising one or more utterances that are considered essential with respect to completing the task; and removing one or more utterances associated with a given conversation management turn from the dialog model when the relevance value of the one or more utterances is determined to be below a given threshold value. ### Claim 16 (depends on 15) The article of claim 15, wherein identifying the one or more relevant concepts from the document comprises a graph-based decomposition process. ### Claim 17 (depends on 16) The article of claim 16, wherein computing the relevance value comprises determining a measure of centrality associated with a text graph. ### Claim 18 (depends on 15) The article of claim 15, wherein identifying the one or more relevant concepts from the document further comprises computation of one or more of a term frequency, an inverse document frequency, and a term frequency-inverse document frequency. ### Claim 19 (depends on 15) The article of claim 15, wherein the one or more relevant concepts comprise one or more of linguistic constituents and tokens. ### Claim 20 (depends on 15) The article of claim 15, wherein computing the relevance value further comprises computing one or more of a maximum marginal relevance value, an integer linear programming value, and a sequential minimal optimization value.