DETAILED ACTION
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 .
Claim Rejections - 35 USC § 102
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.
Claims 1-7 and 11-14 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by US6072113 (US’113), hereinafter US’113.
Regarding claim 1, US’702 discloses ‘An information processing system (US’113, Fig. 1 , col. 6, lines 64-65:”musical performance teaching system”) comprising: at least one memory that stores a program; and at least one processor (US’113, col. 6, lines 66-67, col. 7, lines 11-14:” computer apparatus includes a CPU 11, a ROM 12, a RAM 13... hard disk 16... program memory area stores programs”) that executes the program to:
discloses ‘acquire user playing data indicative of playing of a piece of music by a user (US’113, col. 2, lines 29-31:”inputting performance data of the student from an electronic musical instrument... making an evaluation of practice results based on the performance data'; col. 5, lines 29-31: 'electronic musical instrument... transmitting performance data representing the playing by the student to the computer apparatus”, the performance data represents the user's musical performance; receives student performance data from an electronic musical instrument; acquisition and analysis of user playing data)
generate habit data indicative of a playing habit of the user in playing the piece of music on a musical instrument (US’112, col. 3, line(s) 23, 29-31:”training musical instrument performance … the history of the practice results … enabling a proper judgment of the student's practice progress”, teaches history of practice data and practice progress data which characterize the student's performance tendencies and therefore constitute data indicative of a playing habit of the user), by inputting the acquired user playing data into at least one first trained model that learns a relationship between (US’113, col. 7, lines 29-33:”user model data consists... performance talent data... and personal tendency data representing the tendency'; col. 7, lines 42-49:”playing skill include... uniformity of fingering strength... agility... finger extensity... directional adaptability... correctness... chord depression... collaboration of both hands”, teaches performance talent, playing skill, and personal tendency data are habit/profile data indicating how the user plays):
player playing training data indicative of playing of a piece of reference music by a player (US’113, col. 5, lines 29-31:”electronic musical instrument... transmitting performance data representing the playing by the student to the computer apparatus”, teaches player performance data), ;
and corresponding training habit data indicative of a playing habit of the player in playing the piece of reference music on a musical instrument, the playing habit being indicated by the player playing training data (US’113, col. 3, lines 31-46:” storing practice schedule data representing a schedule of training musical instrument performance skill of the student in a memory … making an evaluation of practice results based on the performance data of the student from the electronic musical instrument, and .. progression of the training based on … training reflecting … the evaluation of practice results. Thus, the performance training … is determined based on the degree of student's mastering the performance skill”, training based on practice results);
and identify a practice phrase based on the generated habit data (US’113, col. 2, lines 9-12:”selecting music data of a practice music piece for training of the student... in accordance with the judgment made about the performance skill of the student'; col. 4, lines 60-61: “selecting any of the plurality of practice music piece of the second kind based on the evaluation of practice progress”, teaches selecting practice music/sub-practice pieces according to evaluated skill/progress; practice music piece or phrase selected/adapted for the player).
Regarding claim 2, US’113 discloses ‘The information processing system according to claim 1, as discussed above.
US’113 further discloses ‘wherein: the at least one first trained model learns a relationship between (US’113, col. 7, lines 29-32:”user model data consists, as shown in FIG. 16, performance talent data including note reading skill data and playing skill data and representing the overall performance talent (ability)”, teaches performance talent, playing skill, and personal tendency data are habit/profile data indicating how the user plays):
(i) control training data that includes: the player playing training data; and reference music training data indicative of a musical score of the piece of reference music (US’113, col. 3, lines 31-46:” storing practice schedule data representing a schedule of training musical instrument performance skill of the student in a memory … making an evaluation of practice results based on the performance data … progression of the training based on … the evaluation of practice results. Thus, the performance training”, training based on practice results); col. 2, lines 9-13:“selecting music data of a practice music piece for training of the student … about the performance skill of the student, and training the student by presenting a musical score”, score/music data combined with performance data reads on control data/control training data.);
and (ii) the corresponding habit training data, and the at least one processor executes the program to generate the habit data by inputting, into the at least one first trained model, control data that includes (US’113, col. 7, lines 29-33:”user model data consists... performance talent data... and personal tendency data representing the tendency'; col. 7, lines 42-49:”playing skill include... uniformity of fingering strength... agility... finger extensity... directional adaptability... correctness... chord depression... collaboration of both hands”, performance talent, playing skill, and personal tendency data are habit/profile data indicating how the user plays):
the user playing data; and music data indicative of a musical score of the piece of music (US’113, col. 7, lines 57-60:“practice music data... containing... score data, performance data, fingering data and attribute data”; col. 8, lines 10-22:”score data includes image data for visually displaying the notes and the rests'; 'performance data includes tempo data... pitch and duration'; col. 29, lines 8-:”attribute data includes... requisite levels... with respect to the respective skills”, score/music data combined with performance data reads on control data/control training data).
Regarding claim 3, US’113 discloses ‘The information processing system according to claim 1, as discussed above.
US’113 further discloses ‘ ‘further comprising a plurality of practice phrases, each practice phrase of the plurality of practice phrases corresponding to a different playing habit of a different player in playing the musical instrument (US’113, col. 29, lines 21-23:"the specific practice piece of music is a short piece of music consisting of about four or eight measures (bars) prepared for overcoming a specific subject”, multiple short practice music portions corresponding to different instructional subjects),
wherein the at least one processor further executes the program to select a practice phrase that corresponds to the generated habit data from among the plurality of practice phrases (US’113, col. 30, lines 27-30:”the student's preference or performance level with the music category or the requisite performance level represented by the attribute data";(US’113, col. 2, lines 9-12:“selecting music data of a practice music piece for training of the student... in accordance with the judgment made about the performance skill of the student”, selection of practice material according to user characteristics).
Regarding claim 4, US’113 discloses ‘The information processing system according to claim 1, as discussed above.
US’113 further discloses ‘wherein the at least one processor further executes the program to generate the practice phrase (US’113, col. 29, lines 21-23:"the specific practice piece of music is a short piece of music consisting of about four or eight measures (bars) prepared for overcoming a specific subject”, creation of targeted practice material)by editing a reference phrase based on the generated habit data (US’113, col. 32, lines 20-22: "the music score data ... undergo modifications, and the modified practice music data and score data are cut out per unit such as a phrase", modification of existing musical material and phrase-level generation of practice content).
Regarding claim 5, US’113 discloses ‘The information processing system according to claim 4, as discussed above.
US’113 further discloses ‘wherein: the reference phrase includes a time series of chords (US’113, col. 29, lines 30-32:”each music data comprises music title data, music score data, performance data, fingering data and attribute data", teaches musical score information containing chord and note progression information associated with a music piece)
and the editing of the reference phrase includes changing the time series of chords (US’113, col. 32, lines 20-22:"the music score data ... undergo modifications, and the modified practice music data and score data are cut out per unit such as a phrase", teaches modification of phrase-level musical content).
Regarding claim 6, US’113 discloses ‘The information processing system according to claim 4, as discussed above.
US’113 further discloses ‘wherein: the reference phrase includes a disjunct motion in which a pitch difference exceeds a threshold, and the editing of the reference phrase includes omitting or changing the disjunct motion (US’113, col. 32, lines 20-22:"the music score data ... undergo modifications, and the modified practice music data and score data are cut out per unit such as a phrase", teaches modification of melodic phrase content).
Regarding claim 7, US’113 discloses ‘The information processing system according to claim 4, as discussed above.
US’113 further discloses ‘wherein: the reference phrase includes designating a playing technique for a musical instrument (US’113, col. 38, lines 47-57:“The keywords on practice indicate what kinds of performance skill the student can master ... such as skills of chord performance ... scale performance, fingering ... cross-passing of a finger under other fingers ... triplets, syncopation, different rhythms for the right and left hands”, teaches designation of a performance technique through specified chord performance, scale performance, fingering technique, cross-passing fingers, triplets and syncopation)
and the editing of the reference phrase includes changing the playing technique (US’113, col. 33, lines 47-52:" modification process, for example, where the practice area is indicating performance in a slower tempo, note duration data and so forth are to be modified within the performance data. And in step 1308, the CPU 11 supplies the above modified performance data to the electronic musical instrument 25", modification of performance parameters associated with a phrase, including tempo and note duration, thereby changing the manner in which the phrase is performed).
Regarding claim 11, US’945 discloses ‘An electronic musical instrument comprising: a playing device for input operation of a musical instrument by a user (US’113, col. 8, lines 59-60:“an electronic musical instrument 25 for the student's performance practice”);
at least one memory that stores a program; and at least one processor that executes the program (US’113, col. 9, lines 12-13:” operation by the CPU 11 executing the programs stored in the ROM 12”) to:
US’113 further discloses ‘and present the identified practice phrase to the user (US’113, col. 2, lines 9-13:”selecting music data of a practice music piece for training of the student... in accordance with the judgment made about the performance skill of the student”; col. 4, lines 60-62:”selecting any of the plurality of practice music piece of the second kind based on the evaluation of practice progress”; col. 5, lines 8-11”, : “modifying... practice music piece... based on... evaluation of the student's progress”, presents musical score/practice music to the student on the display).
acquire, from the playing device, user playing data indicative of playing of a piece of music by the user;
generate habit data indicative of a playing habit of the user in playing the piece of music on the musical instrument, by inputting the acquired user playing data into at least one first trained model that learns a relationship between:
player playing training data indicative of playing of a piece of reference music by a player;
and corresponding habit training data indicative of a playing habit of the player in playing the piece of reference music on a musical instrument, the playing habit being indicated by the player playing training data;
identify a practice phrase based on the generated habit data; (Claim 11 corresponds to claim 1)
Regarding claim 12, US’702 discloses ‘A computer-implemented information processing method (US’113, col. 1, lines 47-48:” computerized musical performance teaching system and method”) comprising:
acquiring user playing data indicative of playing of a piece of music by a user;
generating habit data indicative of a playing habit of the user in playing the piece of music on a musical instrument, by inputting the acquired user playing data into at least one first trained model that learns a relationship between:
player playing training data indicative of playing of a piece of reference music by a player;
and corresponding training habit data indicative of a playing habit of the user in playing the piece of music on a musical instrument, the playing habit being indicated by the player playing training data;
and identifying a practice phrase based on the generated habit data. (Claim 12 corresponds to claim 1)
Regarding claim 13, US’113 discloses ‘The computer-implemented information processing method according to claim 12, as discussed above.
further comprising providing a plurality of practice phrases, each practice phrase of the plurality of practice phrases corresponding to a different playing habit of a different player in playing the musical instrument,
wherein the practice phrase is identified by selecting a practice phrase that corresponds to the generated habit data, from among the plurality of practice phrases. (Claim 13 corresponds to claim 3)
Regarding claim 14, US’113 discloses ‘The computer-implemented information processing method according to claim 12, as discussed above.
wherein the practice phrase is identified by editing a reference phrase based on the generated habit data, to generate the practice phrase. (Claim 14 corresponds to claim 4)
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 8-10 and 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over US’113, view of US20180341702 (US’702), hereinafter US’702.
Regarding claim 8, US’113 discloses ‘The information processing system according to claim 1, as discussed above.
US’113 further discloses ‘the habit training data (US’113, col. 7, lines 29-33:”user model data … performance talent data including note reading skill data and playing skill data … and personal tendency data”, teaches data indicative of a student's playing habits, tendencies, and performance characteristics).
and corresponding training practice phrase based on the playing habit indicated by the habit training data (US’113, col. 29, lines 21-23:"the specific practice piece of music is a short piece of music consisting of about four or eight measures (bars) prepared for overcoming a specific subject", teaches a practice phrase associated with a particular training objective; teaches a practice phrase used for musical instruction),
US’113 further discloses ‘identify the practice phrase based on the habit data (US’113, col. 10, lines 48-51:” the practice piece of music has been thus determined, a schedule of practice is made with respect to the determined music based on and in accordance with the performance skill represented by the user model data", teaches use of habit-related user model information to identify appropriate practice material).
US’113 does not expressly disclose ‘further comprising at least one second trained model that learns a relationship between: the habit training data and corresponding training practice phrase.
‘wherein the at least one processor further executes the program to identify the practice phrase by inputting the habit data into the at least one second trained model."
However, US’702 discloses "at least one second trained model that learns a relationship between the habit training data and corresponding training practice phrase (US’702, ¶[0067]:"a supervised learning process can then be used to learn a function" , ¶[0067]:”machine learning analysis... used to predict the difficulty of each composition... corpus... labeled... difficulty level”, teaches a trained model that learns relationships between input characteristics and corresponding output information).
US’702 further discloses "identify the practice phrase by inputting the habit data into the at least one second trained model (US’702, ¶[0063]:”machine learning analysis 528 may be used to analyze the structured sheet music data ... to generate higher-level semantic metadata", teaches application of a trained model to input data in order to generate corresponding output information).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to replace the rule-based practice-material selection of US’113 with, or augment it using, the supervised machine-learning techniques of US’702 because US’702 teaches learning relationships between musical characteristics and corresponding output information from training data, thereby improving the accuracy, adaptability, and personalization of selecting practice phrases based upon a user's performance habits and tendencies.
Regarding claim 9, US’113 (in view of US’702) discloses ‘The information processing system according to claim 8, as discussed above.
US’113 does not expressly disclose ‘wherein: the at least one second trained model comprises a plurality of second trained models,
each second trained model of the plurality of second trained models corresponding to a different musical instrument,
and the at least one processor further executes the program to identify the practice phrase by using any one of the plurality of second trained models.
However, US’702 discloses ‘wherein: the at least one second trained model comprises a plurality of second trained models (US’702, ¶[0065]:”ensemble learning uses multiple machine learning algorithms", teaches multiple trained models),
each second trained model of the plurality of second trained models corresponding to a different musical instrument (US’702, Table 2-continued:” Idiomatic Instrumental Techniques”, ”Instrumental Changes” “same passage played on different instruments can have varying degrees of difficulty. For example, 16'h note flourishes are relatively easy to perform on flute and piccolo, but extremely difficult on tuba”, analysis of instrument-specific musical characteristics and idiomatic instrumental techniques; teaches instrument-dependent modeling),
and the at least one processor further executes the program to identify the practice phrase by using any one of the plurality of second trained models (US’702, ¶[0100]:phrase extraction 542 is a process for identifying smaller musical passages… A phrase 544 may be identified using rules derived from music theory, heuristics, analysis of individual measures obtained via rules analysis 524, machine learning analysis 528, or both”, each trained model is selected and applied according to the particular analysis being performed).
It would have been obvious to combine US113's music teaching system that evaluates student performance and selects/modifies practice music with the machine-learning metadata/difficulty analysis of US’702’s to implement the known evaluation/selection functions with trained models because machine learning was known for detecting musical patterns, generalizing from labeled data, and predicting difficulty/semantic metadata.
Regarding claim 10, US’113 discloses ‘The information processing system according to claim 1, as discussed above.
US’113 does not expressly disclose ‘wherein: the at least one first trained model comprises a plurality of first trained models,
each first trained model of the plurality of first trained models corresponding to a different musical instrument,
and the at least one processor further executes the program to generate the habit data by using any one of a first trained model from among the plurality of first trained models.
However, US’702 discloses ‘wherein: the at least one first trained model comprises a plurality of first trained models (US’702, ¶[0065]:”ensemble learning uses multiple machine learning algorithms", teaches multiple trained models),
each first trained model of the plurality of first trained models corresponding to a different musical instrument (US’702, Table 2-continued:” Idiomatic Instrumental Techniques”, ”Instrumental Changes” “same passage played on different instruments can have varying degrees of difficulty. For example, 16'h note flourishes are relatively easy to perform on flute and piccolo, but extremely difficult on tuba”, analysis of instrument-specific musical characteristics and idiomatic instrumental techniques; teaches instrument-dependent modeling),
and the at least one processor further executes the program to generate the habit data by using any one of a first trained model from among the plurality of first trained models (US’702, ¶[0100]:phrase extraction 542 is a process for identifying smaller musical passages… A phrase 544 may be identified using rules derived from music theory, heuristics, analysis of individual measures obtained via rules analysis 524, machine learning analysis 528, or both”, each trained model is selected and applied according to the particular analysis being performed).
It would have been obvious to combine US113's music teaching system that evaluates student performance and selects/modifies practice music with the machine-learning metadata/difficulty analysis of US’702’s to implement the known evaluation/selection functions with trained models because machine learning was known for detecting musical patterns, generalizing from labeled data, and predicting difficulty/semantic metadata.
Regarding claim 15, US’113 discloses ‘The computer-implemented information processing method according to claim 12, as discussed above.
further comprising at least one second trained model that learns a relationship between: the habit training data;
and corresponding training practice phrase based on the playing habit indicated by the habit training data,
wherein the at least one processor further executes the program to identify the practice phrase by inputting the habit data into the at least one second trained model. (Claim 15 corresponds to claim 8)
Regarding claim 16, US’702 discloses a computing system comprising: at least one memory that stores a program; and at least one processor that executes the program (US’113, col. 1, lines 57-60:”a machine readable medium containing program instructions executable in a computerized musical performance teaching system for causing the system to realize such a musical performance training”; col. 6, line 67, col. 7, lines 11-15:”computer apparatus includes a CPU 11, a ROM 12, a RAM 13... hard disk 16... program memory area stores programs, teaches the computing system architecture) to:
acquire first training data that includes: player playing training data indicative of playing of a piece of reference music by a player (US’113, col. 2, lines 29-31:”inputting performance data of the student from an electronic musical instrument... making an evaluation of practice results based on the performance data'; col. 5, lines 29-31: 'electronic musical instrument... transmitting performance data representing the playing by the student to the computer apparatus”, the performance data represents the user's musical performance; receives student performance data from an electronic musical instrument; acquisition and analysis of user playing data);
and corresponding habit training data indicative of a playing habit of the player in playing the piece of reference music on a musical instrument, the playing habit being indicated by the player playing training data (US’113, col. 3, lines 31-46:” storing practice schedule data representing a schedule of training musical instrument performance skill of the student in a memory … making an evaluation of practice results based on the performance data of the student from the electronic musical instrument, and .. progression of the training based on … training reflecting … the evaluation of practice results. Thus, the performance training … is determined based on the degree of student's mastering the performance skill”, training based on practice results);
US’113 does not expressly disclose ‘machine learning,
[and]
and establish, using machine learning with the first training data, at least one first trained model that learns a relationship between the player playing training data and the habit training data.
However, US’702 discloses ‘machine learning (US’702, ¶[0063]:”machine learning analysis 528 may be used to analyze the structured sheet music data... to generate higher-level semantic metadata”, teaches use of a trained model to generate output information from input information)
and establish, using machine learning with the first training data, at least one first trained model that learns a relationship between the player playing training data (US’702 , ¶[0064]:"Machine learning is a subfield of computer science that studies a class of algorithms that can detect patterns in data and generalize those patterns", the model learns relationships from data) and the habit training data (US’702, ¶[0067]:"a supervised learning process can then be used to learn a function" , ¶[0067]:”machine learning analysis... used to predict the difficulty of each composition... corpus... labeled... difficulty level”, a trained model that learns a relationship between input data and output information; the supervised model learns a relationship between input data and corresponding output information).
It would have been obvious to use the machine-learning metadata/difficulty analysis and incorporate the supervised machine-learning techniques of US’702 in order to implement the known evaluation/selection functions with trained models to US’113's computerized music teaching system that evaluates student performance and selects/modifies practice music because machine learning was known for detecting musical patterns and predicting difficulty in composition.
Regarding claim 17, US’113 (in view of US’702) discloses ‘The machine learning system according to claim 16, as discussed above.
US’113 further discloses ‘wherein: the acquiring of the first training data includes:
acquiring player playing data indicative of playing of the piece of reference music by the player (US’113, col. 2, lines 22:”practice schedule”; col. 2, lines 29-31:”inputting performance data of the student from an electronic musical instrument... making an evaluation of practice results based on the performance data'; col. 5, lines 29-31: 'electronic musical instrument... transmitting performance data representing the playing by the student to the computer apparatus”, the performance data represents the user's musical performance; receives student performance data from an electronic musical instrument; acquisition and analysis of user playing data); acquiring comment data indicating:
a playing habit of the player in playing the musical instrument (US’112, col. 3, line(s) 23, 29-31:”training musical instrument performance … the history of the practice results … enabling a proper judgment of the student's practice progress” teaches history of practice data and practice progress data which characterize the student's performance tendencies and therefore constitute data indicative of a playing habit of the user) at a time point within the piece of reference music; and the time point (US’113, col. 3, lines 27-29:” the performance training is conducted according to the training schedule, while the history of the practice results is also memorized”, teaches data associated with a particular location within the musical performance);
and generating the first training data (US’113, col. 4, lines 44-45:different types of computerized tutors have “different types of tutors having different characteristic ways of tutoring the students”; col. 7, lines 52-53:”personal tendency”; col. 8, lines 6-10:”therecords with respect to the respective practice areas such as the dates of practice, the rates of success in practice, the approvals of practice finish, the time estimated (scheduled) for practice, the time actually consumed for practice by students”, teaches generation of training information from player performance characteristics) that includes:
the player playing training data; and the corresponding habit training data (US’113, col. 3, lines 31-46:” storing practice schedule data representing a schedule of training musical instrument performance skill of the student in a memory … making an evaluation of practice results based on the performance data of the student from the electronic musical instrument, and .. progression of the training based on … training reflecting … the evaluation of practice results. Thus, the performance training … is determined based on the degree of student's mastering the performance skill”, training based on practice results),
the player playing data includes a section that includes the time point indicated by the comment data (US’113, col. 24, lines 43-47:” the first phrase of the practice music data stored in the RAM 13 is designated based on the practice area thus read out, for example the first phrase portion indicated by an encircled numeral one in the score” (teaches sections of performance data associated with particular locations in the music),
the player playing training data indicates the playing of the piece of reference music within the section of the player playing data (US’113, col. 5, lines 29-31:”electronic musical instrument... transmitting performance data representing the playing by the student to the computer apparatus”, teaches player performance data),
and the corresponding habit training data indicates the playing habit indicated by the comment data (US’113, col. 7, lines 52-54:”The data on personal tendency consists of Such data as represent as user's preference of music, user's wishes in regard to the lesson to take, and user's character”, teaches habit-related data corresponding to the player's performance characteristics).
US’113 does not expressly disclose establishing the claimed training relationship using machine-learning techniques.
However, US’702 discloses "using machine learning with the first training data (US’702, ¶[0067]:"a supervised learning process can then be used to learn a function", teaches creation of training relationships using machine learning).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to apply the supervised machine-learning techniques of US’702 to the performance-history, user-model, and practice-characteristic data of US’113 because US’702 teaches learning relationships from training data and US’113 already collects player-performance characteristics and habit-related information suitable for use as machine-learning training examples.
Regarding claim 18, US’113 (in view of US’702) discloses ‘The machine learning system according to claim 17, as discussed above.
US’113 further discloses ‘wherein: the at least one processor further executes the program to: acquire the player playing data from a first apparatus (US’113, col. 5, lines 29-31:” electronic musical instrument being adapted for playing by a student and transmitting performance data representing the playing by the student to the computer apparatus", teaches acquisition of player performance data from a first apparatus);
and acquire the comment data from a second apparatus (US’113, col. 7, lines 21-25:”use this computer device and the user information … representing the name of the user … user model data; col. 7, lines 44-56:”connected to the computer apparatus are disk drivers … used to record various data relating to the music performance training and then to transfer the data”; col. 9, lines 50-54:“The student will respond to (answer) the given subjects one after another using the keyboard 14 or the electronic musical instrument 25, while the computer will judge the student’s skill with respect to the various subjects based on the student's”, teaches acquisition of habit-related data from a second apparatus separate from the instrument).
Regarding claim 19, US’113 (in view of US’702) discloses ‘The machine learning system according to claim 16, as discussed above.
US’113 further discloses ‘wherein the first trained model learns a relationship (US’113, col. 7, lines 29-32:”user model data consists, as shown in FIG. 16, performance talent data including note reading skill data and playing skill data and representing the overall performance talent (ability)”, teaches performance talent, playing skill, and personal tendency data are habit/profile data indicating how the user plays) between: (i) control training data that includes: the player playing training data; and reference music training data indicative of a musical score of the piece of reference music (US’113, col. 3, lines 31-46:” storing practice schedule data representing a schedule of training musical instrument performance skill of the student in a memory … making an evaluation of practice results based on the performance data … progression of the training based on … the evaluation of practice results. Thus, the performance training”, training based on practice results); col. 2, lines 9-13:“selecting music data of a practice music piece for training of the student … about the performance skill of the student, and training the student by presenting a musical score”, score/music data combined with performance data reads on control data/control training data.);
and (ii) the corresponding habit training data (US’113, col. 7, lines 29-33:”user model data consists... performance talent data... and personal tendency data representing the tendency'; col. 7, lines 42-49:”playing skill include... uniformity of fingering strength... agility... finger extensity... directional adaptability... correctness... chord depression... collaboration of both hands”, performance talent, playing skill, and personal tendency data are habit/profile data indicating how the user plays).
Regarding claim 20, US’113 (in view of US’702) discloses ‘The machine learning system according to claim 16, as discussed above.
US’113 further discloses ‘wherein the at least one processor further executes the program to: acquire a plurality of pieces of second training data (US’113, col. 3, lines 27-31:” the performance training is conducted according to the training schedule, while the history of the practice results is also memorized therein, thereby enabling a proper judgment of the student's practice progress”, maintaining user model data, history of practice data, practice-progress information, and practice schedules for a student over multiple practice sessions), each piece of second training data of the plurality of pieces of second training data including: the habit training data (US’113, col. 7, lines 29-33:”user model data consists... performance talent data... and personal tendency data representing the tendency'; col. 7, lines 42-49:”playing skill include... uniformity of fingering strength... agility... finger extensity... directional adaptability... correctness... chord depression... collaboration of both hands”, teaches data indicative of a player's habits, tendencies, and performance characteristics);
and corresponding training practice phrase based on the playing habit indicated by the habit training data (US’113, col. 3, lines 31-46:” storing practice schedule data representing a schedule of training musical instrument performance skill of the student in a memory … making an evaluation of practice results based on the performance data of the student from the electronic musical instrument, and .. progression of the training based on … training reflecting … the evaluation of practice results. Thus, the performance training … is determined based on the degree of student's mastering the performance skill”, training based on practice results);
US’113 further discloses "corresponding training practice phrase (US’113, col. 29, lines 21-23:"the specific practice piece of music is a short piece of music consisting of about four or eight measures (bars) prepared for overcoming a specific subject", teaches a practice phrase) based on the playing habit indicated by the habit training data (US’113, col. 10, lines 24-26:"selects several practice music pieces from among the internal database 17 in accordance with the user model data”, teaches practice phrases selected based upon the player's characteristics and tendencies).
US’113 does not expressly disclose ‘and establish, using the plurality of pieces of second training data with machine learning, a second trained model that learns a relationship between:
the habit training data of each piece of second training data;
and the corresponding training practice phrase of each piece of second training data.
However, US’702 discloses ‘establish ... with machine learning ... a second trained model (US’702, ¶[0067]:"a supervised learning process can then be used to learn a function", teaches creation of a trained model from training examples),
a second trained model that learns a relationship (US’702, ¶[0063]:”machine learning analysis 528 may be used to analyze the structured sheet music data... to generate higher-level semantic metadata”, teaches a trained model that learns relationships between input information and corresponding output information).
US’702 further discloses ‘learns a relationship between: the habit training data ... and the corresponding training practice phrase (US’702, ¶[0067]:”music data 112 may include a corpus of compositions or parts that are labeled e.g., manually labeled) as having a certain difficulty level (e.g. on a 1-5 scale, a 1-10 scale, etc.”, using labeled training examples in a supervised-learning process to learn a function relating input characteristics to corresponding output information; a learned relationship between training inputs and corresponding outputs).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to utilize the user-model data, practice-history data, and associated practice phrases of US’113 as training examples for the supervised machine-learning techniques of US’702 because US’113 already associates player characteristics and tendencies with selected practice material, and US’702 teaches learning such relationships from training data to generate predictive models. The combination would have automated and improved the generation of practice phrases corresponding to player habits and performance tendencies.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. US11288975 teaches AI/model-based music instruction: musical score model, student performance model, captured performance comparison, generated/customized practice music.
US20220238088 teaches trained acoustic model trained on score/performance data.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to NICOLE K GILLESPIE whose telephone number is (571)482-4187. The examiner can normally be reached Monday-Friday 7:30-5pm.
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, Dedei K Hammond can be reached at (571)270-3819. 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.
/NICOLE K GILLESPIE/ Examiner, Art Unit 2837
/DEDEI K HAMMOND/ Supervisory Patent Examiner, Art Unit 2837
Prosecution Insights