DETAILED ACTION
This communication is a first Office Action Non-Final rejection on the merits. Claims 1-19 as originally filed are currently pending and considered below.
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 .
Status of Claims
This Non-Final Office action is in response to the application filed on June 03, 2024. Claims 1-19 are pending.
Priority
Application 18732238 was filed on 06/03/2024 and claims the priority benefit of U.S. provisional patent application 63/470,330 filed 06/01/2023.
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 1-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claims 1‐9 are directed to a method (process), Claims 10-18 are directed to a system (machine), and Claim 19 is directed to a non-transitory computer readable storage medium storing (machine/apparatus). Thus, these claims fall within one of the four statutory categories of invention. (Step 1: YES).
For step 2A, the Examiner has identified independent method Claim 1 as the claim that represents the claimed invention for analysis and is similar to independent claim 10 and 19. Claim 1, as exemplary is recited below, isolating the abstract idea from the additional elements, wherein the abstract idea is set in bold:
A method for predicting student coursework status, the method comprising: storing coursework progression data in a course database in memory, wherein the coursework progression data includes metadata associated with coursework performance data of different students in one or more online courses: filtering the coursework progression data based on a received request to identify a filtered set of coursework progression data; predicting a status for one of the students associated with the received request based on use of a status predicting machine-learning model to analyze the filtered set of coursework progression data, wherein the status predicting machine-learning model has been trained in accordance with training data correlating a student status type to one or more coursework performance indicators; and generating a display that presents the predicted status for each of the students associated with the received request.
The above bolded limitations recite the abstract idea of assessing learning progress of different students within online courses and providing a student status engine to track the learning progress of each student. These limitations under its broadest reasonable interpretation, covers certain methods of organizing human activity (i.e., managing personal behavior or relationships or interactions between people) but for the recitation of generic computer components. That is, other than reciting a system implemented by a data processor (computer) the claimed invention amounts to the abstract idea stated above. For example, for the related computer components, this claim encompasses educational management activities that could conventionally be performed by teachers, academic advisors, or administrators manually as part of monitoring student coursework performance and progression. This evaluation process can be done manually using paper gradebooks, spreadsheets, or through direct observation of student’s performance over time. Additionally, predicting student coursework status is considered a method of organizing human activity related to educational performance management, because it involves analyzing and categorizing student administrative activity aimed at instructional decisions and student outcomes. If a claim limitation, under its broadest reasonable interpretation, covers management of interactions between parties, but for the recitation of generic computer components, then it falls within the “certain methods of organizing human activity” grouping of abstract ideas. The mere nominal recitation of a “a memory”, “online courses”, “a status predicting machine-learning model”, and “training data” do not take the claim out of the methods of organizing human interactions grouping. Thus, claims 1, 10, and 19 recites an abstract idea. (Step 2A- Prong 1: YES. The claims recite an abstract idea).
This judicial exception is not integrated into a practical application (2nd prong of eligibility test for step 2A). In particular, Claim 1 recites additional elements of “a memory”, “online courses”, “a status predicting machine-learning model”, and “training data”. Claim 10 recites the same additional elements of claim 1 with the additions of “one or more processors” and “a non-transitory computer readable storage medium”. Claim 19 10 recites the same additional elements of claim 1 with the additions of “non-transitory machine-readable medium”. These additional elements are all considered nothing more than generic computing devices to perform generic communicating functions such as storing data and instructions, transmitting and receiving data between computers. These elements are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of communicating data between users) such that they amount no more than mere instructions to apply the exception using a generic computer component in technological environment. See MPEP 2106.05(f) and (h). The claims recite the additional element “machine learning model” and “training data” which is considered nothing more than a general link machine learning because there is no recitation of specifics of how this additional element is being used. Accordingly, these additional elements (combination of computer and the use of machine learning) do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea and are recited at a high level of generality when considered both individually and as a whole. Thus, Claims 1, 10, and 19 are directed to an abstract idea without a practical application. (Step 2A-Prong 2: NO: the additional claimed elements are not integrated into a practical application).
For step 2B, the claim(s) do not include additional elements that are sufficient to amount to significantly more than the judicial exception because they do not amount to more than simply instructing one to practice the abstract idea by using generic computer components to carry out the steps that define the abstract idea, as discussed above. This does not render the claims as being eligible. See MPEP 2106.05(f). The additional elements of using computer, a processor, machine learning model, and a memory when considered both individually and as an ordered combination did not add significantly more to the abstract idea because they were simply applying the abstract idea using generic computer components. In addition, the claims recite the additional element “machine learning model” and “training data” which is considered nothing more than a general link machine learning because there is no recitation of specifics of how this additional element is being used. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (See MPEP 2106.05(f)). Accordingly, these additional elements, do not change the outcome of the analysis, and claims 1, 10, and 19 are not patent eligible. (Step 2B: NO. The claims do not provide significantly more).
Claims 2, 6, 9, 11, 15, and 18 recite limitations that further define the same abstract idea of independent claims to include wherein predicting the student status includes identifying a similarity between the filtered set coursework progression data and historical coursework progression data based on one or more rules weighted, a knowledge graph that includes graph-structured data correlating one or more of historical assignment scores, project scores, and exam grades to a student status level, labeling the filtered set of coursework progression data based on feedback regarding the predicted status. In addition, the claims recite the additional element “machine learning model” which is considered nothing more than a general link machine learning because there is no recitation of specifics of how this additional element is being used. See MPEP 2106.05(f) and (h) indicate that merely “generally linking” the abstract idea to a particular technological environment or field of use cannot provide a practical application or significantly more. Therefore, the claims are patent ineligible.
Claims 3 and 12 recite limitations that further define the same abstract idea of independent claims to include wherein the training data includes known historical coursework progression data inputs and known status outputs and identify probability-weighted associations between the inputs and the outputs. In addition, the claims recite the additional element “machine learning model” and “neural network”, which is considered nothing more than a general link machine learning because there is no recitation of specifics of how this additional element is being used. See MPEP 2106.05(f) and (h) indicate that merely “generally linking” the abstract idea to a particular technological environment or field of use cannot provide a practical application or significantly more. Therefore, the claims are patent ineligible.
Claims 4 and 13 recite limitations that further define the same abstract idea of independent claims to include generating one or more customized learning activities. In addition, the claims recite the additional element “machine learning model” and “student device”, which is considered nothing more than a general link machine learning because there is no recitation of specifics of how this additional element is being used. See MPEP 2106.05(f) and (h) indicate that merely “generally linking” the abstract idea to a particular technological environment or field of use cannot provide a practical application or significantly more. Therefore, the claims are patent ineligible.
Claims 5, 7-8, 14, and 16-17, recite limitations that further define the same abstract idea of independent claims to include wherein the learning activities are customized based on the predicted status of the student, adjusting one or more weights associated with one or more input features that include one or more of student attendance, quiz scores, assignment scores, course grades, and grade categories, and wherein the predicted status includes one or more likelihoods of failure of one of the online courses. The dependent claims do not include any new additional elements and therefore are considered patent ineligible for the reasons given above.
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, 4-11, and 13-19 are rejected under 35 U.S.C. 103 as being unpatentable over Lynch et al. (US 20240394817) in view of Issac et al. (US20240394817), further in view of Danson et al. (US 20150100303).
With regards to Claim 1, Lynch et al. teaches a method for predicting student coursework status, the method comprising: (See Abstract & FIG 1)
storing coursework progression data in a course database in memory (See [0101]-One or more servers may extract courseware-level data 600 derived from the tracked online activities of the plurality of students taking the plurality of online courses. The courseware-level data 600 is organized based on the structure of each course in a plurality of courses and stored in a database.), wherein the coursework progression data includes metadata associated with coursework performance data of different students in one or more online courses; (See [0101]- As examples, the courseware-level data 600 derived from the online activities of the plurality of students taking the plurality of online may comprise exam scores, homework scores and time spent on homework. Also See [0090]- The metadata, or categories of information that may be collected for the courseware-level data 600, student-level data 601, institution-level data 602 and/or teacher-level data 603, may be determined in any desired manner. Also See [0093]- Data may be continuously and automatically collected and analyzed to generate course-level data for one or more online digital courses and student-level data 601 for one or more students taking the courses.)
filtering the coursework progression data based on a received request to identify a filtered set of coursework progression data; (See [0120]- A student may also request to have a course analyzed to detect assignments or assessments in the course that may require additional work. (Step 402) The analysis may proceed based on the performances of all past students that have taken the course. In another embodiment, the student may wish to customize the analysis based on the student. In this case, the data for the student in the course may be weighted so that the analysis is more specific towards the student that is requesting the analysis. (Step 403) This may be desirable as the student requesting the analysis in the course may be very different, from the students who have taken the course in the past.)
Lynch et al. teaches a received request but does not teach predicting a status for one of the students associated with the received request based on use of a status predicting machine-learning model to analyze the filtered set of coursework progression data, wherein the status predicting machine-learning model has been trained in accordance with training data correlating a student status type to one or more coursework performance indicators. However, Issac et al. teaches:
predicting a status for one of the students associated with the received request based on use of a status predicting machine-learning model to analyze the filtered set of coursework progression data (See [0003]- monitoring, by the processor set, performance of the student in a course using a predictive machine learning model that predicts a score in the course based on the student data. Also See [0004]- in response to receiving opt-in consent from a student, obtain student data associated with the student; train a predictive machine learning model that predicts a score in a course; monitor performance of the student in the course using the student data with the predictive machine learning model.), wherein the status predicting machine-learning model has been trained in accordance with training data correlating a student status type to one or more coursework performance indicators; (See [0005]- train a predictive model that predicts a score in a course, wherein the predictive model comprises a decision tree model. Also See [0044]- the predictive model is trained using supervised learning using a training dataset that includes student data labeled with an actual course grade for plural students that previously enrolled in the course…the prediction module 235 is configured to use the predictive model to predict student performance in a course at different points in time and to detect a negative (e.g., downward) trend in the predicted performance for a student.)
Lynch et al. and Issac et al. are all considered to be analogous to the claimed invention because they are in the same field of predicting student coursework status. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Lynch et al. reference to further include predicting a status for one of the students associated with the received request based on use of a status predicting machine-learning model to analyze the filtered set of coursework progression data, wherein the status predicting machine-learning model has been trained in accordance with training data correlating a student status type to one or more coursework performance indicators as taught by Issac et al. This is desirable such that it offers better co-learning for K-12 students and higher education experienced candidates by blending prediction and allocation modeling approaches and making offerings compatible with the current sustainability development goals (SDGs). (See Issac, [0015]).
The Lynch-Issac combination teaches a predicted status but does not teach generating a display that presents the predicted status for each of the students associated with the received request. However, Danson et al. teaches:
generating a display that presents the predicted status for each of the students associated with the received request (See [0021]- more processing devices such as servers (not shown), each having one or more processors. The servers can be configured to send information (e.g., electronic files such as web pages) to be displayed on one or more devices (e.g., instructor device 102 and student device 104). Also See [0053]- After generation of the scores, the scores may be provided to the display module 140. The display module 140 is configured to generate one or more visual displays to convey the scores and/or student performance predictions to the instructor device 101 and/or student device 103. Also See [0071]- output a score, display the score, predict a likelihood of a student outcome, etc.).
Lynch et al., Issac et al., and Danson et al. are all considered to be analogous to the claimed invention because they are in the same field of predicting student coursework status. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Lynch-Issac combination to further include generating a display that presents the predicted status for each of the students associated with the received request as taught by Danson et al. This is desirable such that it advantageously analyzes online classroom communications or posts by students and makes predictions on the students' likely outcomes in the class. (See Danson, [0015]).
In regards to Claim 10 the Lynch-Issac-Danson combination teaches the claimed invention similar to Claim 1 with the addition of:
Lynch et al. teaches:
A system for predicting student coursework status, the system comprising: (See Abstract & FIG 1)
one or more processors that execute instructions stored by a non-transitory computer readable storage medium to:
(See Abstract & FIG 1, Also See [0039]- One or more processing units 204 may be implemented as one or more integrated circuits. Also See [0035]- one or more data stores 110 may reside on a non-transitory storage medium within the server 102. Also See [0049]- Computer system 200 may comprise one or more storage subsystems 210, comprising hardware and software components used for storing data and program instructions, such as system memory 218 and computer-readable storage media 216.)
In regards to Claim 19 the Lynch-Issac-Danson combination teaches the claimed invention similar to Claim 1 with the addition of:
Lynch et al. teaches:
A non-transitory computer-readable storage medium comprising instructions executable by a computing system to perform a method for predicting student coursework status, the method comprising: (See Abstract & FIG 1, Also See [0035]- one or more data stores 110 may reside on a non-transitory storage medium within the server 102. Also See [0049]- Computer system 200 may comprise one or more storage subsystems 210, comprising hardware and software components used for storing data and program instructions, such as system memory 218 and computer-readable storage media 216.)
In regards to Claim 2 and 11, the Lynch-Issac-Danson combination teaches the claimed invention as recited in the independent claim above.
Lynch et al. further teaches:
wherein predicting the student status includes identifying a similarity between the filtered set coursework progression data and historical coursework progression data (See [0106]- based on how students from the institution perform in the courses in the courseware-level data 600 compared to students from other institutions performing the same courses, may be stored in the database. In addition, or alternatively, another institutional ranking based on how students perform from the institution as compared to students from other institutions on any desired metric, such as standardized tests, national rankings, etc. may be collected and stored as institutional-level data. (Step 303)… the institutional-level data may comprise public/private data, admission requirement data and historical institution performance data. Also See [0131]- the data from the past is stored and used in future predictions as long as the data is relevant to predicting future course results (once data is no longer relevant to making future predictions or producing future posterior distributions 801, the data may be deleted).) based on one or more rules weighted (See [0006]- any part or parts of the data may be weighted to customize the analysis of the Bayesian multi-level model. In preferred embodiments, course data, in the courseware-level data, for the course being analyzed is heavily weighted. In some embodiments, the data for the student or students, in the student-level data, taking the course may be weighted.)
Lynch et al. does not teach by the status predicting machine-learning model. However, Issac et al. teaches:
by the status predicting machine-learning model (See [0044]- the predictive model is trained using supervised learning using a training dataset that includes student data labeled with an actual course grade for plural students that previously enrolled in the course. Also See [0005]- train a predictive model that predicts a score in a course, wherein the predictive model comprises a decision tree model. Also See [0044]- the predictive model is trained using supervised learning using a training dataset that includes student data labeled with an actual course grade for plural students that previously enrolled in the course…the prediction module 235 is configured to use the predictive model to predict student performance in a course at different points in time and to detect a negative (e.g., downward) trend in the predicted performance for a student.)).
Lynch et al., Issac et al., and Danson et al. are all considered to be analogous to the claimed invention because they are in the same field of predicting student coursework status. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Lynch-Issac-Danson combination to further include by the status predicting machine-learning model as taught by Issac et al. This is desirable such that it offers better co-learning for K-12 students and higher education experienced candidates by blending prediction and allocation modeling approaches and making offerings compatible with the current sustainability development goals (SDGs). (See Issac, [0015]).
In regards to Claim 4 and 13, the Lynch-Issac-Danson combination teaches the claimed invention as recited in the independent claim above.
Lynch et al. further teaches:
generating one or more customized learning activities accessible by a student device of the student (See [0072]- Referring to FIG. 8, the present invention is designed to wrap around a plurality of digital online courses to provide personalized and situationally informed instructional and behavioral guidance to faculty and students. Using a combination of courseware data, demographic and institutional information, and data from prior course and student performance, the invention may employ a Bayesian multi-level model 800 to determine estimates of course content challenge, activity study time requirements, and learning outcome difficulty levels. Furthermore, the invention may utilize these estimates to target intervention recommendations, suggest optimal opportunities for encouragement. Also See [0088]-Course information, possibly in the form of recommended remediations 803, may be provided directly to students (particularly around content difficulty, activity time estimates, and learning outcome importance) and will help them better self-regulate and allocate their study efforts. Tips and reminders may be generated and provided to students that will also encourage better learning behaviors and the adoption of effective learning strategies among students.).
Lynch et al. does not teach adapting the status predicting machine-learning model for the student. However, Issac et al. teaches:
adapting the status predicting machine-learning model for the student; (See [0004]- in response to receiving opt-in consent from a student, obtain student data associated with the student; train a predictive machine learning model that predicts a score in a course; monitor performance of the student in the course using the student data with the predictive machine learning model. Also See [0044]- the predictive model is trained to output a predicted course grade for a particular student in a particular course based on student data for the particular student.)
Lynch et al., Issac et al., and Danson et al. are all considered to be analogous to the claimed invention because they are in the same field of predicting student coursework status. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Lynch-Issac-Danson combination to further include adapting the status predicting machine-learning model for the student as taught by Issac et al. This is desirable such that it provide individualized recommendations and intervention steps based on student performance predictions. (See Issac, [0017]).
In regards to Claim 5 and 14, the Lynch-Issac-Danson combination teaches the claimed invention as recited in the independent claim above.
Lynch et al. further teaches:
wherein the learning activities are customized based on the predicted status of the student (See [0070]-What is needed is data/information from past courses that effectively surfaces the types of information outlined above, which could be used to support these important activities. Furthermore, delivering this information in a way that is personalized to a particular teaching context and is continually refined as more data about student performance is collected, would make these insights, and the recommendations associated with them, even more relevant, trustworthy, and impactful for instructors and learners. Also See [0088]-Course information, possibly in the form of recommended remediations 803, may be provided directly to students (particularly around content difficulty, activity time estimates, and learning outcome importance) and will help them better self-regulate and allocate their study efforts. Tips and reminders may be generated and provided to students that will also encourage better learning behaviors and the adoption of effective learning strategies among students.).
In regards to Claim 6 and 15, the Lynch-Issac-Danson combination teaches the claimed invention as recited in the independent claim above.
Lynch et al. further teaches:
uses a knowledge graph that includes graph-structured data correlating one or more of historical assignment scores, project scores, and exam grades to a student status level (See [0017]- FIG. 9 illustrates a hierarchical graph illustrating a possible arrangement of the different levels that may be used with the present invention. Also See [0022]-FIG. 14 illustrates a graph showing a predicted of which course objectives are on average the most difficult for students based on a plurality of posterior distributions from a Bayesian multi-level model. Also See [0136]- FIG. 14 illustrates a graph showing a prediction 802 of which course objectives are on average the most difficult for students based on a plurality of posterior distributions 801 from a Bayesian multi-level model 800. As indicated by the graph, the plurality of posterior distributions 801 predicts (as the numbers are higher for those course objectives) four different course objectives that are particularly difficult. Specifically, the plurality of posterior distributions 801 used to generate FIG. 14 predicts that course objectives 1400 are going to be the most difficult based on the past experiences of other students taking the course.).
Lynch et al. does not teach wherein the status predicting machine-learning model. However, Issac et al. teaches:
wherein the status predicting machine-learning model ((See [0003]- monitoring, by the processor set, performance of the student in a course using a predictive machine learning model that predicts a score in the course based on the student data. Also See [0004]- in response to receiving opt-in consent from a student, obtain student data associated with the student; train a predictive machine learning model that predicts a score in a course; monitor performance of the student in the course using the student data with the predictive machine learning model.).
Lynch et al., Issac et al., and Danson et al. are all considered to be analogous to the claimed invention because they are in the same field of predicting student coursework status. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Lynch-Issac-Danson combination to further include by the status predicting machine-learning model as taught by Issac et al. This is desirable such that it offers better co-learning for K-12 students and higher education experienced candidates by blending prediction and allocation modeling approaches and making offerings compatible with the current sustainability development goals (SDGs). (See Issac, [0015]).
In regards to Claim 7 and 16, the Lynch-Issac-Danson combination teaches the claimed invention as recited in the independent claim above.
Lynch et al. further teaches:
further comprising adjusting one or more weights associated with one or more input features that include one or more of student attendance, quiz scores, assignment scores, course grades, and grade categories (See [0006]- any part or parts of the data may be weighted to customize the analysis of the Bayesian multi-level model. In preferred embodiments, course data, in the courseware-level data, for the course being analyzed is heavily weighted. In some embodiments, the data for the student or students, in the student-level data, taking the course may be weighted. Also See [0118]-In this case, the data for the students in the course may be weighted so that the analysis is more specific towards the students that are actually in the course. Also See [0101]- As examples, the courseware-level data 600 derived from the online activities of the plurality of students taking the plurality of online may comprise exam scores, homework scores and time spent on homework.).
In regards to Claim 8 and 17, the Lynch-Issac-Danson combination teaches the claimed invention as recited in the independent claim above.
Lynch et al. does not teach wherein the predicted status includes one or more likelihoods of failure of one of the online courses. However, Danson et al. further teaches:
wherein the predicted status includes one or more likelihoods of failure of one of the online courses (See [0015]- analyzes online classroom communications or posts by students and makes predictions on the students' likely outcomes in the class. Also See [0047]-The performance prediction module 130 is adapted to use the score(s) for the different student metrics to predict the likelihood of a student outcome using a predictive model. The predictive model predicts the likelihood of a student achieving certain goals, such as failing or passing a course, or staying in or dropping out of a course. The predictive model is built using sample sets of previous scores of previous students in previous classes. Also See [0069]- At step 206, the performance prediction module 130 takes the scores and inputs them into a predictive model. At step 208, the predictive model outputs the likelihood of a student outcome based on the scores. For example, the predictive model indicates the probability that a student will pass or fail a course.).
Lynch et al., Issac et al., and Danson et al. are all considered to be analogous to the claimed invention because they are in the same field of predicting student coursework status. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Lynch-Issac-Danson combination to further wherein the predicted status includes one or more likelihoods of failure of one of the online courses as taught by Danson et al. This is desirable such that it advantageously analyzes online classroom communications or posts by students and makes predictions on the students' likely outcomes in the class. (See Danson, [0015]).
Claims 3 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Lynch et al. (US 20240394817) in view of Issac et al. (US20240394817), in view of Danson et al. (US 20150100303) , further in view of Chang et al. (US 20190102678).
In regards to Claim 3 and 12 the Lynch-Issac-Danson combination teaches the claimed invention as recited in the independent claim above.
Lynch et al. further teaches:
coursework progression data (See [0101]- As examples, the courseware-level data 600 derived from the online activities of the plurality of students taking the plurality of online may comprise exam scores, homework scores and time spent on homework.)
Lynch et al. does not teach wherein the training data includes known historical [coursework progression] data inputs and known status outputs, and further comprising generating the status predicting machine-learning model by. However, Issac et al. teaches:
wherein the training data includes known historical [coursework progression] data inputs and known status outputs, and further comprising generating the status predicting machine-learning model by (See [0117]- At step 710, the a performance tracking app of the system permits the user to track their performance. Step 710 may comprise the prediction module 235 predicting course scores for the student using the predictive model for each course and the student data… At step 750, the system collects data and makes a training dataset based on past performance of each student. At step 755, the system saves the collected data in a database.).
Lynch et al., Issac et al., and Danson et al. are all considered to be analogous to the claimed invention because they are in the same field of predicting student coursework status. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Lynch-Issac-Danson combination to further include wherein the training data includes known historical [coursework progression] data inputs and known status outputs, and further comprising generating the status predicting machine-learning model by as taught by Issac et al. This is desirable such that it offers better co-learning for K-12 students and higher education experienced candidates by blending prediction and allocation modeling approaches and making offerings compatible with the current sustainability development goals (SDGs). (See Issac, [0015]).
The Lynch-Issac-Danson combination does not teach using a neural network to identify probability-weighted associations between the inputs and the outputs. However, Chang et al. teaches:
using a neural network to identify probability-weighted associations between the inputs and the outputs (See [0005]- determining respective mapping functions corresponding to a multiclass output of the neural network in association with the input data. Also See [0031]- a neural network apparatus may include a processor configured to input input data to a neural network, determine respective mapping functions corresponding to a multiclass output of the neural network in association with the input data. Also See [0063]- [0063] Each of the nodes of the hidden layers 110 may produce or generate an output based on the each of the nodes implementing a corresponding activation function, e.g., associated with one or more connection weighted inputs from outputs of nodes of a previous layer. Here, though the connection weighted inputs will be discussed herein as being weighted inputs provided by a connection from a node of a previous layer,)
Lynch et al., Issac et al., Danson et al., and Chang et al. are all considered to be analogous to the claimed invention because they are in the same field of predicting student coursework status. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Lynch-Issac-Danson combination to further include using a neural network to identify probability-weighted associations between the inputs and the outputs as taught by Chang et al. This is desirable such that it provides a method for reliable recording and monitoring a user's academic progress to a central resource that is advantageous when considering persons and professionals already in the work force looking to improve their skills and knowledge. (See Chang, [0007])
Claims 9 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Lynch et al. (US 20240394817) in view of Issac et al. (US20240394817), in view of Danson et al. (US 20150100303), further in view of Lin (US 20230320642).
In regards to Claim 9 and 18 the Lynch-Issac-Danson combination teaches the claimed invention as recited in the independent claim above.
Lynch et al. further teaches:
labeling the filtered set of coursework progression data (See [0101]-One or more servers may extract courseware-level data 600 derived from the tracked online activities of the plurality of students taking the plurality of online courses. The courseware-level data 600 is organized based on the structure of each course in a plurality of courses and stored in a database.)
Lynch et al. teaches coursework progeression data but does not teach retraining the status predicting machine-learning model based on the labeled set of coursework progression.
Issac et al. further teaches:
retraining the status predicting machine-learning model based on the labeled set of coursework progression data (See [0044]- the predictive model is trained using supervised learning using a training dataset that includes student data labeled with an actual course grade for plural students that previously enrolled in the course.)
Lynch et al., Issac et al., and Danson et al. are all considered to be analogous to the claimed invention because they are in the same field of predicting student coursework status. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Lynch-Issac-Danson combination to further include retraining the status predicting machine-learning model based on the labeled set of coursework progression data as taught by Issac et al. This is desirable such that it offers better co-learning for K-12 students and higher education experienced candidates by blending prediction and allocation modeling approaches and making offerings compatible with the current sustainability development goals (SDGs). (See Issac, [0015]).
The Lynch et al. teaches labeling the filtered set of coursework progression data but does not teach labeling the filtered set of coursework progression data based on feedback regarding the predicted status. However, Lin teaches
based on feedback regarding the predicted status; (See [0181]- Training the model: The cleaned and preprocessed data is then used to train the foundation model, such as GPT-3, using a process known as supervised learning. During this process, the model is exposed to examples of input and output pairs, such as a patient's statement and a corresponding therapeutic response. The model learns to recognize patterns in the data and generate appropriate responses based on those patterns. They can also be trained using self-supervised learning (SSL) methods, or reinforcement learning with human feedbacks (RLHF) if human annotators are available to score the quality of the outputs)
Lynch et al., Issac et al., Danson et al., and Lin are all considered to be analogous to the claimed invention because they are in the same field of predicting student coursework status. Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the Lynch-Issac-Danson combination to further include based on feedback regarding the predicted status as taught by Lin. This is desirable such that it teach the model to recognize patterns in the data and generate appropriate responses to support the therapeutic. (See Lin, [0184])
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Yamamoto et al. (US 20240386319) discloses a prediction apparatus including a feature extraction unit configured to extract a feature based on past behavior series data of a prediction target and output behavior feature data, a behavior series prediction unit configured to predict a future behavior series of the prediction target based on the behavior feature data using a trained behavior series prediction model for predicting a behavior series.
Li et al. (US 20210398439) discloses a method for predicting student performance in interactive question pools, comprising: a data processing and feature extraction module for: extracting from historical score data records statistical student features reflecting the students' past performances on the questions; and statistical question features indicating a question popularity of each question and the average students' scores on each question.
Jastrzembski et al. (US 20130224699) discloses A method, apparatus and program product are provided for optimizing a training regimen to achieve performance goals. Historical training data is provided. At least one training regimen is defined.
Essa et al. (US -20130096892) discloses a performance prediction system comprising at least one processor, the at least one processor being configured to: define a predictive model based upon a plurality of hypothesises for predicting learner performance, each hypothesis predicting learner performance based upon at least one learner engagement activity.
All sources listed above are relevant to the disclosed and claimed invention.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALAA WADIE HUSSEIN whose telephone number is 571-270-1748. The examiner can normally be reached M-F: 8:00-5:00.
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, Jessica Lemieux can be reached on 571-270-3445. 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.
/A.W.H./
Examiner, Art Unit 3626
/DENNIS W RUHL/Primary Examiner, Art Unit 3626