DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
The claims 2 -12 and 15 -23 are presented for examination.
The specification is objected.
The claims 2 -12 and 15 -23 are rejected under 35 U.S.C. 101.
Claims 2-3, 5-7, 10-12, 15-16, 18-20, and 22 are rejected under 35 U.S.C. 103 as being unpatentable over FENG; Xin (US 20180165706 A1) further in the view of Hotchkies; Blair Livingstone (US 10311371 B1)
Claims 4, 8, 17, 21, and 23 are rejected under 35 U.S.C. 103 as being unpatentable over FENG; Xin (US 20180165706 A1) further in the view of Hotchkies; Blair Livingstone (US 10311371 B1) further in the view of Tan, Linda SL. "Stochastic variational inference for large-scale discrete choice models using adaptive batch sizes." Statistics and Computing 27.1 (2017).
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over FENG; Xin (US 20180165706 A1) further in the view of Hotchkies; Blair Livingstone (US 10311371 B1) further in the view of Tan, Linda SL. "Stochastic variational inference for large-scale discrete choice models using adaptive batch sizes." Statistics and Computing 27.1 (2017), further in the view of Paul Bailey, Claire Kelley, and Trang Nguyen, “Introduction to Weighted Mixed-Effects Models With WeMix” (2019).
This action is Non-final rejection.
Priority
Acknowledgment is made for a domestic priority date of PCT/US2022/043090, filing date 09/09/2022.
Information Disclosure Statement
The IDS filed on 06/01/2023 and 04/17/2025 is reviewed and considered. See the attached file.
Specification
The disclosure is objected to because of the following informalities:
On para 108 , the modeled system 222 should be the modeled system 220.
On para 110, computing device 2, should be computing device 80 or client computing device 2.
On para 113, server computing system 40, should be server computing system 30.
On para 113 and 117, machine-learned models 40 should be machine- learned models 20.
On para 116 , computing system 130, should be computing system 120.
Appropriate correction is required.
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 2 -12 and 15 -23 are rejected under 35 U.S.C. 101 because the claimed invention is directed to mental process without any additional element that provide a practical or amount to significant more than the abstract idea.
Step 1: Yes: the claims 2- 12 recites a method and 15 -21 recites a system, so claims 2- 12 and 15- 21 falls into a statutory category of a process and 22-23 recites apparatus.
Step 2A Prong 1: Yes: claims 2-12 and 15-23 recites abstract idea, abstract ideas in each claim are bolded below.
Regarding claim 2, 15 and 22
initializing, by , a mixed effects model configured to describe a first effect and a second effect on a distribution of the session data (under a broadest reasonable interpretation, this claim limitation can be performed by a human mind using pen and paper. according to the specification [0070] states the mixed model as a mathematical equation and [0141] shows initializing of parameters, so a human mind can initialize the model by assigning initial value to the parameters using observation, judgment and evaluation. Therefore this claim limitation recites a mental process).
optimizing, by , a weighted objective over a plurality of subsets of the session data, the weighted objective comprising a weighting parameter configured to adjust, respectively for the plurality of subsets of the session data, a contribution of the second effect with respect to the first effect (under a broadest claim interpretation this claim limitation recites a mental process. A human mind can assign a weighting to optimize the gathered information, for example according to the specification [0144], optimizing a weighted objective of the gathered information as it is listed is done by applying a weight into the equations. This can be done by a human mind using a pen and paper through observation, evaluation and judgment of the equations, since a human can apply a weight into the equation ).
updating, by the mixed effects model based on the optimized weighted objective (under the broadest reasonable interpretation, this claim recites a mental process. A human mind can update the model by assigning the optimized weighted objective, for example according to specification [0150] the updating is performed by using optimized parameters, so a human mind can assign the optimized parameters into the model to create updated model through evaluation, observation and judgment with the aid of pen and paper).
The dependent claims further defines the abstract ideas .
Regarding claim 3 and 16:
wherein the second effect is associated with one or more levels of values in the session data, and wherein the weighted parameter is based on a frequency that a respective level associated with an input to the weighted objective appears in the session data (this claim limitation further define the abstract idea and further limiting the type of parameter used by specifying the weighted parameters are dependent on the frequency of respective input. A human mind can use a weighted objective based on respective input for optimization by making observation and evaluation on the weight value to assign weight based on frequency as it is recited).
Regarding claim 4 and 17:
wherein the weighted parameter is based on a size of a respective subset of the plurality of subsets (this limitation further specifies the abstract idea by further limiting the type of parameter used by defining weighting parameter based on size of subset and a human mind can use a weighting parameter which is based on size of subset for optimization).
Regarding claim 5 and 18:
wherein optimizing the weighted objective comprises inverting, by , a data structure descriptive of at least a portion of a respective subset of the plurality of subsets (This claim limitation further defines the abstract idea of optimizing the weighted objective by further limiting the method used and human mind can perform inverting using a pan a paper).
Regarding claim 6 and 19:
wherein the mixed effects model disambiguates the first effect and the second effect (under a broadest claim interpretation this claim also recites abstract idea. A human mind can perform observation, evaluation and judgment on the gathered information to clean noise data using a pan and paper. Therefore this claim limitation is a mental process).
Regarding claim 8, 21 and 23:
wherein the weighted objective is optimized by stochastic gradient descent (this claim limitation further defines the abstract idea by further narrowing the type of method used and a human mind can perform optimization using stochastic gradient descent method with the aid of a paper and pen as well).
Regarding claim 9:
estimating, by a prior for a feature corresponding to the second effect; and estimating, by and based on the estimated prior, one or more weights for modeling the feature in the mixed effects model (this also further defines abstract idea. A human mind can make estimation corresponding to the gathered information and by performing evaluation on prior estimation, a human mind can also make weights for modeling the feature. So as it was listed on the above claims the process of optimization using a weighting is a mental process and this limitation is also a mental process since a human mind can perform estimation of the prior and modified modeling feature by making evaluation and judgment using a pen and paper on the gathered information).
Regarding claim 10:
wherein the weighted objective is optimized over the plurality of subsets at least partially in parallel (this claim limitation further define the abstract idea by further limiting the method used to perform optimization using weighted objective).
Regarding claim 11:
wherein the mixed effects model is updated by a first entity , wherein the first entity provides a modeling service to model behavior of a second entity content distribution system (this claim limitation further limits the abstract idea of updating a model using additional element. See below for additional element analysis on Step 2B).
Regarding claim 12:
wherein a first entity implements the updated mixed effects model to control a distribution of content items on a second entity content distribution system (this claim limitation further limits the abstract idea of updating a model using additional. See below for additional element analysis on Step 2B).
Step 2A prong 2: No
The claims do not recite additional elements that integrate the exception into a
practical application of the exception because the claim do not have additional elements
or a combination of additional elements that apply, rely on, or use the judicial exception
in a manner that impose a meaningful limit on the judicial exception.
Claims recites gathering data which is insignificant extra solution activity. Adding
insignificant extra-solution activity to the judicial exception, e.g., mere data gathering in
conjunction with a law of nature or abstract idea such as a step of obtaining information
about credit card transactions so that the information can be analyzed by an abstract
mental process, as discussed in CyberSource V. Retail Decisions, Inc., 654 F.3d 1366,
1375, 99 USPQ2d 1690, 1694 (Fed. Cir. 2011) (see MPEP § 2106.05(g)
The claim limitations which recites data gatherings, and manipulation are listed
below.
Claim 2, 15 and 22:
obtaining, by a computing system comprising one or more processors, session data descriptive of one or more user sessions in the networked environment (insignificant extra-solution activity – data gathering such as 'obtaining information'. See MPEP 2106.05(g).).
Claim 7 and 20:
wherein the first effect is associated with a causal relationship between an intermediate interaction with a content item rendered on a respective client device, the content item transmitted to the client device according to one or more
distribution parameters, and a target interaction with a target networked resource associated with the content item (insignificant extra-solution activity – data
manipulation).
Step 2B: No
The claims do not cite additional elements which are significantly more than the
abstract idea. As outlined above the claims merely use a computer components as a
tool to perform abstract ideas and it also use additional elements like “computing system” and “service provider system” to implement the abstract idea. Merly using of a computer and applying abstract ideas into a system without making improvement to the functionality of a computer is not a significantly more.
The dependent claims include the same abstract ideas as recited in the
independent claim and merely incorporate additional details that narrow the scope of
abstract ideas and fails to add significantly more than the claims as it was covered on step 2A prong 1.
As of claim 22, the claim recites “One or more non-transitory computer-readable media storing instructions that are executable to cause a computing system to perform operations”. In this claim the additional element is used as a tool to perform the operation with out any improvement on the computer system, “which are all
a high- level recitation of a generic computer components and represent mere
instructions to apply the judicial exception on a computer as in MPEP 2106.05(f)”, which
does not provide integration into a practical application.
Though the claim recites additional elements as it is outlined above, they are not
significantly more than abstract idea since the additional elements are merely used as a tool and it does not make improvement to the functioning of the additional elements, see
MPEP 2106.05(a), Improvements to the Functioning of a Computer or To Any Other Technology or Technical Field [R-07.2022]
Therefore, it is concluded that the claims 2-12 and 15 -23 are not found eligible under 35 U.S.C 101.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 2-3, 5-7, 10-12, 15-16, 18-20, and 22 are rejected under 35 U.S.C. 103 as being unpatentable over FENG; Xin (US 20180165706 A1) further in the view of Hotchkies; Blair Livingstone (US 10311371 B1)
As of claim 2, Feng teaches A computer-implemented method for modeling mixed effects in a networked environment, the method comprising ( [0017], According to another aspect of the invention, a computerized method is disclosed that includes aggregating impressions, clickthrough rates and conversion rates of a placed advertising object; solving a mixed model equation).
initializing, by the computing system, a mixed effects model configured to describe a first effect and a second effect on a distribution of the session data ([0002 ], There are many factors affecting advertising efficiency and many newer factors are discovered or accumulated over time. Some of the factors are defined as fixed effects and others defined as random effects in statistical worlds which are typically due to intangible factors. The contribution magnitude of each such factor can be mathematically estimated if sufficient data exists… [0009], There are many more components of demographics that are the newly discovered intangible factors, like individuals search history, purchase history, work interests, other interests, social activity, social influence, friend circle, any intangible information received from social media, user sentiment at any instant, mood, personality, most admired influencers, etc.…).
optimizing, by the computing system, a weighted objective over a plurality of subsets of the session data, the weighted objective comprising a weighting parameter configured to adjust, respectively for the plurality of subsets of the session data, a contribution of the second effect with respect to the first effect; ( [0024] In accordance with a further aspect of the invention, a computerized advertisement optimization system is disclosed that includes a computer server including: an advertisement assessment tool to generate an initial assessment of efficiency of an advertisement; a mixed model equation module to solve a mixed model equation of the advertisement efficiency and placement strategy using weighted tangible parameters for fixed effects and weighted intangible parameters for random effects and provide an estimate of the advertisement efficiency and ad placement strategy; an adjustment module to adjust the weightage assigned to at least one chosen parameter from the tangible parameters and intangible parameters, in an iterative fashion to optimize the efficiency and placement strategy; and a fitness evaluation module to evaluate the fitness of the at least one chosen parameter for iterative adjustment of weightage and change the at least one chosen parameter based on their impact on the result of the solution of the mixed model equation; and an optimized advertisement assessment tool to check and extract the estimate of result, from the plurality of results of the iterative solution of the mixed model equation, that provide the optimized advertisement and strategy for placement of the advertisement).
updating, by the computing system, the mixed effects model based on the optimized weighted objective ([0024] , a fitness evaluation module to evaluate the fitness of the at least one chosen parameter for iterative adjustment of weightage and change the at least one chosen parameter based on their impact on the result of the solution of the mixed model equation; and an optimized advertisement assessment tool to check and extract the estimate of result, from the plurality of results of the iterative solution of the mixed model equation, that provide the optimized advertisement and strategy for placement of the advertisement).
While Feng does not explicitly teach obtaining, by a computing system comprising one or more processors, session data descriptive of one or more user sessions in the networked environment.
Hotchkies teaches obtaining, by a computing system comprising one or more processors, session data descriptive of one or more user sessions in the networked environment (Col 17 line 6 -15, FIG. 5A, at (1), the content delivery management service 130 obtains historical data regarding content requests from the request information data store 122. As described above, the historical data can include any attributes or aspects related to content requests, including derived content strategy component information and content delivery performance information. The historical data may be in a form of raw system logs with time stamps).
Feng and Hotchkies are considered analogous to the claimed invention, since they focus on using model for content distribution success in a networked environment. Therefore it would be obvious for a person of ordinary skill in the art to combine Feng teaching of using a weighted mixed model on obtained session data of Hotchikes in order to include these new demographic factors into traditional demographic factors in modeling for improvement of ad efficiency such that the ads presented are optimum for the target demographic and for automatically selecting the most efficiency strategy for ad content development and ad placement (Feng, [0009]), and to create and select a strategy that yields a best predicted performance in the content distribution system (Hotchkies, [0016], the content delivery management service may apply the model to the incoming content request in conjunction with a set of candidate strategies and select a strategy that yields a best predicted performance. In some cases, the set of candidate content delivery strategies may include different combinations of strategy components that have a strong correlation with similar content requests in the training data).
claim 15 is in the same scope as that of claim 2 with additional elements that Feng teaches one or more processors; and one or more non-transitory computer-readable media storing instructions that are executable to cause the computing system to perform operations, the operations ( [0100], One or more of the methodologies or functions described herein may be embodied in the computer-readable medium on which is stored one or more sets of instructions (e.g., software). The software may reside, completely or at least partially, within memory and/or within a processor during execution thereof).
Therefore claim 15, is rejected under the same rational to claim 2.
claim 22 is in the same scope as that of claim 2 with additional elements that Feng teaches One or more non-transitory computer-readable media storing instructions that are executable to cause a computing system to perform operations ([0100], One or more of the methodologies or functions described herein may be embodied in the computer-readable medium …[0101], The terms “computer-readable medium” or “machine readable medium” shall also be taken to include any non-transitory storage medium that is capable of storing, encoding or carrying a set of instructions for execution by a machine and that cause a machine to perform any one or more of the methodologies described herein).
Therefore claim 22, is rejected under the same rational to claim 2.
As of claim 3, the modified model teaches all the limitations of claim 2, and Hotchkies also teaches wherein the second effect is associated with one or more levels of values in the session data, and wherein the weighted parameter is based on a frequency that a respective level associated with an input to the weighted objective appears in the session data (col 17, line 40 -61, Thus, input features and outputs are determined for each content request referenced by the training data. For example, input features corresponding to each content request can include a vector of any combination of attributes derived from the content requests data or applicable user data related to the content request, and another vector of any combination of content delivery strategy components derived from processing information or responses to the content request. Outputs correspond to the same content request may include any defined metrics for measuring content delivery performance, such as a weighted average of user perceived latency and user's purchase propensity corresponding to the content request, which can be further modified by other values related to a type of content, a type of client computing device, a geographic region, combinations of the same, or the like. The outputs may also include indications of ATF configurations derived from user interaction data related to a response to the content request, such as identification of a portion of rendered content as ATF and a confidence level associated with the ATF configuration. The confidence level can be defined based on a type, quantity or consistency of user interactions with the portion of rendered content).
Claim 16 is in the same scope to that of claim 3, therefore claim 16 is rejected under the same rational to claim 3.
As of claim 5, the modified model teaches all the limitations of claim 2, and Feng also teaches wherein optimizing the weighted objective comprises inverting, by the computing system, a data structure descriptive of at least a portion of a respective subset of the plurality of subsets. ([0060] – [0066],
PNG
media_image1.png
546
663
media_image1.png
Greyscale
… . mathematical models may be built using these datasets, for example, by placing different weights on impressions, clickthrough and conversion, based on business requirements, to construct objective functions. Objective function value=impression+10×clickthrough+40×conversions), as it was shown above inverse was applied in the mixed model and those datasets are used for the formation of objective function.
Claim 18 is in the same scope to that of claim 5, therefore claim 18 is rejected under the same rational to claim 5.
As of claim 6, the combined model teaches all the limitations of claim 2, and Feng also teaches , wherein the mixed effects model disambiguates the first effect and the second effect ([0043] The adjustment module now chooses one or more intangible parameters to increment their weightage in an iterative fashion so that at each iteration the mixed model equation is solved by the mixed model equation module to generate an estimated efficiency and pad placement strategy result.
[0044] Some of the intangible parameters will have a perceptible impact on the result and some will not, this is checked by the fitness evaluation module 130, and those intangible parameters having low or no impact on the result are assessed as unfit and removed from the equation to reduce the computational complexity. The impact of the others are evaluated in the iterative process).
Claim 19 is in the same scope to that of claim 6, therefore claim 19 is rejected under the same rational to claim 6.
As of claim 7, the modified model teaches all the limitations of claim 2, and Hotchkies also teaches wherein the first effect is associated with a causal relationship between an intermediate interaction with a content item rendered on a respective client device, the content item transmitted to the client device according to one or more distribution parameters, (col 17 line 25 -39, At (3), the content delivery management service 130 builds one or more models for determining content delivery strategies in response to content requests. Various supervised machine learning methods (e.g., decision trees, artificial neural networks, logistic regression, support vector machine, etc.) can be employed to build the model. The content delivery management service may decide to use a subset of the historical data obtained from the request information data store 122 and user information data store 124 as basis for training data for a specific model. The training data needs to be representative of real-world use of a function (e.g., to predict a defined content delivery performance measure or to determine an ATF configuration based on content request attributes and a proposed content delivery strategy) corresponding to the model)
a target interaction with a target networked resource associated with the content item (fig 5A/4 content request figure 5b /10, updated request data : figure 5c/ 13 new content request).
Claim 20 is in the same scope to that of claim 7, therefore claim 20 is rejected under the same rational to claim 7.
As of claim 10, the modified model teaches all the limitations of claim 2, and Hotchkies also teaches wherein the weighted objective is optimized over the plurality of subsets at least partially in parallel (col 27 line 12- 20, depending on the embodiment, certain acts, events, or functions of any of the methods described herein can be performed in a different sequence, can be added, merged, or left out altogether (e.g., not all described acts or events are necessary for the practice of the algorithm). Moreover, in certain embodiments, acts or events can be performed concurrently, e.g., through multi-threaded processing, interrupt processing, or multiple processors or processor cores or on other parallel architectures, rather than sequentially).
As of claim 11 the modified model teaches all the limitations of claim 2, and Feng also teaches wherein the mixed effects model is updated by a first entity service provider system, wherein the first entity service provider system provides a modeling service to model behavior of a second entity content distribution system (Fig. 1: content provider 104 and service provider 106, [0015], For example, the content delivery management service may derive various attributes (e.g., requested resources, timing of requests, associated network condition, computing capability of request submitting device, geographic information, etc.) of each content request received by the content provider over a specified period of time. In some cases, applicable user attributes (e.g., demographics, purchase histories, Web browsing histories, search term histories, session tracking histories, ownership or rental lists, preferences, settings, etc.) associated with users who submitted the content requests can also be derived. The content delivery management service may also derive various content delivery strategy components (e.g., inclusion or exclusion of certain features in responses, lazy-loading or prefetching of resources, in-lining or external call for resources, low quality or high-quality data formats, dependency graph associated with responses, above-the-fold configurations, routing of the requests, etc.) from data related to responses to each of the content requests. On the other hand, the content delivery management service can collect or derive content delivery performance metrics ).
As of claim 12 the modified model teaches all the limitations of claim 2, and Feng also teaches wherein a first entity service provider system implements the updated mixed effects model to control a distribution of content items on a second entity content distribution system ([0032], Still further, the content provider 104 illustrated in FIG. 1 can include the content delivery management service 130 for determining and implementing optimized content delivery strategy in response to content requests based on machine learning models. As will be discussed in more detail below, illustratively, the content delivery management service 130 may build one or more models for predicting performance of proposed content delivery strategies and for determining appropriate ATF configurations in response to content requests, determine and execute a strategy that yields best predicted performance).
Claims 4, 8, 17, 21, and 23 are rejected under 35 U.S.C. 103 as being unpatentable over FENG; Xin (US 20180165706 A1) further in the view of Hotchkies; Blair Livingstone (US 10311371 B1) further in the view of Tan, Linda SL. "Stochastic variational inference for large-scale discrete choice models using adaptive batch sizes." Statistics and Computing 27.1 (2017).
As of claim 4, the modified model teaches all the limitations of claim 2, but it does not explicitly teach wherein the weighted parameter is based on a size of a respective subset of the plurality of subsets.
While Tan teaches wherein the weighted parameter is based on a size of a respective subset of the plurality of subsets (abstract, Stochastic variational inference allows data to be processed in minibatches by optimizing global variational parameters using stochastic gradient approximation… section 4.4, As the minibatch size increase, our confidence level increases. The stepsize is 1 when the algorithm transits to batch mode (when |B| = H). In the examples, we start with a minibatch size of |B| = 25 and an initial stepsize α|B| = 0.4. We let the stepsize increase linearly with the minibatch size3 until it reaches 1 when |B| = H).
Tan is considered as analogous to the claimed invention, since it teaches mixed model to capture heterogeneity in preferences across decision makers. Therefore , it would be obvious for a person of ordinary skill in the art to apply Tan teaching of weight parameter based on the step size of the subsets in to the combined model.
The motivation would have been to accelerate convergence for large datasets, by develop stochastic variational inference for MMNL models and Stochastic variational inference allows data to be processed in minibatches by optimizing global variational parameters using stochastic gradient approximation and to capture heterogeneity (Tan, abstract).
Claim 17 is in the same scope to that of claim 4, therefore claim 17 is rejected under the same rational to claim 4.
As of claim 8, the modified model teaches all the limitations of claim 2, but it does not explicitly teach wherein the weighted objective is optimized by stochastic gradient descent.
While Tan teaches wherein the weighted objective is optimized by stochastic gradient descent (abstract, Stochastic variational inference allows data to be processed in minibatches by optimizing global variational parameters using stochastic gradient approximation).
Tan is considered as analogous to the claimed invention, since it teaches mixed model to capture heterogeneity in preferences across decision makers. Therefore , it would be obvious for a person of ordinary skill in the art to apply Tan teaching of stochastic gradient for approximation in the combined model).
The motivation would have been to accelerate convergence for large datasets, by develop stochastic variational inference for MMNL models and Stochastic variational inference allows data to be processed in minibatches by optimizing global variational parameters using stochastic gradient approximation and to capture heterogeneity (Tan, abstract).
Claims 21 and 23 are in the same scope to that of claim 8, therefore claims 21 and 23 are rejected under the same rational to claim 8.
Claim 9 is rejected under 35 U.S.C. 103 as being unpatentable over FENG; Xin (US 20180165706 A1) further in the view of Hotchkies; Blair Livingstone (US 10311371 B1) further in the view of Tan, Linda SL. "Stochastic variational inference for large-scale discrete choice models using adaptive batch sizes." Statistics and Computing 27.1 (2017), further in the view of Paul Bailey, Claire Kelley, and Trang Nguyen, “Introduction to Weighted Mixed-Effects Models With WeMix” (2019).
As of claim 9, the modified model teaches all the limitations of claim 2, but it does not explicitly teach estimating, by the computing system, a prior for a feature corresponding to the second effect; and estimating, by the computing system and based on the estimated prior, one or more weights for modeling the feature in the mixed effects model.
While Tan teaches estimating, by the computing system, a prior for a feature corresponding to the second effect ( section 4.1, the stochastic gradient updates for λζ and λΩ thus take the form of
PNG
media_image2.png
105
410
media_image2.png
Greyscale
The present estimate λ(l+1) ζ is a weighted average of the previous estimate λ(l) ζ and the estimate of λζ computed using minibatch B, ˆ λζ) in this context a prior for a feature is mapped to λ(l+1) ζ
Tan is considered as analogous to the claimed invention, since it teaches mixed model to capture heterogeneity in preferences across decision makers. Therefore , it would be obvious for a person of ordinary skill in the art to apply Tan teaching of estimating a prior feature for the random effect in the combined model).
The motivation would have been to accelerate convergence for large datasets, by develop stochastic variational inference for MMNL models and Stochastic variational inference allows data to be processed in minibatches by optimizing global variational parameters using stochastic gradient approximation and to capture heterogeneity (Tan, abstract).
While the modified model does not explicitly teach estimating, by the computing system and based on the estimated prior, one or more weights for modeling the feature in the mixed effects model.
Paul teaches estimating, by the computing system and based on the estimated prior, one or more weights for modeling the feature in the mixed effects model (page 7, WeMix assumes that the weights are already scaled according to the user’s needs. This section describes two common methods that a user may wish to implement.
PNG
media_image3.png
227
889
media_image3.png
Greyscale
Paul is considered to be analogous to the claimed invention, since it focus on weighted mixed model, Therefore it would be obvious for a person of ordinary skill in the art to integrate Paul teaching of calculating the weight for the modeling feature into the modified model.
The motivation would have been by performing weight adjustment using different methods including by scaling weight according to user need to improve the random effect variance estimator in the linear model specially when the sample of the units is small in groups (Paul, page 7).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
ZHANG; Yuwei (US 20170188102 A1, Date Published 2017-06-29) is similar to the claimed invention since it use mixed effect model for video content recommendation by analyzes user historical view data to obtain various personalized preference parameters.
Peng; Jufeng (US 20170300824 A1, Date Published 2017-10-19), is similar to the claimed invention since it teaches A data analytics mixed effect predictive model may then generate, based on the fixed and random effect variables, a future performance estimation value for the risk association of each entity in connection with its plurality of relationships.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ABRHAM A. TAMIRU whose telephone number is (571)272-6987. The examiner can normally be reached Monday - Friday 8:00am - 5:00pm.
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, Ryan Pitaro can be reached at 571 272 4071. 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.
/ABRHAM ALEHEGN TAMIRU/Examiner, Art Unit 2188
/RYAN F PITARO/ Supervisory Patent Examiner, Art Unit 2188
Prosecution Insights