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 .
Receipt of Applicant’s Amendment filed January 14, 2026, is acknowledged.
Response to Amendment
Claims 1, 4-7, 13, 16, 20, and 21 have been amended. Claim 19 has been canceled. Claims 1-18, 20, and 21 are pending and are provided to be examined upon their merits.
Response to Arguments
Applicant’s arguments with respect to claims 1-18, 20, and 21 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. A response is provided below in bold where appropriate.
Applicant notes Drawing Objections, pg. 12 of Remarks:
Objections to the Drawings
The office action objects to the drawings. The attached replacement drawing sheets include corrections to Fig. 4. Accordingly, the drawing objection has been addressed, and withdrawal of the objection is respectfully requested.
The drawing amendment is entered.
Applicant argues 35 USC 112(b), starting pg. 12 of Remarks:
Claim Rejections Under 35 U.S.C. § 112 (b)
Claims 4-7 and 13-18 stand rejected under 35 U.S.C. § 112(b) for indefiniteness as failing to particularly point out and distinctly claim the subject matter which Applicant regards as the invention. These rejections are respectfully traversed.
As described in the present disclosure, a "degree of similarity" between users is calculated using a user-based collaborative filtering recommendation algorithm, which may be implemented by calculating cosine similarity. See paragraph [0091].
Consistent with this disclosure, the term "degree of similarity" in claims 4-7 and 13-16 has been amended to "cosine similarity." This amendment provides an objective, well- understood similarity metric with a clear computational meaning, thereby resolving the alleged indefiniteness. Accordingly, claims 4-7 and 13-16 now recite definite subject matter.
Applicant has “degree of similarity” with “cosine similarity” where there is no measure or standard as to the degree of similarity. The degree could be anything. This rejection is respectfully modified but maintained.
With respect to claim 18, the Office Action's indefiniteness concern is misplaced. Claim 18 does not recite the term "degree of similarity." Instead, claim 18 recites "degrees of match" between fitness effect information and fitness regimen information. As would be readily understood by a person of ordinary skill in the art, this term refers to a quantified degree of matching between information items. For example, as described in paragraph [00121], such a matching degree may be represented by a numerical value (e.g., between 0 and 1), where a larger value indicates a higher degree of match.
Accordingly, claim 18 is clear and definite, and no amendment is required.
Noted and withdrawn.
For at least the foregoing reasons, withdrawal of the § 112(b) rejections of claims 4-7 and 13-18 is respectfully requested.
Matching based on a cosine similarity could be any cosine value from 1 to -1. Therefore, it is indefinite as to matching based on cosine similarity if the cosine value can be anything.
Applicant argues 35 USC 101 Rejection, starting pg. 13 of Remarks:
Claim Rejections Under 35 U.S.C. § 101
Claims 1-18, 20, and 21 stand rejected under 35 U.S.C. § 101 as allegedly being directed to an abstract idea without significantly more. Office Action at page 4. These rejections are respectfully traversed.
Step 1 - Statutory Category
As a threshold matter, amended claim 1 is directed to a recommendation method, i.e., a process. Claim 1 therefore falls squarely within a statutory category of patent-eligible subject matter under 35 U.S.C. § 101.
Step 2A, Prong One -Whether the Claims Recite an Abstract Idea
Under Step 2A, Prong One, the Office asserts that independent claims 1, 20, and 21 are directed to an abstract idea because the recited limitations allegedly fall within the "Certain Methods of Organizing Human Activity" grouping, characterizing the claims as managing personal behavior.
However, the subject matter of independent claim 1 has been amended to expressly recite, inter alia:
"...constructing a user human body model of a user to be recommended
based on physiological feature information input by the user to be recommended, wherein the user human body model is a digital human body model or a 3D human body model; and determining a matching human body model matching with the user human body model from a plurality of comparable human body models in a fitness database."
These limitations do not constitute managing personal behavior, nor do they fall within any other recognized category of abstract ideas. A human cannot, in the human mind or using pencil-and-paper, construct a digital or 3D human body model from physiological feature data, nor can a human mentally perform matching operations between such models stored in a fitness database. The claimed matching between human body models is necessarily a computer- implemented operation requiring digital model construction, storage, and comparison.
A user inputs information to be recommended in order to construct a human body model. This is a user following instructions which is abstract as managing personal behavior. Recommending is teaching, also abstract under certain methods of organizing human activity.
Respectfully, a person can draw a 3-D model, similar to what a computer screen can draw. Both use 2-dimentional devices, paper and display monitor, to represent the “model.”
Accordingly, amended independent claim 1 does not recite an abstract idea under Step 2A, Prong One. Independent claims 20 and 21 incorporate the same substantive features in a computer-implemented operation requiring digital model construction, storage, and comparison.
Using a human body model to provide a fitness regimen is managing personal behavior. This is also teaching a user. The Examiner maintains the claim recite abstract elements.
Step 2A, Pron Two - Integration into a Practical Application
Even if the claims were deemed to recite an abstract idea, the claimed subject matter as amended is not "directed to" such an idea because the claims integrate any alleged judicial exception into a practical application.
Specifically, the subject matter of amended claim 1 recites constructing a user- specific digital or 3D human body model within a computer based on physiological feature information and matching that model against a plurality of comparable human body models stored in a fitness database to determine fitness regimen information. As explained in paragraphs [0083] and [0089] of the specification, this technical process enables more targeted fitness recommendations by identifying comparable users in objectively similar physiological states.
This computer-implemented matching of digital human body models improves the accuracy of fitness regimen recommendations generated by the system. The claims therefore recite a specific technical solution implemented through computer data processing, rather than an abstract result or generalized instruction.
Respectfully, the act of matching can be done by a person and there are no claim steps of new matching technology that improves computer technology itself.
Accordingly, when considered as a whole, the additional elements in amended independent claim 1 integrate any alleged judicial exception into a practical application, thereby satisfying Step 2A, Prong Two.
If technology is being improved, it needs to be claimed. All of the steps, constructing, matching, and determining a fitness regime are abstract.
Step 2B - Significantly More
For completeness, even if the claims were found not to integrate a judicial exception into a practical application, the claims as amended nonetheless amount to significantly more than any alleged abstract idea.
As discussed above and described in paragraphs [0083] and [0089] of the present application, the claimed construction and matching of digital or 3D human body models based on physiological feature information improves the operation of a recommendation system by increasing the accuracy and relevance of automatically generated fitness regimen recommendations. This constitutes a technical improvement in computerized information recommendation systems, rather than a mere automation of a mental process.
The above increasing accuracy and relevance is an effect or result.
From MPEP 2106.05(f):
(3) The particularity or generality of the application of the judicial exception.
A claim having broad applicability across many fields of endeavor may not provide meaningful limitations that integrate a judicial exception into a practical application or amount to significantly more. For instance, a claim that generically recites an effect of the judicial exception or claims every mode of accomplishing that effect, amounts to a claim that is merely adding the words “apply it” to the judicial exception. See
Internet Patents Corporation v. Active Network, Inc., 790 F.3d 1343, 1348, 115 USPQ2d 1414, 1418 (Fed. Cir. 2015) (The recitation of maintaining the state of data in an online form without restriction on how the state is maintained and with no description of the mechanism for maintaining the state describes “the effect or result dissociated from any method by which maintaining the state is accomplished” and does not provide a meaningful limitation because it merely states that the abstract idea should be applied to achieve a desired result). See also O’Reilly v. Morse, 56 U.S. 62 (1854) (finding ineligible a claim for “the use of electromagnetism for transmitting signals at a distance”); The Telephone Cases, 126 U.S. 1, 209 (1888) (finding a method of “transmitting vocal or other sound telegraphically ... by causing electrical undulations, similar in form to the vibrations of the air accompanying the said vocal or other sounds,” to be ineligible, because it “monopolize[d] a natural force” and “the right to avail of that law by any means whatever.”).
While the above accuracy and relevance are not claimed, even if they were, the claims need to recite the steps that result in the accuracy. Further, matching by itself is at a high level, is abstract, and is not improving a technology as claimed.
Accordingly, amended independent claim 1, as well as dependent claims 2-18 and corresponding apparatus and computer-readable medium claims 20 and 21, qualify as patent- eligible subject matter under 35 U.S.C. § 101.
Thus, Applicant respectfully requests withdrawal of the rejection under 35 U.S.C. § 112(b).
The rejection is respectfully maintained but modified for the claim amendments.
Applicant argues 35 USC 103 Rejection, starting pg. 16 of Remarks:
Claim Rejections Under 35 U.S.C. § 102
Claims 1-17, 20, and 21 stand rejected under 35 U.S.C. § 103 for obviousness over United States Patent Application Publication No. 2018/0036591 King ("King") in view of United States Patent Application Publication No. 2017/0027528 to Kaleal ("Kaleal").
These rejections are respectfully traversed.
Distinguishing Features Over King
As amended, the subject matter of independent claim 1 includes at least the following distinguishing technical features not taught or suggested by King:
constructing a user human body model based on physiological feature information input by the user, wherein the user human body model is a digital human body model or a 3D human body model; and
(ii) determining a matching human body model by matching the user human body model with a plurality of comparable human body models stored in a fitness database, the comparable human body models being generated based on physiological feature information of comparable users.
Feature (i): Construction of a Physiological Human Body Model
As described, for example, in paragraph [0082], the claimed system constructs a user human body model based on physiological feature information (e.g., height, weight, and body fat), which matches that model against comparable human body models in a fitness database, and determines fitness regimen information associated with the matched model.
From Applicant’s specification…
“For example, the system obtains physiological feature information input by comparable users such as fitness models, fitness coaches, and other users willing to share data. The physiological feature information may comprise height, weight, body fat, etc. The system can also obtain image information of the comparable users, such as full-body 2D photos or partial body photos.” [0062]
Therefore, physiological features can be based on image information.
In contrast, King discloses that "the user may choose an avatar from a list of avatars (e.g., an avatar that looks like the user or an avatar that looks like a celebrity)" (King 1[0062]). King's avatar is selected from predefined options or generated from uploaded images; it is not constructed from physiological feature information and does not constitute a digital or 3D human body model representing physiological characteristics.
From King…
“…In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout. In some embodiments, workout video blocks in the same group (e.g., family, block type, set, stream, or other groups) may be provided by the same instructor (human, or machine generated). For example, a user may choose any particular instructor for any workout video block (every instructor provides instructions for all the workout sessions available to the user). In some cases, specific instructors (human, or machine generated) may provide specific workout instructions. For example, some instructors may only give instructions for specific body-regions (e.g., legs, arms, etc.), for specific level of difficulty, for specific workout type (e.g., warm-up, cool down, cardio, etc.), or other specific workout instructions.” [0062]
Therefore, King teaches user input their image for creation of an avatar.
Accordingly, King's avatar is not equivalent to the claimed user human body model, and King fails to disclose distinguishing feature (i).
The Examiner respectfully disagrees and maintains King is excellent prior art.
Feature (ii): Model-to-Model Matching in a Fitness Database
As further described in paragraphs [0062]-[0064] and [0082], the subject matter of claim 1 constructs comparable human body models from physiological feature information provided by comparable users (e.g., fitness models, coaches, or other users), stores those models along with associated fitness regimen information in a fitness database, and determines fitness regimen information for the user by matching between human body models.
Applicant’s claims are matching a model they constructed based on a user with another model in a database.
From Applicant’s specification:
“For example, the system can construct a user human body model of the user to be recommended based on physiological feature information of the user to be recommended, match the user human body model with comparable human body models in a fitness database, and determine a comparable human body model similar to the user human body model as a matching human body model, and recommend fitness regimen information related to the matching human body model to the user to be recommended.” [0082]
Therefore, matching models.
King does not teach or even suggest determining fitness regimen information by matching a constructed user human body model with comparable human body models stored in a database. Instead, King recommends workout videos based on user profile information, goals, or instructor content (see, e.g., King 1[0062]). King's disclosure relates to selecting instructional content, not to matching physiological human body models to identify a comparable user whose regimen informs the recommendation.
Applicant has amended their claims to match models.
From King…
“…In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar)….” [0062]
King teaches a user can create an avatar based on an image of themselves.
King also teaches a user can chose an avatar that looks like the user. Therefore, matching the avatar with themselves.
It seems obvious the user could compare (match) their created avatar with avatars that look like the user.
Accordingly, King also fails to disclose distinguishing feature (ii).
New art is cited that teaches matching models.
Kaleal Does Not Cure the Deficiencies of King
Kaleal is cited for disclosing avatar-based fitness guidance. Kaleal discloses that an avatar may observe and respond to a user's physical activity data, provide fitness guidance, or monitor adherence to a schedule (e.g., see Kaleal 11[0060], [0064], and [0076]). However, Kaleal also does not teach or suggest constructing a digital or 3D human body model based on physiological feature information input by the user.
Moreover, Kaleal does not disclose matching a constructed user human body model with comparable human body models to determine a matching human body model, nor determining fitness regimen information based on regimen information associated with such a matched model. Kaleal's avatar provides guidance, but it is not a matched human body model derived from physiological model-to-model comparison.
Thus, Kaleal does not remedy the deficiencies of King with respect to the distinguishing features of amended claim 1.
Kaleal was used to specifically teach human body model. Both prior arts teach avatar.
New art is cited that teaches matching models.
Lack of Motivation and Predictable Result
Neither King nor Kaleal, alone or in combination, teaches or suggests the claimed approach of (i) constructing physiological digital or 3D human body models and (ii) determining fitness regimen information by matching those models against comparable human body models stored in a fitness database. The cited references operate at the level of avatars, profiles, and instructional content, not at the level of physiological model construction and model-to-model matching.
Accordingly, even if combined, King and Kaleal would not have rendered obvious the technical solution recited in the subject matter of amended claim 1.
For at least the reasons set forth above, the subject matter of amended independent claim 1 is now in condition for allowance. Applicant has amended independent claims 20 and 21 substantially similar to the amended subject matter of independent claim 1.
Applicant respectfully submits that amended claims 1, 20, and 21 are now in condition for allowance. In addition, claims 2-18 depend from claim 1, and thus, claims 2-18 are also allowable at least for the same reasons as claims 1, 20, and 21.
Withdrawal of the 35 U.S.C. § 103 rejection is respectfully requested.
The rejection is respectfully maintained but modified based on the claim amendments.
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 1-18, 20, and 21 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claims 1-18, 20, and 21 are directed to a method, system or product, which are statutory categories of invention. (Step 1: YES).
The Examiner has identified system Claim 1 as the claim that represents the claimed invention for analysis and is similar to system claim 20 and product claim 21.
Claim 1 recites the limitations of:
A recommendation method for fitness regimen information, executed by a processor, comprising:
constructing a user human body model of a user to be recommended based on physiological feature information input by the user to be recommended, wherein the user body model is a digital human body model or a 3D human body model;
determining a matching human body model matching with the user human body model from a plurality of comparable human body models, in a fitness database, the plurality of comparable human body models being generated based on physiological feature information of a plurality of comparable users; and
determining fitness regimen information for the user to be recommended based on fitness regimen information of a comparable user associated with the matching human body model.
These above limitations, under their broadest reasonable interpretation, cover performance of the limitation as certain methods of organizing human activity. The claim recites elements, highlighted in bold above, which covers performance of the limitation as managing personal behavior. Constructing a user human body model of a user to be recommended (teaching), based on physiological feature information input by the user (following rules or instruction) and determining a fitness regimen information for the user to be recommended based on fitness regimen of a comparable user associated with the matching human body model (teaching) is managing personal behavior. Determining a matching human body model matching with the user from a plurality of comparable human body models is managing relationships between people as a user’s body model is matched to other body models. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation as managing personal behavior or managing relationships between people, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. Claims 20 and 21 are also abstract for similar reasons. (Step 2A-Prong 1: YES. The claims are abstract)
In as much as the claims are determining a matching human body model for physiological features and determining fitness regimen information, the claims are also abstract under Mental Processes grouping of abstract ideas. A person in their mind and with pen and paper can construct a 3D human body model, determine in their mind a matching with the human body model, and determine a fitness regimen information for the user to be recommended based on a comparable user associated with the matching human body model. The digital human body model could be constructed with a generic computer. Mental processes have been shown to encompass using a generic computer.
This judicial exception is not integrated into a practical application. In particular, the claims only recite: processor (Claim 1); memory, processor (Claim 20); non-transitory computer-readable storage medium, processor (Claim 21). The computer hardware is recited at a high-level of generality (i.e., as a generic processor performing a generic computer function) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Therefore claims 1, 20, and 21 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)
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because, when considered separately and as an ordered combination, they do not add significantly more (also known as an “inventive concept”) to the exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a computer hardware amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Accordingly, these additional elements, when considered separately and as an ordered combination, do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Thus claims 1, 20, and 21 are not patent eligible. (Step 2B: NO. The claims do not provide significantly more)
Dependent claims 2-18 further define the abstract idea that is present in their independent claim 1 and thus correspond to Certain Methods of Organizing Human Activity and Mental Processes and hence are abstract for the reasons presented above. The dependent claims do not include any additional elements that integrate the abstract idea into a practical application or are sufficient to amount to significantly more than the judicial exception when considered both individually and as an ordered combination. The dependent claims themselves are abstract or just further limiting abstract ideas. Claims 4-7 and 13-16 16 are also rejected as mathematical concepts as they recite or depend from claims that recite cosine similarity which is a formula for determining matching. Therefore, the claims 2-18 are directed to an abstract idea. Thus, the claims 1-18, 20, and 21 are not patent-eligible.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-18, 20, and 21 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites “constructing a user human body model of a user to be recommended based on physiological feature information input by the user to be recommended,…” where “to be recommended” is indefinite as recommend a user human body model and recommend physiological feature information are never recommended. For examination purposes, the “to be recommended” is ignored. Claims 20 and 21 have a similar problem.
Claim 4 recites “determining the matching human body model based on a cosine similarity” where cosine similarity is a relative term rendering the claim indefinite. The cosine similarity could be any undefined value with no limitation or basis as to the value. Claims 5-7, 13, and 16 have a similar problem.
Claims 2-18 are further rejected as they depend from their independent claim 1 and claims 5-7 and 14-17 also depend from their respective claims 4 and 13.
Examiner Request
The Applicant is requested to indicate where in the specification there is support for amendments to claims should Applicant amend. The purpose of this is to reduce potential 35 U.S.C. §112(a) or §112 1st paragraph issues that can arise when claims are amended without support in the specification. The Examiner thanks the Applicant in advance.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-3, 8-12, 20, and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Pub. No. US 2018/0036591 to King et al. in view of Pub. No. US 2017/0027528 to Kaleal, III et al. in view of Pub. No. US 2009/0259648 to Boker et al.
Regarding claims 1, 20, and 21
(claim 1) A recommendation method for fitness regimen information, executed by a processor, comprising:
constructing a user human body model of a user to be recommended based on physiological feature information input by the user to be recommended, wherein the user body model is a digital human body model or a 3D human body model;
[No Patentable Weight is given to alternative claim language where only one of the alternatives is required. In this case, digital human body model is provided.]
{
From Applicant’s specification on physiological features…
“For example, the system obtains physiological feature information input by comparable users such as fitness models, fitness coaches, and other users willing to share data. The physiological feature information may comprise height, weight, body fat, etc. The system can also obtain image information of the comparable users, such as full-body 2D photos or partial body photos.” [0062]
Therefore, an image of a user, as well as height, weight, etc. are examples of physiological information.
}
King et al. teaches:
Computer systems…
“The present disclosure relates generally to computer systems and, more specifically, to systems and methods for prescribing fitness-related activities responsive to events.” [0002]
User may upload (input) an image of themselves (physiological feature information) to create (construct) an avatar (digital human body model)…
“In some embodiments, a workout video block may include instructions provided by a human instructor (e.g., a coach, a trainer, a physical therapist, a chiropractor, a healthcare provider, or other person giving the workout instructions). In some cases, the instructions may be described or demonstrated by the person giving the instructions in the video, described by a person different than the persons demonstrating the workout instructions, or any combination thereof. In some embodiments, a workout video block may include instructions provided by a machine generated character configured to describe or demonstrate workout instructions (e.g., an avatar). In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout. In some embodiments, workout video blocks in the same group (e.g., family, block type, set, stream, or other groups) may be provided by the same instructor (human, or machine generated). For example, a user may choose any particular instructor for any workout video block (every instructor provides instructions for all the workout sessions available to the user). In some cases, specific instructors (human, or machine generated) may provide specific workout instructions. For example, some instructors may only give instructions for specific body-regions (e.g., legs, arms, etc.), for specific level of difficulty, for specific workout type (e.g., warm-up, cool down, cardio, etc.), or other specific workout instructions.” [0062]
determining a matching human body model matching with the user human body model from a plurality of comparable human body models, in a fitness database, the plurality of comparable human body models being generated based on physiological feature information of a plurality of comparable users; and
User may choose an avatar (human body model) from a list (database) of avatars (human body models) that look like (match) the user…
“In some embodiments, a workout video block may include instructions provided by a human instructor (e.g., a coach, a trainer, a physical therapist, a chiropractor, a healthcare provider, or other person giving the workout instructions). In some cases, the instructions may be described or demonstrated by the person giving the instructions in the video, described by a person different than the persons demonstrating the workout instructions, or any combination thereof. In some embodiments, a workout video block may include instructions provided by a machine generated character configured to describe or demonstrate workout instructions (e.g., an avatar). In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout. In some embodiments, workout video blocks in the same group (e.g., family, block type, set, stream, or other groups) may be provided by the same instructor (human, or machine generated). For example, a user may choose any particular instructor for any workout video block (every instructor provides instructions for all the workout sessions available to the user). In some cases, specific instructors (human, or machine generated) may provide specific workout instructions. For example, some instructors may only give instructions for specific body-regions (e.g., legs, arms, etc.), for specific level of difficulty, for specific workout type (e.g., warm-up, cool down, cardio, etc.), or other specific workout instructions.” [0062]
Example of avatar and video where avatar looks like (matching human body model) the user, and video with the same group (comparable human body models)….
“In some embodiments, a workout video block may include instructions provided by a human instructor (e.g., a coach, a trainer, a physical therapist, a chiropractor, a healthcare provider, or other person giving the workout instructions). In some cases, the instructions may be described or demonstrated by the person giving the instructions in the video, described by a person different than the persons demonstrating the workout instructions, or any combination thereof. In some embodiments, a workout video block may include instructions provided by a machine generated character configured to describe or demonstrate workout instructions (e.g., an avatar). In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout. In some embodiments, workout video blocks in the same group (e.g., family, block type, set, stream, or other groups) may be provided by the same instructor (human, or machine generated). For example, a user may choose any particular instructor for any workout video block (every instructor provides instructions for all the workout sessions available to the user). In some cases, specific instructors (human, or machine generated) may provide specific workout instructions. For example, some instructors may only give instructions for specific body-regions (e.g., legs, arms, etc.), for specific level of difficulty, for specific workout type (e.g., warm-up, cool down, cardio, etc.), or other specific workout instructions.” [0062]
Workout video with avatar (human body model) that looks like the user…
“…In some embodiments, a workout video block may include instructions provided by a machine generated character configured to describe or demonstrate workout instructions (e.g., an avatar). In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout…” [0062]
Video based on user profile information…
“Selection component 130 may be configured to select a first workout video block from the collection of video blocks. In some cases, selection of the first video block may be based on one or more of the user profile information, the user preference, information obtained from sensors 104, the groupings of the workout video blocks (e.g., body-region), workout intensity level, information obtained from other components of computing environment 100, or any combination thereof. For example, a first workout video may be selected based on one or more of the fitness goal of the user, a fitness level of the user, exercise constraints, health information, medical information, or other user profile attributes (described above)…” [0069]
User profiles including physiological information with fitness information and storage (database), therefore fitness database…
“In some embodiments, user profile component 124 may be configured to obtain one or more user profiles or user other information associated with users of computing environment 100. The one or more user profiles or user information may include information located in one or more of the client computing platforms 102, external resources 106, sensors 104, storage 115, or other locations within or outside computing environment 100 (e.g., websites, web platforms, servers, storage mediums, cloud storage, etc.). The user profiles may include one or more of user profile attributes, for example, information identifying users (e.g., a username, a number, an identifier, or other identifying information), security login information (e.g., a login code or password), account information, subscription information, health information, medical information (e.g., medical history, medications, etc.), physiological information (e.g., height, weight, age, gender, etc.), fitness information (e.g., fitness level, fitness achievements, etc.), restrictions (e.g., exercise constraint), fitness goals, physiological information, relationship information (e.g., information related to relationships between users in the computing environment 100), usage information, demographic information, history, client computing platforms associated with a user, or other information related to users. In some embodiments, user profile component 124 may be configured to access websites, web platforms, servers, storage mediums, or other locations from where user profiles may be accessed, obtained, retrieved, or requested in response to requests from users, components within or outside computing environment 100, or other requests. For instance, third-party API's for fitness trackers, networked scales, or networked fitness equipment may be accessed to retrieve metrics by which the profiles are enhanced. Profiles may include user feedback on particular exercises and instructors, as well as user constraints, like indications that certain body areas are susceptible or subject to injury. These values may be referenced when composing automatically workouts, e.g., embodiments may match an injured body area to a body area of workout videos and in response select corresponding, e.g., lower, level of intensity of video block.” [0063]
See Human Body Model below.
See Match below.
determining fitness regimen information for the user to be recommended based on fitness regimen information of a comparable user associated with the matching human body model.
Detected features to recommend workouts (determining fitness regimen) using features cluster (comparable user)…
“…Some embodiments may then use these detected features and clusters to recommend workouts for other users. For example, some embodiments may receive a request for workout from a given user, determine which cluster most closely matches that given user, and then select a workout for that user that includes the futures detected among the users in that cluster within their workouts.” [0123]
“Some embodiments may suggest trainers or friends for a user to work out with. Some embodiments may cluster users and trainers according to various criteria, for example, attributes of user profiles, like goals or workout patterns. For instance, some embodiments may model users as feature vectors, with user profile attributes like workout goals, performance, timing, and feedback being mapped to scalars of the vectors. Some embodiments may cluster the vectors with a DBSCAN algorithm and suggesting pairings. Or some embodiments may rank pairings based on Euclidian distance in the vector space, e.g., suggesting to a user the five closest other users or trainers.” [0138]
Human Body Model
King et al. teaches avatar and video as well as profile. The do not specifically teach human body model.
Kaleal, III et al. also in the business of avatar and profile teaches:
Example of avatar and
“This avatar visualization system allows a user to dynamically pick and choose different health and fitness programs and/or change different variables of a health and fitness program and see how the user would appear in the future based on the selected health and fitness program and/or the different variables. Accordingly, a user can select a health and fitness program that will cause the user to achieve an optimally desired appearance. For example, as the user selects different health and fitness programs and/or can changes variables of a selected health and fitness program, the avatar visualization system can dynamically adapt the appearance of an avatar presented to the user that corresponds to a predicted visualization of how the user will appear based on completion and adherence to the different health and fitness or the health and fitness program with the respectively chosen variables. As a result, the user can select a specific health and fitness program based on how it will affect the user's appearance.” [0039]
Video…
“In yet another aspect, physical and physiological activity data about a user corresponding to movement/motion and appearance of the user 102 can be captured by client device 106. For example, client device 106 can include a visual capture device 110 such as a still image camera, a video camera, or a three dimensional camera/scanner configured to capture image and/or video data of the user 102. According to this example, client device 106 can collect video and still images of the user 102 as the user performs an activity, task, or routine (e.g., a workout routine). The image data can be analyzed using pattern recognition to determine whether the user's movement corresponds to model movement metrics for the activity, task or routine. For instance, while performing a fitness routine such as a yoga or dance routine, image data captured by visual capture device 110 can be processed and analyzed (e.g., in real-time) to determine whether the user is executing the correct movements/poses and using proper form.” [0044]
Example of 504 and human body…
“In an aspect, a user can establish a profile with avatar guidance system 200 that includes a variety of personal information related to the user and the user's usage of avatar guidance system 200. For example, when employing avatar guidance system 200 for fitness and health related purposes, a user can be present with interface 500 to facilitate establishing a user profile and entering various personal information related to the user's health and fitness profile. For instance, interface 500 include can information section 502 that facilitates receiving user input regarding the user's physical profile, the user's physical limitations, and the user's dietary restrictions. Interface 500 can also include section 504 that presents an interactive pictorial representation of a human with the various muscle groups displayed. In an aspect, using this section the user can select body parts and/or muscle groups to indicate where the user has injuries and/or physical limitations.” [0148]
My profile with physical profiles and human body model…
PNG
media_image1.png
428
678
media_image1.png
Greyscale
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of King et al. the ability to relate a human body model with a profile as taught by Kaleal, III et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by King et al. who also teaches profile related to avatar and video as models.
Match
The combined references teach avatar. They also teach fitness database. They do not teach match.
Boker et al. also in the business of avatar teaches:
Match user’s avatar (user’s human body model) to avatar in inventory (database)….
“The attributes of the user's avatar received in response to the query may be matched to attributes of automated or un-manned avatars in the inventory or any other similar database. In determining whether a match exists between the attributes of the user's avatar and any of the automated avatars, several factors and/or pre-defined matching criteria may be considered. Examples of factors or criteria may include: which attributes of the user's avatar may be used in the matching process; a predetermined number of attributes may need to be matched or substantially matched to select the automated avatar; what constitutes a match; certain attributes of the user's avatar may be assigned a higher priority or weight that other attributes for matching purposes; and any other criteria to facilitate selecting an automated avatar to effectively interact with the user's avatar and enhance the user's experience. If a match is determined to exist based on the matching criteria, then one or more matched automated avatars from the inventory of automated avatars may be selected.” [0022]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to match avatars as taught by Boker et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Boker et al. who also teaches the benefits of matching avatars to enhance user’s experience.
Regarding claim 2
The recommendation method according to claim 1, wherein the determining fitness regimen information for the user to be recommended based on the fitness regimen information of the comparable user associated with the matching human body model comprises:
displaying fitness effect information of the comparable user associated with the matching human body model and corresponding fitness regimen information of the fitness effect information to the user to be recommended; and
[No Patentable Weight is given to non-functional descriptive claim language of “ displaying fitness effect information of the comparable user associated with the matching human body model and corresponding fitness regimen information of the fitness effect information to the user to be recommended” as this is just displaying information.]
King et al. teaches:
Display workout video (fitness effect information)…
“…For example, in some embodiments, communication component 140 causes a user interface to display the selected workout video block. In some cases, communications component 140 may be configured to communicate other information related to the selected workout video block (e.g., description, reviews, ratings, etc.). In some cases, communications component 140 may be configured to send other information to the user. For example, the user may receive promotions, health tips, workout tips, reminders (e.g., it has been “a number of days” since your last workout), and/or other information.” [0084]
determining the fitness regimen information of the user to be recommended based on a selection of the fitness effect information and the corresponding fitness regimen information by the user to be recommended.
Instructions (determining) physical activities (fitness regimen information) for (based on) strengthening muscles, weight loss, etc. (effect information)…
“Access component 120 may be configured to access a collection of workout video blocks. In some embodiments, a workout video block is a video containing one or more of a portion of a workout, an exercise, a yoga pose, training, a warm-up, aerobics, a dance, a routine, a drill, other types of physical activities, or any combination thereof. In some cases, a workout video block may include instructions of physical activities for the cardiovascular system, strengthening muscles, weight loss, to help enhance or maintain physical fitness or overall health and wellness. A workout video block may have a duration of about three minutes, or in some cases, an integral multiple of some quanta, like 1 minute, to facilitate dynamic composition. In some cases, a workout video block may have a duration of less than three minutes. In some cases, a workout video block may have a duration of more than three minutes. In some embodiments, a given individual workout video block may be the smallest video segment that can be provided to a user. For example, an individual workout video block may include one exercise.” [0049]
Regarding claim 3
The recommendation method according to claim 1, wherein the determining fitness regimen information for the user to be recommended based on the fitness regimen information of the comparable user associated with the matching human body model comprises:
displaying a plurality of fitness effect information of a target part associated with the matching human body model to the user to be recommended, training periods and training intensities corresponding to the plurality of fitness effect information, according to the target part selected by the user to be recommended; and
[No Patentable Weight is given to non-functional descriptive claim language of “displaying a plurality of fitness effect information of a target part associated with the matching human body model to the user to be recommended, training periods and training intensities corresponding to the plurality of fitness effect information, according to the target part selected by the user to be recommended;” as this is just displaying information.]
King et al. teaches:
Display workout video (fitness effect information)…
“…For example, in some embodiments, communication component 140 causes a user interface to display the selected workout video block. In some cases, communications component 140 may be configured to communicate other information related to the selected workout video block (e.g., description, reviews, ratings, etc.). In some cases, communications component 140 may be configured to send other information to the user. For example, the user may receive promotions, health tips, workout tips, reminders (e.g., it has been “a number of days” since your last workout), and/or other information.” [0084]
Video (displaying) with legs, chest, back (target part)…
“In some embodiments, the selection of video blocks in a sequence is based on both a workout stream, the location of the user in the workout stream, and real-time feedback. For instance, a workout stream may specify a low-intensity warmup, a high-intensity warmup, legs, chest, back, arms, cardio, legs, chest, back, arms, cardio, legs, chest, back, arms, cardio, and a low-intensity cool down. Within each of these stages, each of which may correspond to a selection for a video block, some embodiments may select a video block consistent with the stage based on real-time feedback. For instance, after arms, the user may indicate they are overly tired via a native application, or a heart-rate monitor may indicate a heart rate above a threshold. In response, for the next stage, cardio, some embodiments may select a lower level of intensity than would have otherwise been choses, dynamically selecting a video block while staying within the confines of the stream to have a consistent workout sequence that is tailored to their experience. Variants are described below in which a gradient descent is used to train a model for selecting subsequent video blocks, workouts, or workout plans based on things like user preferences, injuries, and patterns in previous user feedback, and the like. Further, some embodiments may achieve this with a server architecture designed to serve a relatively large number of users bandwidth intensive video feeds.” [0032]
determining, based on target fitness effect information selected from the plurality of fitness effect information by the user to be recommended, a training period and a training intensity corresponding to the target fitness effect information as the fitness regimen information.
Example of low and high intensity (training intensity)…
“In some embodiments, the selection of video blocks in a sequence is based on both a workout stream, the location of the user in the workout stream, and real-time feedback. For instance, a workout stream may specify a low-intensity warmup, a high-intensity warmup, legs, chest, back, arms, cardio, legs, chest, back, arms, cardio, legs, chest, back, arms, cardio, and a low-intensity cool down. Within each of these stages, each of which may correspond to a selection for a video block, some embodiments may select a video block consistent with the stage based on real-time feedback. For instance, after arms, the user may indicate they are overly tired via a native application, or a heart-rate monitor may indicate a heart rate above a threshold. In response, for the next stage, cardio, some embodiments may select a lower level of intensity than would have otherwise been choses, dynamically selecting a video block while staying within the confines of the stream to have a consistent workout sequence that is tailored to their experience. Variants are described below in which a gradient descent is used to train a model for selecting subsequent video blocks, workouts, or workout plans based on things like user preferences, injuries, and patterns in previous user feedback, and the like. Further, some embodiments may achieve this with a server architecture designed to serve a relatively large number of users bandwidth intensive video feeds.” [0032]
Instructions for physical activities (recommended target fitness) Workout period of time (training period)…
“Access component 120 may be configured to access a collection of workout video blocks. In some embodiments, a workout video block is a video containing one or more of a portion of a workout, an exercise, a yoga pose, training, a warm-up, aerobics, a dance, a routine, a drill, other types of physical activities, or any combination thereof. In some cases, a workout video block may include instructions of physical activities for the cardiovascular system, strengthening muscles, weight loss, to help enhance or maintain physical fitness or overall health and wellness. A workout video block may have a duration of about three minutes, or in some cases, an integral multiple of some quanta, like 1 minute, to facilitate dynamic composition. In some cases, a workout video block may have a duration of less than three minutes. In some cases, a workout video block may have a duration of more than three minutes. In some embodiments, a given individual workout video block may be the smallest video segment that can be provided to a user. For example, an individual workout video block may include one exercise.” [0049]
Regarding claim 8
The recommendation method according to claim 1, wherein the determining, based on the physiological feature information of the user to be recommended, the matching human body model for the physiological feature information from the plurality of comparable human body models comprises:
determining the matching human body model from the plurality of comparable human body models based on the physiological feature information and living habit information of the user to be recommended.
King et al. teaches:
Instructions (determining) physical activities (fitness regimen information) for (based on) strengthening muscles, weight loss, etc. (effect information)…
“Access component 120 may be configured to access a collection of workout video blocks. In some embodiments, a workout video block is a video containing one or more of a portion of a workout, an exercise, a yoga pose, training, a warm-up, aerobics, a dance, a routine, a drill, other types of physical activities, or any combination thereof. In some cases, a workout video block may include instructions of physical activities for the cardiovascular system, strengthening muscles, weight loss, to help enhance or maintain physical fitness or overall health and wellness. A workout video block may have a duration of about three minutes, or in some cases, an integral multiple of some quanta, like 1 minute, to facilitate dynamic composition. In some cases, a workout video block may have a duration of less than three minutes. In some cases, a workout video block may have a duration of more than three minutes. In some embodiments, a given individual workout video block may be the smallest video segment that can be provided to a user. For example, an individual workout video block may include one exercise.” [0049]
Habits such as drink water…
“Some embodiments may also include video blocks that pertain to things other than exercises. For example, some embodiments may use the techniques described above to infer that particular habits would be helpful for the user and select videos advocating for and educating it about those habits. For example, some embodiments may follow a workout with the video block instructing the user to drink 64 ounces of water, to stretch, to engage in particular nutritional patent practices.” [0104]
Sleeping behavior (living habit information)…
“The third-party application program interface servers 928 are, in some cases, any of the various types of servers described above by which events and data relating to those events may be obtained from third-party applications, such as airline or hotel reservation systems, fitness-facility member management systems, third-party application program interface servers that expose data gathered by Internet of things appliances 930 or by wearable computing devices 926, and the like. In some embodiments, the Internet of things appliances 930 are home-based Internet of things appliances, like the examples described above, such as smart lights, network-connected scales, smart thermostats, smart refrigerators, security systems configured to indicate whether the user is present, smart beds or pillows configured to indicate a user sleeping behavior, and the like. In some embodiments, the Internet of things appliances 930 are appliances in a fitness facility, such as networked gym equipment having actuators by which intensity or difficulty of the workout equipment may be modulated and sensors by which a user's use of the equipment may be monitored, including biometric sensors and sensors indicative of movement of the equipment, like tachometers, accelerometers, strain gages, and the like. In some embodiments, these Internet of things appliances 930 may also expose application program interfaces, either directly to the prescription engine 922 or via one of the third-party API servers 928, by which actuators of the Internet of things appliances may be adjusted, for instance, responsive to a command changing a set point, content may be sent for presentation on the appliance, and by which data gathered by sensors of the Internet of things appliances 930 may be interrogated.” [0176]
Regarding claim 9
The recommendation method according to claim 8, wherein the determining the matching human body model from the plurality of comparable human body models based on the physiological feature information and the living habit information of the user to be recommended comprises:
determining a plurality of candidate human body models from the plurality of comparable human body models based on the physiological feature information of the user to be recommended; and
King et al. teaches:
Suggest trainers or friends (recommend) by cluster users (plurality of candidate) based on user profiles (human body model)…
“Some embodiments may suggest trainers or friends for a user to work out with. Some embodiments may cluster users and trainers according to various criteria, for example, attributes of user profiles, like goals or workout patterns. For instance, some embodiments may model users as feature vectors, with user profile attributes like workout goals, performance, timing, and feedback being mapped to scalars of the vectors. Some embodiments may cluster the vectors with a DBSCAN algorithm and suggesting pairings. Or some embodiments may rank pairings based on Euclidian distance in the vector space, e.g., suggesting to a user the five closest other users or trainers.” [0138]
determining the matching human body model from the plurality of candidate human body models based on the living habit information of the user to be recommended;
Profile (human body model) with behavior (habit)…
“In some embodiments, some of the user profile information may be obtained through accessing the user profile on one or more social media sites, or the user's online presence (instead of asking the user questions, user profile component 124 may be able to extract information about the user's behavior, past activities, preferences, user's ratings of other workouts, likes and dislikes, etc.). This operation may be performed by user profile component 124, or other components within or outside of computing environment 100. User profile component 124 may be configured to collect and store data about the user obtained from one or more social media sites, or from the user's online presence (e.g., products viewed, or bought online, viewing times, rating, behavior, etc.)” [0068]
or
determining a plurality of candidate human body models from the plurality of comparable human body models based on the living habit information of the user to be recommended; and
[No Patentable Weight is given to alternative or contingent claim language where only one limitation is required.]
determining the matching human body model from the plurality of candidate human body models based on the physiological feature information of the user to be recommended.
[No Patentable Weight is given to alternative or contingent claim language where only one limitation is required.]
Regarding claim 10
The recommendation method according to claim 8, wherein the determining the matching human body model from the plurality of comparable human body models based on the physiological feature information and the living habit information of the user to be recommended comprises:
determining the matching human body model from the plurality of comparable human body models, based on health condition information of the user to be recommended.
King et al. teaches:
User profile with health information…
“In some embodiments, user profile component 124 may be configured to obtain one or more user profiles or user other information associated with users of computing environment 100. The one or more user profiles or user information may include information located in one or more of the client computing platforms 102, external resources 106, sensors 104, storage 115, or other locations within or outside computing environment 100 (e.g., websites, web platforms, servers, storage mediums, cloud storage, etc.). The user profiles may include one or more of user profile attributes, for example, information identifying users (e.g., a username, a number, an identifier, or other identifying information), security login information (e.g., a login code or password), account information, subscription information, health information, medical information (e.g., medical history, medications, etc.), physiological information (e.g., height, weight, age, gender, etc.), fitness information (e.g., fitness level, fitness achievements, etc.), restrictions (e.g., exercise constraint), fitness goals, physiological information, relationship information (e.g., information related to relationships between users in the computing environment 100), usage information, demographic information, history, client computing platforms associated with a user, or other information related to users. In some embodiments, user profile component 124 may be configured to access websites, web platforms, servers, storage mediums, or other locations from where user profiles may be accessed, obtained, retrieved, or requested in response to requests from users, components within or outside computing environment 100, or other requests.” [0063]
Profiles to identify groups of users similar (comparable) to one another…
“In some embodiments, a machine-learning model may be trained to select workouts based on a user's goal. For example, in some cases, a training set may include a goal set by previous users, profiles of those users, workouts by those users, and an indication of whether the users achieve their goals. Some embodiments may filter the training set according to whether users satisfy their stated goals. Some embodiments may cluster users (e.g., with a density based clustering algorithm, like DB-SCAN) according to profiles to identify groups of users who are similar to one another, for example, of similar profiles and have sent similar goals. In some cases, some embodiments may then detect features of workouts within each of the clusters, for example, patterns in chosen workouts associated with meeting the goal for those in the cluster. For instance, for each cluster, embodiments may train a decision tree to classify users as likely to meet their goal based on workout history. Some embodiments may then use these detected features and clusters to recommend workouts for other users. For example, some embodiments may receive a request for workout from a given user, determine which cluster most closely matches that given user, and then select a workout for that user that includes the futures detected among the users in that cluster within their workouts.” [0123]
Regarding claim 11
The recommendation method according to claim 10, wherein the determining the matching human body model from the plurality of comparable human body models based on the health condition information of the user to be recommended comprises:
determining a plurality of candidate human body models from the plurality of comparable human body models based on the physiological feature information of the user to be recommended; and
King et al. teaches:
Suggest trainers or friends (recommend) by cluster users (plurality of candidate) based on user profiles (human body model)…
“Some embodiments may suggest trainers or friends for a user to work out with. Some embodiments may cluster users and trainers according to various criteria, for example, attributes of user profiles, like goals or workout patterns. For instance, some embodiments may model users as feature vectors, with user profile attributes like workout goals, performance, timing, and feedback being mapped to scalars of the vectors. Some embodiments may cluster the vectors with a DBSCAN algorithm and suggesting pairings. Or some embodiments may rank pairings based on Euclidian distance in the vector space, e.g., suggesting to a user the five closest other users or trainers.” [0138]
determining the matching human body model from the plurality of candidate human body models based on the living habit information and the health condition information of the user to be recommended;
“In some embodiments, user profile component 124 may be configured to obtain one or more user profiles or user other information associated with users of computing environment 100. The one or more user profiles or user information may include information located in one or more of the client computing platforms 102, external resources 106, sensors 104, storage 115, or other locations within or outside computing environment 100 (e.g., websites, web platforms, servers, storage mediums, cloud storage, etc.). The user profiles may include one or more of user profile attributes, for example, information identifying users (e.g., a username, a number, an identifier, or other identifying information), security login information (e.g., a login code or password), account information, subscription information, health information, medical information (e.g., medical history, medications, etc.), physiological information (e.g., height, weight, age, gender, etc.), fitness information (e.g., fitness level, fitness achievements, etc.), restrictions (e.g., exercise constraint), fitness goals, physiological information, relationship information (e.g., information related to relationships between users in the computing environment 100), usage information, demographic information, history, client computing platforms associated with a user, or other information related to users. In some embodiments, user profile component 124 may be configured to access websites, web platforms, servers, storage mediums, or other locations from where user profiles may be accessed, obtained, retrieved, or requested in response to requests from users, components within or outside computing environment 100, or other requests.” [0063]
or
determining a plurality of candidate human body models from the plurality of comparable human body models based on the living habit information and the health condition information of the user to be recommended; and
[No Patentable Weight is given to alternative or contingent claim language where only one limitation is required.]
determining the matching human body model from the plurality of candidate human body models based on the physiological feature information of the user to be recommended.
[No Patentable Weight is given to alternative or contingent claim language where only one limitation is required.]
Regarding claim 12
The recommendation method according to claim 1, further comprising:
obtaining physiological feature information after training of the user to be recommended after training for a preset period of time based on the fitness regimen information;
King et al. teaches:
Feedback of action on prescription acts (recommendations of fitness acts).…
“Further, in some embodiments, the prescription engine implements a feedback loop, where the action a user takes on any given prescription acts as input data to further influence future decision making by the prescription engine. By taking a machine learning approach, some embodiments improve the accuracy of prescriptions over time.” [0030]
Instructions for physical activities (recommended target fitness) Workout period of time (training period)…
“Access component 120 may be configured to access a collection of workout video blocks. In some embodiments, a workout video block is a video containing one or more of a portion of a workout, an exercise, a yoga pose, training, a warm-up, aerobics, a dance, a routine, a drill, other types of physical activities, or any combination thereof. In some cases, a workout video block may include instructions of physical activities for the cardiovascular system, strengthening muscles, weight loss, to help enhance or maintain physical fitness or overall health and wellness. A workout video block may have a duration of about three minutes, or in some cases, an integral multiple of some quanta, like 1 minute, to facilitate dynamic composition. In some cases, a workout video block may have a duration of less than three minutes. In some cases, a workout video block may have a duration of more than three minutes. In some embodiments, a given individual workout video block may be the smallest video segment that can be provided to a user. For example, an individual workout video block may include one exercise.” [0049]
generating a human body model after training based on the physiological feature information after training;
User has advanced to next stage and select (generating) second video block (human body model) based on feedback and after first video block….
“At operation 912 a second workout video block may be selected from the collection. In some cases, a session record may be updated to indicate the user has advanced to a next stage of a workout stream, e.g., from legs to back. The second video block may be selected based on the feedback, the intensity of the second workout video block, a current state of the user in a workout stream, and a body-region grouping of the second video block. In some embodiments, operation 912 may be performed by a selection component the same as or similar to selection component 130 (shown in FIG. 1 and described herein).” [0115]
determining a matching human body model for the human body model after training from the plurality of comparable human body models based on the human body model after training; and
Workout video with avatar (human body model) that looks like the user
“…In some embodiments, a workout video block may include instructions provided by a machine generated character configured to describe or demonstrate workout instructions (e.g., an avatar). In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout…” [0062]
Video based on user profile information…
“Selection component 130 may be configured to select a first workout video block from the collection of video blocks. In some cases, selection of the first video block may be based on one or more of the user profile information, the user preference, information obtained from sensors 104, the groupings of the workout video blocks (e.g., body-region), workout intensity level, information obtained from other components of computing environment 100, or any combination thereof. For example, a first workout video may be selected based on one or more of the fitness goal of the user, a fitness level of the user, exercise constraints, health information, medical information, or other user profile attributes (described above)…” [0069]
determining new fitness regimen information for the user to be recommended based on fitness regimen information associated with the matching human body model for the human body model after training.
Second video block with workout (new fitness regimen information)…
“At operation 912 a second workout video block may be selected from the collection. In some cases, a session record may be updated to indicate the user has advanced to a next stage of a workout stream, e.g., from legs to back. The second video block may be selected based on the feedback, the intensity of the second workout video block, a current state of the user in a workout stream, and a body-region grouping of the second video block. In some embodiments, operation 912 may be performed by a selection component the same as or similar to selection component 130 (shown in FIG. 1 and described herein).” [0115]
Claims 4, 6, and 13-15 are rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (9) above in further view of Pub. No. US 2023/0115028 to Arunachala.
Regarding claim 4
The recommendation method according to claim 1, wherein the determining, based on the physiological feature information of the user to be recommended, the matching human body model for the physiological feature information from the plurality of comparable human body models comprises:
generating a user human body model of the user to be recommended based on the physiological feature information of the user to be recommended; and
King et al. teaches:
Example of avatar and video (matching human body model) and video with the same group (comparable human body models)….
“In some embodiments, a workout video block may include instructions provided by a human instructor (e.g., a coach, a trainer, a physical therapist, a chiropractor, a healthcare provider, or other person giving the workout instructions). In some cases, the instructions may be described or demonstrated by the person giving the instructions in the video, described by a person different than the persons demonstrating the workout instructions, or any combination thereof. In some embodiments, a workout video block may include instructions provided by a machine generated character configured to describe or demonstrate workout instructions (e.g., an avatar). In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout. In some embodiments, workout video blocks in the same group (e.g., family, block type, set, stream, or other groups) may be provided by the same instructor (human, or machine generated). For example, a user may choose any particular instructor for any workout video block (every instructor provides instructions for all the workout sessions available to the user). In some cases, specific instructors (human, or machine generated) may provide specific workout instructions. For example, some instructors may only give instructions for specific body-regions (e.g., legs, arms, etc.), for specific level of difficulty, for specific workout type (e.g., warm-up, cool down, cardio, etc.), or other specific workout instructions.” [0062]
determining the matching human body model based on a cosine similarity between the user human body model and the plurality of comparable human body models.
Density based clustering (degree of similarity) with similar profiles (body models)…
“…Some embodiments may cluster users (e.g., with a density based clustering algorithm, like DB-SCAN) according to profiles to identify groups of users who are similar to one another, for example, of similar profiles and have sent similar goals. In some cases, some embodiments may then detect features of workouts within each of the clusters, for example, patterns in chosen workouts associated with meeting the goal for those in the cluster. For instance, for each cluster, embodiments may train a decision tree to classify users as likely to meet their goal based on workout history. Some embodiments may then use these detected features and clusters to recommend workouts for other users. For example, some embodiments may receive a request for workout from a given user, determine which cluster most closely matches that given user, and then select a workout for that user that includes the futures detected among the users in that cluster within their workouts.” [0123]
Profile with physiological information…
“…The user profiles may include one or more of user profile attributes, for example, information identifying users (e.g., a username, a number, an identifier, or other identifying information), security login information (e.g., a login code or password), account information, subscription information, health information, medical information (e.g., medical history, medications, etc.), physiological information (e.g., height, weight, age, gender, etc.), fitness information (e.g., fitness level, fitness achievements, etc.), restrictions (e.g., exercise constraint), fitness goals, physiological information, relationship information (e.g., information related to relationships between users in the computing environment 100), usage information, demographic information, history, client computing platforms associated with a user, or other information related to users. In some embodiments, user profile component 124 may be configured to access websites, web platforms, servers, storage mediums, or other locations from where user profiles may be accessed, obtained, retrieved, or requested in response to requests from users, components within or outside computing environment 100, or other requests…” [0063]
Cosine Similarity
The combined references teach model and similarity. They do not teach cosine similarity.
Arunachala also in the business of model and similarity teaches:
Avatar features and definitions (model) and select best-matching avatar features from library using lowest cosine distance…
“The avatar features and characteristic definitions 1210 and 1212 can be provided to construct avatar module 1214, which can select best-matching avatar features from avatar library 1216. For example, construct avatar module 1214 can use a model trained to map such avatar features into a semantic space of the avatar library and select closest (e.g., lowest cosine distance) avatar feature from the library also mapped into the semantic space. In various cases, the construct avatar module 1214 can select avatar features from the avatar library that are created with the corresponding characteristics 1212 or can set parameters of the obtained avatar features according to the characteristics 1212. With the correct avatar features obtained, having the correct characteristics, the construct avatar module 1214 can generate a resulting avatar 1218.” [0081]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use cosine distance as taught by Arunachala since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Arunachala who also teaches the benefits of cosine distance for matching avatars.
Regarding claim 6
The recommendation method according to claim 4, wherein the determining the matching human body model based on the degree of similarity between the user human body model and the plurality of comparable human body models comprises:
proportionally scaling the user human body model to generate a scaled user human body model which matches the size of the plurality of comparable human body models; and
King et al. teaches:
Example of avatar and a video (scaled human body model)…
“…In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout. In some embodiments, workout video blocks in the same group (e.g., family, block type, set, stream, or other groups) may be provided by the same instructor (human, or machine generated)…” [0062]
determining a matching human body model based on the cosine similarity between the scaled user human body model and the comparable human body models.
Avatar looks like (degree of similarity) the user…
“…In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout. In some embodiments, workout video blocks in the same group (e.g., family, block type, set, stream, or other groups) may be provided by the same instructor (human, or machine generated)…” [0062] Inherent with avatar and video is scaled.
Cosine Similarity
The combined references teach model and similarity. They do not teach cosine similarity.
Arunachala also in the business of model and similarity teaches:
Avatar features and definitions (model) and select best-matching avatar features from library using lowest cosine distance…
“The avatar features and characteristic definitions 1210 and 1212 can be provided to construct avatar module 1214, which can select best-matching avatar features from avatar library 1216. For example, construct avatar module 1214 can use a model trained to map such avatar features into a semantic space of the avatar library and select closest (e.g., lowest cosine distance) avatar feature from the library also mapped into the semantic space. In various cases, the construct avatar module 1214 can select avatar features from the avatar library that are created with the corresponding characteristics 1212 or can set parameters of the obtained avatar features according to the characteristics 1212. With the correct avatar features obtained, having the correct characteristics, the construct avatar module 1214 can generate a resulting avatar 1218.” [0081]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use cosine distance as taught by Arunachala since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Arunachala who also teaches the benefits of cosine distance for matching avatars.
Regarding claim 13
The recommendation method according to claim 1, wherein the determining, based on the physiological feature information of the user to be recommended, the matching human body model for the physiological feature information from the plurality of comparable human body models comprises:
generating a user feature vector based on the physiological feature information of the user to be recommended;
King et al. teaches:
Training set with profiles of users (physiological feature information)…
“In some embodiments, a machine-learning model may be trained to select workouts based on a user's goal. For example, in some cases, a training set may include a goal set by previous users, profiles of those users, workouts by those users, and an indication of whether the users achieve their goals. Some embodiments may filter the training set according to whether users satisfy their stated goals. Some embodiments may cluster users (e.g., with a density based clustering algorithm, like DB-SCAN) according to profiles to identify groups of users who are similar to one another, for example, of similar profiles and have sent similar goals. In some cases, some embodiments may then detect features of workouts within each of the clusters, for example, patterns in chosen workouts associated with meeting the goal for those in the cluster. For instance, for each cluster, embodiments may train a decision tree to classify users as likely to meet their goal based on workout history. Some embodiments may then use these detected features and clusters to recommend workouts for other users. For example, some embodiments may receive a request for workout from a given user, determine which cluster most closely matches that given user, and then select a workout for that user that includes the futures detected among the users in that cluster within their workouts.” [0123]
Example of predictive model a using vector…
“… In some cases, a predictive model (e.g., a vector of weights) may be calculated as a batch process run periodically. Some embodiments may construct the model by, for example, assigning randomly selected weights; calculating an error amount with which the model describes the historical data and a rates of change in that error as a function of the weights in the model in the vicinity of the current weight (e.g., a derivative, or local slope); and incrementing the weights in a downward (or error reducing) direction. In some cases, these steps may be iteratively repeated until a change in error between iterations is less than a threshold amount, indicating at least a local minimum, if not a global minimum. To mitigate the risk of local minima, some embodiments may repeat the gradient descent optimization with multiple initial random values to confirm that iterations converge on a likely global minimum error. Other embodiments may iteratively adjust other machine learning models to reduce the error function, e.g., with a greedy algorithm that optimizes for the current iteration. The resulting, trained model, e.g., a vector of weights or thresholds, may be stored in memory and later retrieved for application to new calculations on newly calculated aggregate estimates.” [0124]
determining a matching user from the plurality of comparable users based on a cosine similarity between the user feature vector and comparable feature vectors of the plurality of comparable users, the comparable feature vectors being generated based on physiological feature information of the comparable users; and
Cluster users based on user profiles and feature vectors…
“Some embodiments may suggest trainers or friends for a user to work out with. Some embodiments may cluster users and trainers according to various criteria, for example, attributes of user profiles, like goals or workout patterns. For instance, some embodiments may model users as feature vectors, with user profile attributes like workout goals, performance, timing, and feedback being mapped to scalars of the vectors. Some embodiments may cluster the vectors with a DBSCAN algorithm and suggesting pairings. Or some embodiments may rank pairings based on Euclidian distance in the vector space, e.g., suggesting to a user the five closest other users or trainers.” [0138]
See Cosine Similarity below.
determining a comparable human body model of the matching user as the matching human body model.
Rank pairing of closes other users…
“Some embodiments may suggest trainers or friends for a user to work out with. Some embodiments may cluster users and trainers according to various criteria, for example, attributes of user profiles, like goals or workout patterns. For instance, some embodiments may model users as feature vectors, with user profile attributes like workout goals, performance, timing, and feedback being mapped to scalars of the vectors. Some embodiments may cluster the vectors with a DBSCAN algorithm and suggesting pairings. Or some embodiments may rank pairings based on Euclidian distance in the vector space, e.g., suggesting to a user the five closest other users or trainers.” [0138]
Cosine Similarity
The combined references teach model and similarity. They do not teach cosine similarity.
Arunachala also in the business of model and similarity teaches:
Avatar features and definitions (model) and select best-matching avatar features from library using lowest cosine distance…
“The avatar features and characteristic definitions 1210 and 1212 can be provided to construct avatar module 1214, which can select best-matching avatar features from avatar library 1216. For example, construct avatar module 1214 can use a model trained to map such avatar features into a semantic space of the avatar library and select closest (e.g., lowest cosine distance) avatar feature from the library also mapped into the semantic space. In various cases, the construct avatar module 1214 can select avatar features from the avatar library that are created with the corresponding characteristics 1212 or can set parameters of the obtained avatar features according to the characteristics 1212. With the correct avatar features obtained, having the correct characteristics, the construct avatar module 1214 can generate a resulting avatar 1218.” [0081]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use cosine distance as taught by Arunachala since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Arunachala who also teaches the benefits of cosine distance for matching purposes.
Regarding claim 14
The recommendation method according to claim 13, wherein the generating the user feature vector based on the physiological feature information of the user to be recommended comprises:
generating the user feature vector based on at least one of living habit information of the user to be recommended and a weight of the living habit information, or health condition information of the user to be recommended and a weight of the health condition information, and
[No Patentable Weight is given to alternative or contingent claim language where only one limitation is required.]
King et al. teaches:
Vectors with user profiles…
“Some embodiments may suggest trainers or friends for a user to work out with. Some embodiments may cluster users and trainers according to various criteria, for example, attributes of user profiles, like goals or workout patterns. For instance, some embodiments may model users as feature vectors, with user profile attributes like workout goals, performance, timing, and feedback being mapped to scalars of the vectors. Some embodiments may cluster the vectors with a DBSCAN algorithm and suggesting pairings. Or some embodiments may rank pairings based on Euclidian distance in the vector space, e.g., suggesting to a user the five closest other users or trainers.” [0138]
Profiles may include health information…
“In some embodiments, user profile component 124 may be configured to obtain one or more user profiles or user other information associated with users of computing environment 100. The one or more user profiles or user information may include information located in one or more of the client computing platforms 102, external resources 106, sensors 104, storage 115, or other locations within or outside computing environment 100 (e.g., websites, web platforms, servers, storage mediums, cloud storage, etc.). The user profiles may include one or more of user profile attributes, for example, information identifying users (e.g., a username, a number, an identifier, or other identifying information), security login information (e.g., a login code or password), account information, subscription information, health information, medical information (e.g., medical history, medications, etc.), physiological information (e.g., height, weight, age, gender, etc.), fitness information (e.g., fitness level, fitness achievements, etc.), restrictions (e.g., exercise constraint), fitness goals, physiological information, relationship information (e.g., information related to relationships between users in the computing environment 100), usage information, demographic information, history, client computing platforms associated with a user, or other information related to users. In some embodiments, user profile component 124 may be configured to access websites, web platforms, servers, storage mediums, or other locations from where user profiles may be accessed, obtained, retrieved, or requested in response to requests from users, components within or outside computing environment 100, or other requests.” [0063]
Example of predictive model a using vector…
“… In some cases, a predictive model (e.g., a vector of weights) may be calculated as a batch process run periodically. Some embodiments may construct the model by, for example, assigning randomly selected weights; calculating an error amount with which the model describes the historical data and a rates of change in that error as a function of the weights in the model in the vicinity of the current weight (e.g., a derivative, or local slope); and incrementing the weights in a downward (or error reducing) direction. In some cases, these steps may be iteratively repeated until a change in error between iterations is less than a threshold amount, indicating at least a local minimum, if not a global minimum. To mitigate the risk of local minima, some embodiments may repeat the gradient descent optimization with multiple initial random values to confirm that iterations converge on a likely global minimum error. Other embodiments may iteratively adjust other machine learning models to reduce the error function, e.g., with a greedy algorithm that optimizes for the current iteration. The resulting, trained model, e.g., a vector of weights or thresholds, may be stored in memory and later retrieved for application to new calculations on newly calculated aggregate estimates.” [0124]
the physiological feature information of the user to be recommended and a weight of the physiological feature information, the comparable feature vector of the comparable user being generated based on at least one of living habit information of the comparable user and a weight of the living habit information, or health condition information of the comparable user and a weight of the health condition information, and physiological feature information of the comparable user and a weight of the physiological feature information.
Regarding claim 15
The recommendation method according to claim 14, wherein
the weight of the health condition information of the user to be recommended is greater than the weight of the living habit information of the user to be recommended, and the weight of the living habit information of the user to be recommended is greater than the weight of the physiological feature information of the user to be recommended; and
See Assign Weight below.
the weight of the health condition information of the comparable user is greater than the weight of the living habit information of the comparable user, and the weight of living habit information of the comparable user is greater than the weight of the physiological feature information of the comparable user.
See Assign Weight below.
Assign Weight
The combined references teach vector and weight. They do not explicitly teach weight for health condition greater than living habit information and greater than physiological feature information for a user and comparable user. However, one of ordinary skill in the art would recognize that weights can be assigned based on various criteria to achieve a desired outcome or priority.
It would have been obvious to one of ordinary skill in the art before the effective filing date of Applicant’s filing to modify the combined references with the knowledge available to such an artisan that weights can be assigned based on desired outcome or priorities. This would have been known work in the field of endeavor prompting variations of it in the same field based on use of weights and would provide predictable results.
Claim 5 is rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (10) above in further view of Pub. No. US 2018/0353836 to Li et al.
Regarding claim 5
The recommendation method according to claim 4, wherein the determining the matching human body model based on the cosine similarity between the user human body model and the plurality of comparable human body models comprises:
determining a comparable human body model with an overlap area greater than a threshold value with the user human body model as the matching human body model.
The combined references teach images. They do not teach overlap.
Li et al. also in the business of images teaches:
Overlay representing a upper and lower ranges of individuals and spanning the distance between (greater than) the upper and lower ranges…
“The key frame detector 230 may work in conjunction with the output generator 240 to provide the user with an opportunity to adjust the key frame for increased accuracy. The key frame including a representation of a reference position zone (e.g., an overlay representing a positional range of a human body at the key stage, etc.) corresponding to the key stage of the activity may be generated for output on a display device of a mobile device of the participant. In an example, the reference position zone may key be generated using a model for the stage of the activity. For example, the model may include upper and lower ranges for images of individuals engaged in the activity labeled as corresponding with the key stage and the reference position zone may be created by generating an overlay spanning the distance between the upper and the lower ranges of the images of the individuals engaged in the activity. The generated key frame including the representation of the reference zone position and a set of frames having timestamps between a start timestamp of the activity and an end timestamp for the activity may be transmitted (e.g., by the transceiver 215) for display on the display device. An input may be received indicating that a new frame has been selected for the key stage, and the new frame may be selected as the key frame. For example, the baseball player may be presented a display of the selected key frame with an overlay of a position of a model player at the key stage. The user may be able to scroll forward and backward through frames of the video stream and may select a frame the player feels is a better match to the position overlay. The frame selected by the player may then be used as the key frame for the key stage.” [0031]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to determine an overlap area as taught by Li et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Li et al. who teaches the advantages of ensuring an overlay covers upper and lower images of an individual.
Cosine Similarity
The combined references teach model and similarity. They do not teach cosine similarity.
Arunachala also in the business of model and similarity teaches:
Avatar features and definitions (model) and select best-matching avatar features from library using lowest cosine distance…
“The avatar features and characteristic definitions 1210 and 1212 can be provided to construct avatar module 1214, which can select best-matching avatar features from avatar library 1216. For example, construct avatar module 1214 can use a model trained to map such avatar features into a semantic space of the avatar library and select closest (e.g., lowest cosine distance) avatar feature from the library also mapped into the semantic space. In various cases, the construct avatar module 1214 can select avatar features from the avatar library that are created with the corresponding characteristics 1212 or can set parameters of the obtained avatar features according to the characteristics 1212. With the correct avatar features obtained, having the correct characteristics, the construct avatar module 1214 can generate a resulting avatar 1218.” [0081]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use cosine distance as taught by Arunachala since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Arunachala who also teaches the benefits of cosine distance for matching avatars.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (10) above in further view of Patent No. US 12004871 to Fazeli et al.
Regarding claim 7
The generation method according to claim 4, wherein the generating the user human body model of the user to be recommended based on the physiological feature information of the user to be recommended comprises:
generating a user current human body model of the user to be recommended based on the physiological feature information of the user to be recommended; and
King et al. teaches:
User may choose (generating) an avatar that looks like the user (current human body model)…
“…In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout. In some embodiments, workout video blocks in the same group (e.g., family, block type, set, stream, or other groups) may be provided by the same instructor (human, or machine generated)…” [0062] Inherent with avatar and video is scaled.
generating a user target human body model according to an adjustment of the user to be recommended for the user current human body model based on a fitness target;
Target profile (human body model) and prescriptions (recommendations)…
“Some embodiments mitigate some (and in some cases all) of the above-described issues with a system referred to as a “prescription engine” that, in some embodiments, guides a user through their fitness journey by leveraging resources, both physical and digital, for prescription at any given moment to advance them towards their health goals. It does this by responding to specific events (such as triggers) to activate prescriptions based on a user's profile and needs. Some implementations tell a user exactly what to do, how to do it, where to do it, and why they should be doing it at any second throughout the day when the prescription engine or determines such guidance relevant. As explained below, events activate prescriptions based on the target user's profile and needs.” [0029]
Where prescribe is fitness activities…
“Some aspects include a process to prescribe fitness-related activities responsive to events, the process including: receiving, with one or more processors, with a fitness prescription engine, an event indicative of a current or future state of a user, wherein: the user is associated with a mobile computing device upon which a native application executes; the native application is configured to send events to the fitness prescription engine via a network; and the fitness prescription engine is configured to prescribe fitness-related activities responsive to events for a user-base with a plurality of users including the user; determining, with one or more processors, with the fitness prescription engine, a fitness need of the user based on a user profile of the user, wherein: the fitness need is determined based on a fitness goal of the user in the user profile; and the fitness need is determined based on a previous fitness-related prescription in the user profile; determining, with one or more processors, with the fitness prescription engine, a current fitness-related prescription in response to both the fitness need and the event, wherein: determining the current fitness-related prescription comprises selecting a fitness resource from among a plurality of candidate fitness resources; and the selected fitness resource is designated in the current prescription as a fitness resource to be accessed by the user in accordance with the current prescription; and causing, with one or more processors, with the fitness prescription engine, the current fitness-related prescription to be presented to the user.” [0012]
See Target Body below.
the determining the matching human body model based on the degree of similarity between the user human body model and the plurality of comparable human body models comprises;
Avatar looks like (degree of similarity) the user…
“…In some embodiments, the user may choose an avatar from a list of avatars (e.g., avatar that looks like the user or an avatar that looks like a celebrity, etc.). In some embodiments, the user may upload an image (of themselves of someone else to be used in the creation of the avatar). In some cases, a workout video block may include a combination of instructions provided (described or demonstrated) by a human and a machine generated character. For example, a video may show a real person describing the workout and an avatar performing the workout. In some embodiments, workout video blocks in the same group (e.g., family, block type, set, stream, or other groups) may be provided by the same instructor (human, or machine generated)…” [0062] Inherent with avatar and video is scaled.
determining the matching human body model based on the cosine similarity between the user target human body model and the plurality of comparable human body models.
See Target Body below.
Target Body
The combined references teach body model. They do not teach target body model and similarity.
Fazeli et al. also in the business of body model teaches:
Target body model and measurements similar to another person…
“In other examples, a user may select a 2D image of a body of another person, such as a celebrity, and the disclosed implementations will utilize the image of that other body to determine a target body composition and to generate a predicted personalized 3D body model of the body of the user with body measurements similar to those of the body of the other person. For example, the selected or provided 2D image of the body of another person, such as a celebrity, may be processed to determine body composition of the body represented in the image and/or to identify the person in the image so that body measurements and body parameters of the body of that other person can be obtained from other sources. For example, if the selected image is an image of a body of a celebrity, the celebrity may be identified and body measurements and body parameters of the body of the celebrity obtained from one or more public sources. Based on the body measurements and body parameters of the body of the other person, the personalized 3D body model of the body of the user may be altered to generate a predicted personalized 3D body model of that user with body measurements that correspond to those of the body represented in the selected or provided image (e.g., the image of a celebrity).” (col. 4, lines 12-34)
“Still further, the disclosed implementations, using the current body measurements of the user and user selected predicted body measurements, referred to herein as target body measurements, may generate a body change journey that the user can follow that guides the user through nutrition, sleep, exercise, etc., so that the user can change their current body composition to the target body composition. Periodic check-ins with visual updates of the predicted and actual changes in body measurements may be provided to encourage the user, adjust the body change journey if necessary, and to keep the user motivated toward a selected goal/target.” (col. 4, lines 35-46)
Using plurality of bodies…
“Each silhouette 1154 representative of the body may then be processed to determine body traits or features of the human body. For example, different CNNs may be trained using silhouettes of bodies, such as human bodies, from different orientations with known features. In some implementations, different CNNs may be trained for different orientations. For example, a first CNN 1156A-1 may be trained to determine front view features from front view silhouettes 1154-1. A second CNN 1156A-2 may be trained to determine right side features from right side silhouettes. A third CNN 1156A-3 may be trained to determine back view features from back view silhouettes. A fourth CNN 1156A-4 may be trained to determine left side features from left side silhouettes. Different CNNs 1156A-1 through 1156A-N may be trained for each of the different orientations of silhouettes 1154-1 through 1154-N. Alternatively, one CNN may be trained to determine features from any orientation silhouette.” (col. 32, lines 40-57)
“Utilizing the personalized 3D body parameters, a personalized 3D body model of the body is generated. For example, the personalized 3D body parameters may be provided to a body model, such as the Shape Completion and Animation of People (“SCAPE”) body model, a Skinned Multi-Person Linear (“SMPL”) body model, etc., and the body model may generate the personalized 3D body model of the body of the user based on those predicted body parameters.” (col. 26, lines 23-30)
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to determine similarity with a target body as taught by Fazeli et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Fazeli et al. who teaches the advantages of knowing the difference between a target body model and current body.
Cosine Similarity
The combined references teach model and similarity. They do not teach cosine similarity.
Arunachala also in the business of model and similarity teaches:
Avatar features and definitions (model) and select best-matching avatar features from library using lowest cosine distance…
“The avatar features and characteristic definitions 1210 and 1212 can be provided to construct avatar module 1214, which can select best-matching avatar features from avatar library 1216. For example, construct avatar module 1214 can use a model trained to map such avatar features into a semantic space of the avatar library and select closest (e.g., lowest cosine distance) avatar feature from the library also mapped into the semantic space. In various cases, the construct avatar module 1214 can select avatar features from the avatar library that are created with the corresponding characteristics 1212 or can set parameters of the obtained avatar features according to the characteristics 1212. With the correct avatar features obtained, having the correct characteristics, the construct avatar module 1214 can generate a resulting avatar 1218.” [0081]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use cosine distance as taught by Arunachala since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Arunachala who also teaches the benefits of cosine distance for matching avatars.
Claims 16 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over the combined references in section (10) above in further view of Pub. No. US 2016/0203263 to Maier et al.
Regarding claim 16
The recommendation method according to claim 13, wherein the determining the matching user from the plurality of comparable users based on the cosine similarity between the user feature vector and comparable feature vectors of the plurality of comparable users comprises:
determining, using a machine learning model, a user training target vector of the user to be recommended based on the user feature vector, the user training target vector comprising training target information corresponding to a body part which the user to be recommended wants to achieve;
King et al. teaches:
Feature vectors with user profiles…
“Some embodiments may suggest trainers or friends for a user to work out with. Some embodiments may cluster users and trainers according to various criteria, for example, attributes of user profiles, like goals or workout patterns. For instance, some embodiments may model users as feature vectors, with user profile attributes like workout goals, performance, timing, and feedback being mapped to scalars of the vectors. Some embodiments may cluster the vectors with a DBSCAN algorithm and suggesting pairings. Or some embodiments may rank pairings based on Euclidian distance in the vector space, e.g., suggesting to a user the five closest other users or trainers.” [0138]
Training set with profiles of users (physiological feature information) and select workout (training target) for a user …
“In some embodiments, a machine-learning model may be trained to select workouts based on a user's goal. For example, in some cases, a training set may include a goal set by previous users, profiles of those users, workouts by those users, and an indication of whether the users achieve their goals. Some embodiments may filter the training set according to whether users satisfy their stated goals. Some embodiments may cluster users (e.g., with a density based clustering algorithm, like DB-SCAN) according to profiles to identify groups of users who are similar to one another, for example, of similar profiles and have sent similar goals. In some cases, some embodiments may then detect features of workouts within each of the clusters, for example, patterns in chosen workouts associated with meeting the goal for those in the cluster. For instance, for each cluster, embodiments may train a decision tree to classify users as likely to meet their goal based on workout history. Some embodiments may then use these detected features and clusters to recommend workouts for other users. For example, some embodiments may receive a request for workout from a given user, determine which cluster most closely matches that given user, and then select a workout for that user that includes the futures detected among the users in that cluster within their workouts.” [0123]
Machine generated workout instructions for specific body-regions…
“… For example, a user may choose any particular instructor for any workout video block (every instructor provides instructions for all the workout sessions available to the user). In some cases, specific instructors (human, or machine generated) may provide specific workout instructions. For example, some instructors may only give instructions for specific body-regions (e.g., legs, arms, etc.), for specific level of difficulty, for specific workout type (e.g., warm-up, cool down, cardio, etc.), or other specific workout instructions.” [0062]
determining a user feature matrix of the user to be recommended based on the user feature vector and the user training target vector; and
“In some embodiments, the block type groups may be grouped into sets. For example, as shown in FIG. 2, a set 240 may include one or more block type groups 230 each block type group 230 representing a different body region (e.g., a “Warm Up” set may include a “lower”, “upper”, “back” block type groups).” [0055]
Example of matrix with attributes (feature matrix)…
“Three blocks, three families, and three types are shown, but commercially relevant embodiments are expected to include substantially more of each, with substantially more families in each type, and substantially more blocks in each family. In some cases, the blocks may be arranged in a multi-dimensional matrix, with a pointer to a given video block file at each value of the matrix. Dimensions of the matrix may correspond to attributes of the video blocks, e.g., a muscle, a muscle group, an intensity, a range of movement, and the like. A data structure need not be referred to as a matrix in program code to serve as a matrix, provided that the data structure associates each video block with a plurality of attributes that can correspond to dimensions of a matrix. In some cases, the dimensions may include those listed in FIG. 3.” [0058]
determining a matching user from the plurality of comparable users based on a degree of similarity between the user feature matrix and comparable feature matrices of the plurality of comparable users, the comparable feature matrices being generated based on comparable feature vectors and comparable training target vectors of the plurality of comparable users.
Matrix with user feature….
“Three blocks, three families, and three types are shown, but commercially relevant embodiments are expected to include substantially more of each, with substantially more families in each type, and substantially more blocks in each family. In some cases, the blocks may be arranged in a multi-dimensional matrix, with a pointer to a given video block file at each value of the matrix. Dimensions of the matrix may correspond to attributes of the video blocks, e.g., a muscle, a muscle group, an intensity, a range of movement, and the like. A data structure need not be referred to as a matrix in program code to serve as a matrix, provided that the data structure associates each video block with a plurality of attributes that can correspond to dimensions of a matrix. In some cases, the dimensions may include those listed in FIG. 3.” [0058]
The combined references teach matrix. They do not teach similarity.
Maier et al. also in the business of matrix teaches:
Similarity matrix…
“In other embodiments, the systems and methods of the present disclosure may perform an on-the-fly comparison of a patient's image(s) to comparison image(s) of the same or similar tissue regions from one or more other individuals for whom the corresponding health status and/or outcomes are known. The on-the-fly comparison may comprise calculating metrics related to the degree of similarity between the patient's medical image(s) and the comparison image(s) (a similarity matrix, for example), and identifying a corresponding cohort of the one or more individuals represented by the comparison image(s) whose image(s) are the most similar to the patient's image(s) based on these similarity metrics…” [0022]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to determine similarity matrix as taught by Maier et al. since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Maier et al. who teaches the advantages of determining similarity metrics.
Cosine Similarity
The combined references teach model and similarity. They do not teach cosine similarity.
Arunachala also in the business of model and similarity teaches:
Avatar features and definitions (model) and select best-matching avatar features from library using lowest cosine distance…
“The avatar features and characteristic definitions 1210 and 1212 can be provided to construct avatar module 1214, which can select best-matching avatar features from avatar library 1216. For example, construct avatar module 1214 can use a model trained to map such avatar features into a semantic space of the avatar library and select closest (e.g., lowest cosine distance) avatar feature from the library also mapped into the semantic space. In various cases, the construct avatar module 1214 can select avatar features from the avatar library that are created with the corresponding characteristics 1212 or can set parameters of the obtained avatar features according to the characteristics 1212. With the correct avatar features obtained, having the correct characteristics, the construct avatar module 1214 can generate a resulting avatar 1218.” [0081]
It would have been obvious to one of ordinary skill in the art before the effective filing date to include in the method and system of the combined references the ability to use cosine distance as taught by Arunachala since the claimed invention is merely a combination of old elements and in the combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. Further motivation is provided by Arunachala who also teaches the benefits of cosine distance for matching purposes.
Regarding claim 17
The recommendation method according to claim 16, wherein the machine learning model is trained using the comparable feature vectors as inputs and the comparable training target vectors as outputs.
King et al. teaches:
Feature vectors with user profiles…
“Some embodiments may suggest trainers or friends for a user to work out with. Some embodiments may cluster users and trainers according to various criteria, for example, attributes of user profiles, like goals or workout patterns. For instance, some embodiments may model users as feature vectors, with user profile attributes like workout goals, performance, timing, and feedback being mapped to scalars of the vectors. Some embodiments may cluster the vectors with a DBSCAN algorithm and suggesting pairings. Or some embodiments may rank pairings based on Euclidian distance in the vector space, e.g., suggesting to a user the five closest other users or trainers.” [0138]
Training set with profiles of users (physiological feature information) and select workout (training target) for a user …
“In some embodiments, a machine-learning model may be trained to select workouts based on a user's goal. For example, in some cases, a training set may include a goal set by previous users, profiles of those users, workouts by those users, and an indication of whether the users achieve their goals. Some embodiments may filter the training set according to whether users satisfy their stated goals. Some embodiments may cluster users (e.g., with a density based clustering algorithm, like DB-SCAN) according to profiles to identify groups of users who are similar to one another, for example, of similar profiles and have sent similar goals. In some cases, some embodiments may then detect features of workouts within each of the clusters, for example, patterns in chosen workouts associated with meeting the goal for those in the cluster. For instance, for each cluster, embodiments may train a decision tree to classify users as likely to meet their goal based on workout history. Some embodiments may then use these detected features and clusters to recommend workouts for other users. For example, some embodiments may receive a request for workout from a given user, determine which cluster most closely matches that given user, and then select a workout for that user that includes the futures detected among the users in that cluster within their workouts.” [0123]
Machine generated workout instructions for specific body-regions…
“… For example, a user may choose any particular instructor for any workout video block (every instructor provides instructions for all the workout sessions available to the user). In some cases, specific instructors (human, or machine generated) may provide specific workout instructions. For example, some instructors may only give instructions for specific body-regions (e.g., legs, arms, etc.), for specific level of difficulty, for specific workout type (e.g., warm-up, cool down, cardio, etc.), or other specific workout instructions.” [0062]
Claim Analysis - 35 USC § 103
Based on search for Claim 18, no prior art rejection is made at this time.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KENNETH BARTLEY whose telephone number is (571)272-5230. The examiner can normally be reached Mon-Fri: 7:30 - 4:00 EST.
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, SHAHID MERCHANT can be reached at (571) 270-1360. 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.
/KENNETH BARTLEY/Primary Examiner, Art Unit 3684