# US 10,872,118 B2 · System and methods for automatic machine-learning based objective recommendation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,872,118 B2 - Document ID: US10872118B2 - Status: Granted - Kind: B2 - Application number: 15/852,865 - Filed: 2017-12-22 - Published: 2019-06-27 - Granted: 2020-12-22 - Earliest claimed: 2017-12-22 - Assignees: Pearson Education, Inc. - Applicants: Pearson Education, Inc. - Inventors: Johann A. Larusson; Timothy J. Stewart; David W. Strong; Kristina Evans; Quinn N. Lathrop; Luis M. Oros - Web page: https://patentgrep.com/patent/US10872118B2 ## CPC - G06F 16/90328: {using search space presentation or visualization, e.g. category or range presentation and selection} - G06F 16/24578: {using ranking} - G06F 16/248: Presentation of query results - 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 Systems and methods for automated objective identification are disclosed herein. The system can include a user device and a memory. The memory can include a filed database including field data associated with previously identified objectives. The memory can include a scoring database containing a machine-learning scoring algorithm. The system can include at least one server that can receive an identifier of a content portion, extract field information identifying at least one attribute of the identified content portion from the content portion, input extracted field information into the machine-learning scoring algorithm; receive identification of objectives forming a set of objectives from the machine-learning scoring algorithm; sort the objectives forming the set of objectives according to scores generated for each of the objectives in the set of objectives; and output the sorted objectives to the user device. ## Claims ### Claim 1 A system for automated objective identification, the system comprising: a user device comprising an input/output subsystem; a memory comprising: a field database comprising field data associated with previously identified objectives, Wherein each of the previously identified objectives is associated with field data identifying at least one attribute of content associated with the associated objective; and a scoring database comprising a machine-learning scoring algorithm trained for predicting related objectives based on identified attributes of inputted content; and at least one server configured to: receive an identifier of a content portion; extract field information identifying at least one attribute of the identified content portion from the content portion; input extracted field information into the machine-learning scoring algorithm; receive identification of objectives forming a set of objectives from the machine-learning scoring algorithm; generate a score for each of the objectives forming the set of objectives, wherein generating the score comprises: generating a raw score via the machine learning algorithm; and modifying the raw score, wherein the raw score is modified according to at least one feature of the objective associated with the raw score; sort the objectives forming the set of, objectives according to scores generated for each of the objectives in the set of objectives; and output the sorted objectives to the user device. ### Claim 2 (depends on 1) The system of claim 1, wherein the machine-learning scoring algorithm comprises a vector space model. ### Claim 3 (depends on 1) The system of claim 1, wherein the machine-learning scoring algorithm identifies the objectives forming the set of objectives according to a correspondence between a vector characterizing attributes of the content portion and attributes of the previously identified objectives. ### Claim 4 (depends on 3) The system of claim 3, wherein the at least one server is further configured to generate a score for each of the objectives forming the set of objectives. ### Claim 5 (depends on 4) The system of claim 4, Wherein generating the score comprises receiving a raw score from the machine-learning scoring algorithm, and modifying the raw score. ### Claim 6 (depends on 5) The system of claim 5, wherein modifying the raw score comprises: selecting one of the objectives forming the set objectives; identifying the raw score associated with the selected one of the objectives forming the set of objectives; identifying at least one, feature of the selected one of the objectives forming the set of objectives; and adjusting the raw score according to the at least one feature. ### Claim 7 (depends on 6) The system of claim 6, wherein identifying at least one feature of the selected one of the objectives forming the set of objectives comprises: identifying raw features of selected one of the objectives forming the set of objectives; and calculating features from the identified raw features. ### Claim 8 (depends on 7) The system of claim 7, wherein adjusting the raw score according to the at least one feature comprises adding a product of each of the calculated features and an associated parameter and a product of the raw score and an associated parameter. ### Claim 9 (depends on 8) The system of claim 8, wherein the features comprise at least one of: a ratio of a number of verbs to a number of words in the objective; and a frequency of content being associated with the objective. ### Claim 10 (depends on 9) The system of claim 9, wherein the at least one server is further configured to: receive identification of an authored objective from the user device; evaluate the authored objective; generate a score for the authored objective; and include the authored objective in the sorting of objectives forming the set of objectives according to scores. ### Claim 11 A method for automated objective identification, the method comprising: receiving an identifier of a content portion from a user device at least one server; extracting with the at least one server field information identifying at least one attribute of the identified content portion from the content portion; inputting extracted field information into a machine-learning scoring algorithm, wherein the machine-learning scoring algorithm is trained for predicting related objectives based on identified attributes of inputted content; receiving identification of objectives forming a set of objectives from the machine-learning scoring algorithm; generate a score for each of the objectives forming the set of objectives, wherein generating the score comprises: generating a raw score via the machine learning algorithm; and modifying the raw score, wherein the raw score is modified according to at least one feature of the objective associated with the raw score; sorting with the at least one server the objectives forming the set of objectives according to scores generated for each of the objectives in the set of objectives; and outputting the sorted objectives to the user device. ### Claim 12 (depends on 11) The method of claim 11, wherein the machine-learning scoring algorithm comprises a vector space model. ### Claim 13 (depends on 11) The method of claim 11, wherein the machine-learning scoring algorithm identifies the objectives forming the set of objectives according to a correspondence between a vector characterizing attributes of the content portion and attributes of the previously identified objectives. ### Claim 14 (depends on 13) The method of claim 13, further comprising generating a score for each of the objectives forming the set of objectives. ### Claim 15 (depends on 14) The method of claim 14, wherein generating the score comprises receiving a raw score from the machine-learning scoring algorithm, and modifying the raw score. ### Claim 16 (depends on 15) The method of claim 15, wherein modifying the raw score comprises: selecting one of the objectives forming the set objectives; identifying the raw score associated with the selected one of the objectives forming the set of objectives; identifying at least one feature of the selected one of the objectives forming the set of objectives; and adjusting the raw score according to the at least one feature. ### Claim 17 (depends on 16) The method of claim 16, wherein identifying at least one feature of the selected one of the objectives forming the set of objectives comprises: identifying raw features of selected one of the objectives forming the set of objectives; and calculating features from the identified raw features. ### Claim 18 (depends on 17) The method of claim 17, wherein adjusting the raw score according to the at least one feature comprises adding a product of each of the calculated features and an associated parameter and a product of the raw score and an associated parameter. ### Claim 19 (depends on 18) The method of claim 18, wherein the features comprise at least one of: a ratio of a number of verbs to a number of words in the objective; and a frequency of content being associated with the objective. ### Claim 20 (depends on 19) The method of claim 19, further comprising: receiving identification of an authored objective from the user device; evaluating the authored objective; generating a score for the authored objective; and including the authored objective in the sorting of objectives forming the set of objectives according to scores.