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 .
Status of the Claims
Claims 1-27 are currently pending. Claims 1, 10, and 19 were amended in the reply filed January 20, 2026. No claims were cancelled and no new claims were added.
Response to Arguments
112(a):
Applicant's amendments overcome the rejection made under 35 U.S.C. § 112(a) to claims 1-27 and it is withdrawn.
101:
Applicant's arguments filed with respect to the rejection made under 35 U.S.C. § 101 have been fully considered but they are not persuasive. Applicant argues that the claims are “directed to a specific technological solution implemented in a networked computing system for machine learning-based home comparison and target price determination for a home builder entity” (Remarks p. 13). Specifically, that the claimed geographic constraint “meaningfully improves the relevance and operation of the computerized clustering process” (Remarks p. 13), the claimed system “improves the technology of computerized home pricing for builders” and “improves builder efficiency by reducing manual analysis, subjective judgment, and iterative trial-and-error pricing” (Remarks p. 14), and that overall, the claim recitations “improve computerized pricing platform by enabling accurate pricing determinations and automated, feature-driven instructions that were not previously achievable using conventional systems” (Remarks p. 14).
Examiner respectfully disagrees. The improvements listed by Applicant are improvements to the abstract idea of determining target home prices, which is not an improvement to technology. An improvement in the abstract idea itself is not an improvement in technology. For example, in Trading Technologies Int’l v. IBG, 921 F.3d 1084, 1093-94, 2019 USPQ2d 138290 (Fed. Cir. 2019), the court determined that the claimed user interface simply provided a trader with more information to facilitate market trades, which improved the business process of market trading but did not improve computers or technology (See MPEP 2106.05(a)(II)).
Furthermore, Examiner notes that “the claim must include more than mere instructions to perform the method on a generic component or machinery to qualify as an improvement to an existing technology” (see MPEP 2106.05(a)(II)). As such, merely performing an abstract idea on a computer or “computerized” does not transform the abstract idea into a technology.
Accordingly, the rejection is maintained.
103:
Applicant's arguments filed with respect to the rejection made under 35 U.S.C. § 103 have been fully considered but they are not persuasive. Applicant argues that the “cited combination of Stewart, Boudreau, and Bleakley fails to disclose or suggest every feature of claim 1” (Remarks p. 16). Specifically, that “Stewart merely describes property listing data as inputs that already exists, not as derived features extracted from specifically defined parameter values” (Remarks p. 16) and the cited portions of Bleakley “merely describe a phase development planning generally” which is “is silent regarding extracting the development plan information into a feature vector, using the phased development scheduled information to cluster homes in a multidimensional feature space, or using the phased development scheduled information in determining a target price for a builder's home, as generally recited by claim 1” Remarks p. 17).
Examiner respectfully disagrees with Applicant’s interpretation of the cited prior art of record and the broadest reasonable interpretation of the claimed invention. Examiner's position is that Stewart in combination with Boudreau and Bleakley teaches all of the limitations of Applicant’s claim 1 as described in the 103 rejection below. In particular, Examiner notes Stewart at [0039], which teaches “feature vectors extracted from a new real-estate property and new set of comps”. With respect to Bleakley, Examiner notes that Bleakley is not cited for “extracting the development plan information into a feature vector, using the phased development scheduled information to cluster homes in a multidimensional feature space, or using the phased development scheduled information in determining a target price for a builder's home” as Applicant argues above. Rather, it is the combination of Stewart in combination with Boudreau and Bleakley that teaches those limitations. One cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986).
Accordingly, the rejection is maintained.
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 1-27 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., an abstract idea) without significantly more.
Independent Claims
MPEP 2106 Step 2A- Prong 1:
Independent claims 1, 10, and 19 recite, receiving a first set of parameter values corresponding to a first home associated with a first entity, the first entity comprising a home builder and the first home comprising a home constructed by the home builder, and a second set of parameter values corresponding to a set of homes associated with one or more other entities,
where the first set of parameter values comprises a completion status, a construction timeline, a home location, and a set of home plan data for the first home, and where the second set of parameter values comprises, for each home in the set of homes, a respective home location and a respective set of home plan data;
extracting a first set of features from the first set of parameter values to generate a first feature vector, where the first feature vector comprises a numerical representation of the first set of features extracted from the first set of parameter values;
identify one or more related homes to the first home,
classify homes represented as feature vectors as belonging to a cluster of one or more clusters in a multidimensional feature space based on a commonality of features associated with the cluster,
where the one or more clusters are defined by proximity between datapoints in the multidimensional feature space using a supervised learning routine,
wherein training is performed using data corresponding to a single geographic area;
determining a target price for the first home based on prices of the one or more related homes identified;
transmitting an instruction based at least in part on the target price, the instruction comprising an indication of one or more features of the one or more related homes that make the one or more related homes more comparable to the first home;
and displaying the instruction and the indication.
The limitations above are processes that under broadest reasonable interpretation cover “certain methods of organizing human activity” (including sales activities or behaviors, or business relations). Specifically, determining target home prices is a sales activity and/or behavior. Examiner particularly notes paragraphs [0005-0006] of Applicant’s specification, which clarifies the relationship to analyze and predict trends in the housing market.
MPEP 2106 Step 2A- Prong 2:
The judicial exceptions are not integrated into a practical application. Claims 1, 10, and 19 as a whole amount to: merely including instructions to implement an abstract idea on a computer, or merely using a computer as a tool to perform an abstract idea, or “apply it”; or generally linking the use of the judicial exception to a particular technological environment or field of use.
Independent claims 1, 10, and 19 recite the following additional elements to perform the above recited steps: a memory (claim 1), a processor (claim 1), a first and second node of a network (claims 1, 10, and 19), a trained machine learning (ML) model (claims 1, 10, and 19), a graphical user interface (claims 1, 10, and 19) and a non-transitory computer readable medium (claim 19). These additional elements are generic computer components performing generic computer functions at a high level of generality, and are recited at a high level of generality. These additional elements amount to no more than mere instructions to apply the exception using a generic computer component.
Examiner notes that, under the broadest reasonable interpretation, claim elements such as generating feature vectors and clustering data are mathematical concepts and, therefore, part of the abstract idea.
Individually and as a whole, these additional elements do not integrate the judicial exceptions into a practical application because the claims do not: improve the functioning of the computer itself or any other technology or technical field; apply the judicial exception with, or by use of, a particular machine; effect a transformation or reduction of a particular article to a different state or thing; add meaningful limitations beyond generally linking the use of the judicial exception to a particular technological environment to transform the judicial exception into patent-eligible subject matter; amount to more than a recitation of the words "apply it" (or an equivalent) or are more than mere instructions to implement an abstract idea or other exception on a computer.
MPEP 2106 Step 2B:
Independent claims 1, 10, and 19 do not include additional elements that are sufficient to amount to significantly more (also known as an “inventive concept”) than the judicial exception. As discussed above, the additional elements are generic computer components performing generic computer functions at a high level of generality. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. Alone or in combination, the additional elements do not contribute significantly more than the judicial exception and as a result, the claims are ineligible.
Dependent Claims
Dependent claims 2-9, 11-18, and 20-27, recite additional details that merely narrow the previously recited abstract idea limitations, without adding any additional elements for analysis. Thus, claims 2-9, 11-18, and 20-27 are also ineligible for the reasons stated above with respect to independent claims 1, 10, and 19.
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.
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 1-4, 6-13, 15-22, and 24-27 are rejected under 35 U.S.C. 103 as being unpatentable over U.S. Patent Publication No. 2022/0084079 to Stewart (Stewart) in view of U.S. Patent Publication No. 2020/0265270 to Boudreau et al. (Boudreau) and in further view of U.S. Patent Publication No. 2013/0346151 to Bleakley et al. (Bleakley).
As to claims 1, 10, and 19, Stewart teaches:
(Claim 1) a memory; and a processor coupled to the memory, the processor configured to perform the steps of (“… In various embodiments, the software architecture 606 is implemented by hardware such as machine 700 of FIG. 7 that includes processors 704, memory/storage 706, and I/O components 718.” [0063]):
(Claim 19) a non-transitory computer readable medium comprising code for performing steps comprising (“Furthermore, the machine-readable medium is non-transitory (in other words, not having any transitory signals) in that it does not embody a propagating signal …” [0079]):
receiving, at a first node of a network, a first set of parameter values corresponding to a first home associated with a first entity and a second set of parameter values corresponding to a set of homes associated with one or more other entities (“Server system [i.e., a first node of a network] 108 then automatically computes or predicts a value for the subject real-estate property and provides the value to the client device 110 instantly or after a period of time (e.g., 24 hours). For example, the server system 108 retrieves another trained machine learning model (e.g., a Siamese Network) that receives listing information for a plurality of comps [i.e., a second set of parameter values corresponding to a set of homes associated with one or more other entities] and listing information for a subject real-estate property [i.e., a first home associated with a first entity] …” [0018-0019]),
where the first set of parameter values comprises (“… Characteristics of each property stored in the MLS server may also be provided. Characteristics include a location of the property [i.e., a home location], a school district, a tax rate, a home owners association rate, interior conditions (e.g., whether the property has been renovated, whether the property has stainless steel appliances, whether the property has a pool, whether the property has granite countertops), whether the property is characterized as new construction, whether the property has previously been occupied, and so forth [i.e., a set of home plan data] …” [0030-0031]);
extracting a first set of features from the first set of parameter values to generate a first feature vector (“As shown in FIG. 3, the machine learning technique training module 220 receives input vectors that include a subject real-estate property listing [i.e., a first set of features] and a plurality of comps (e.g., comp 1-N) …” [0051]),
where the first feature vector comprises a numerical representation of the first set of features extracted from the first set of parameter values (“… “X” denotes a vector of input variables [i.e., a numerical representation] (e.g., any one of the real-estate property listing information associated with a set of comps) …” [0038]);
providing the first feature vector to a trained machine learning (ML) model to identify one or more related homes to the first home (“… The user inputs an address of the subject real-estate property and selects an option to receive an automated offer or value of the subject real-estate property in the website. Server system 108 receives the request and identifies comparable or “comps” [i.e., one or more related homes to the first home] (e.g., a plurality of comparable real-estate properties) having similar attributes as the subject real-estate property …” and “As shown in FIG. 3, the machine learning technique training module 220 receives input vectors that include a subject real-estate property listing and a plurality of comps (e.g., comp 1-N). In some implementations, the input vectors are tensors of three dimensions. A first dimension of the tensors represents various subject properties, a second dimension of the tensors represent the comparable properties for each subject that is in the first dimension, and a third dimension represents the features of each comparable property and subject property …” [0017 and 0051-052]),
where the trained ML model is configured to classify homes represented as feature vectors as belonging to a cluster of one or more clusters in a multidimensional feature space based on a commonality of features associated with the cluster (“… In another example, for an unsupervised learning phase, a model is developed to cluster the dataset into n groups, and is evaluated over several epochs as to how consistently it places a given input into a given group and how reliably it produces the n desired clusters across each epoch” and “… In some implementations, the parameters of the machine learning technique training module 220 are updated after a batch of subject is processed rather than based on an individual closed listing. For example, a cluster of subjects of closed listings may be retrieved from a three-dimensional tensor [i.e., a multidimensional feature space] and applied to the machine learning technique training module 220 …” [0040-0044 and 0050-0055]),
wherein training of the ML model is performed using data corresponding to a single geographic area (“… For example, the trained machine learning techniques may be neural networks that identify a set of 10 or more comparable real-estate properties that have recently sold, such as in the past 6 months or 1 year, that are of a similar size, are within a predefined geographical distance, and of the same type as the given or subject real-estate property” and “… The plurality of previously closed listings may correspond to a particular geographical region (e.g., a neighborhood, a zip code, a city, a state, a country, and any combination thereof) …” [0017 and 0051]);
determining a target price for the first home based on prices of the one or more related homes identified via the ML model (“At operation 403, the computing system processes the subject real-estate property listing information together with the plurality of comparable real-estate property listings using a trained machine learning technique to predict a value [i.e., a target price] for the subject real-estate property …” [0061]);
transmitting, to a second node of the network, an instruction based on the target price (“At operation 404, the computing system performs an action with respect to the subject real-estate property based on the predicted value of the subject real-estate property. For example, the estimated value [i.e., an instruction] is provided to a computing device to be presented to a user [i.e., a second node of the network]. In some cases, a distribution of values is presented to an operator or user along with the corresponding weights of the comps for each value along the distribution of values” [0062]).
(Examiner’s Note: under the broadest reasonable interpretation and per paragraph [0113] of Applicant’s specification, an “instruction” is interpreted to include a report of a recommended target price [i.e., estimated value], as taught by Stewart.)
the instruction comprising an indication of one or more features of the one or more related homes that make the one or more related homes more comparable to the first home (“… The weights assigned to the set of training comparable real-estate properties represent how much a value of a respective one of the set of training comparable real-estate properties influences the value of the real-estate property of interest …” and “… For example, the estimated value is provided to a computing device to be presented to a user. In some cases, a distribution of values is presented to an operator or user along with the corresponding weights of the comps for each value along the distribution of values.” [0018 and 0060-0062] Examiner notes that the weights taught by Stewart are used to determine that related homes are more comparable);
and displaying the instruction and the indication at a graphical user interface (GUI) of the second node of the network (“… At operation 404, the computing system performs an action with respect to the subject real-estate property based on the predicted value of the subject real-estate property. For example, the estimated value is provided to a computing device to be presented to a user. In some cases, a distribution of values is presented to an operator or user along with the corresponding weights of the comps for each value along the distribution of values.” and “… For example, the frameworks 618 provide various graphic user interface (GUI) functions, high-level resource management, high-level location services, and so forth …” [0060-0062 and 0066]).
Stewart does not teach, where the one or more clusters are defined by proximity between datapoints in the multidimensional feature space using a supervised learning routine. However, Boudreau teaches, where the one or more clusters are defined by proximity between datapoints in the multidimensional feature space using a supervised learning routine (“… After determining the closest neighbors to a data element in the feature space [i.e., proximity between datapoints in the multidimensional space], RI module 53 may then compute mutuality scores and a cluster score for each data element …” and “Optionally, the labeled data set [i.e., a supervised learning routine] may be used as an input to a machine learning algorithm in order to train a model to classify new data elements. The resulting trained model could be used to classify new data sets with different elements, provided such data sets are capable of representation within the same feature space.” [0042-0043 and 0079]);
It would have been obvious to one having ordinary skill in the art at the effective filling date of the invention to include, where the one or more clusters are defined by proximity between datapoints in the multidimensional feature space using a supervised learning routine, as taught by Boudreau with the home price prediction system of Stewart. Motivation to do so comes from the teachings of Boudreau that doing so would provide for efficient classification of data elements of large data sets [0003].
Stewart in view of Boudreau does not teach, the first entity comprising a home builder and the first home comprising a home constructed by the home builder; where the first set of parameter values comprises a completion status, a construction timeline. However, Bleakley teaches, the first entity comprising a home builder and the first home comprising a home constructed by the home builder (“Accordingly, real estate developers, homebuilders, master-planned community developers, land bankers, lenders, financiers, municipalities, or speculative investors looking to plan, value, or sell real estate developments can use the disclosed systems and methods to determine estimated valuations for the development …” and “… In some implementations, virtual properties can also include properties that have actually been built in the development. For example, their actual characteristics can be input into the system 100, and such properties can be valued as if they were virtual. Thus, the system 100 can value individual properties based on the individual property's characteristics input to the system 100, whether or not the individual property has already been built or is to be built in the future …” [0019 and 0025-0028]),
where the first set of parameter values comprises a completion status, a construction timeline (“… For example, the method 400 may access a development plan that includes information on plans or phases within the development and the types and characteristics of the properties planned to be constructed in the development (or that may have already been constructed) …” and “… Some embodiments of the method 600 can accommodate phased developments in which groups of properties may be constructed at different times (e.g., phase 1 in year 1, phase 2 in year 2, and so forth) …” [0046-0049 and 0056]).
It would have been obvious to one having ordinary skill in the art at the effective filling date of the invention to include, the first entity comprising a home builder and the first home comprising a home constructed by the home builder; where the first set of parameter values comprises a completion status, a construction timeline, as taught by Bleakley with the home price prediction system of Stewart in view of Boudreau. Motivation to do so comes from the teachings of Bleakley that doing so would help determine which plan most closely meets (or exceeds) the developer's goal for the development [0058].
As to claims 2, 11, and 20, Stewart in view of Boudreau and in further view of Bleakley teaches all of the limitations of claim 1 as discussed above. Stewart does not teach, wherein the trained machine learning model is configured to perform K nearest neighbors clustering. However, Boudreau teaches, wherein the trained machine learning model is configured to perform K nearest neighbors clustering (“… Therefore, the mutuality score for a given value of k represents the proportion of mutual neighbors among that data element's closest k neighbors. Specifically, the k-th mutuality score for a particular data element is the proportion of that data element's k nearest neighbors for which the data element is also a k nearest neighbor (referred to as mutual neighbors).” [0043]).
It would have been obvious to one having ordinary skill in the art at the effective filling date of the invention to include, wherein the trained machine learning model is configured to perform K nearest neighbors clustering, as taught by Boudreau with the home price prediction system of Stewart. Motivation to do so comes from the teachings of Boudreau that doing so would provide for efficient classification of data elements of large data sets [0003].
As to claims 3, 12, and 21, Stewart in view of Boudreau and in further view of Bleakley teaches all of the limitations of claim 1 as discussed above. Stewart further teaches, where the one or more related homes correspond to the one or more clusters in the multidimensional feature space having a distance to a location in the multidimensional feature space that corresponds to the first home (“… In an example, a delineation [i.e., a distance] between data clusterings is used to select a model that produces the clearest bounds for its clusters of data” and “In some implementations, the parameters of the machine learning technique training module 220 are updated after a batch of subject is processed rather than based on an individual closed listing. For example, a cluster of subjects of closed listings [i.e., one or more related homes] may be retrieved from a three-dimensional tensor and applied to the machine learning technique training module 220 …” [0044 and 0055]).
While Stewart teaches, where the one or more related homes correspond to the one or more clusters in the multidimensional feature space having a distance to a location in the multidimensional feature space that corresponds to the first home, Stewart does not teach a smallest Euclidean distance. However, Boudreau teaches, a smallest Euclidean distance (“… To determine the closest neighbors to a data element in the feature space, RI module 53 may first compute the distance between each two data elements in the feature space, for example, by computing the Euclidean distance between the data elements in the feature space, or by using other suitable formulas.” [0042]). Since each individual element and its function are shown in the art, albeit shown in separate references, the difference between the claimed subject matter and the prior art rests not on any individual element or function but in the very combination itself—that is in the substitution of the smallest Euclidean distance of Boudreau for the distance of Stewart. Thus, the simple substitution of one known element for another producing a predictable result renders the claim obvious. Motivation to do so comes from the teachings of Boudreau that doing so would provide for efficient classification of data elements of large data sets [0003].
As to claims 4, 13, and 22, Stewart in view of Boudreau and in further view of Bleakley teaches all of the limitations of claim 3 as discussed above. Stewart further teaches, where the trained machine learning model is configured to rank the one or more related homes based on the multidimensional feature space from the location corresponding to the first home to locations corresponding to the one or more related homes (“… The trained machine learning model outputs a value for the subject real-estate property and a set of weights [i.e., rank] for the comps [i.e., one or more related homes] based on the listing information of the comps and the subject real-estate property. The trained machine learning model is trained to jointly establish a relationship between weights assigned to the set of comps and value adjustments of the set of comps and a value of a real-estate property of interest …” and “… The input vector or in some cases the three-dimensional tensor [i.e., the multidimensional feature space] is applied to the Siamese Networks which estimates in tandem or jointly, a weight of each comp in the subset and a price adjustment for each comp in the subset …” [0018 and 0051-0052]).
While Stewart teaches, where the trained machine learning model is configured to rank the one or more related homes based on the multidimensional feature space from the location corresponding to the first home to locations corresponding to the one or more related homes, Stewart does not teach based on Euclidean distances within the multidimensional feature space. However, Boudreau teaches, based on Euclidean distances within the multidimensional feature space (“At 512, classification tool 32 identifies the k_max nearest neighbors of each data element and stores them. As noted, nearest neighbors may be identified based on proximity of data elements to one another within the feature space, for example, based on Euclidean distance within the feature space …” [0057]). Since each individual element and its function are shown in the art, albeit shown in separate references, the difference between the claimed subject matter and the prior art rests not on any individual element or function but in the very combination itself—that is in the substitution of the Euclidean distances within the multidimensional feature space of Boudreau for the multidimensional feature space of Stewart. Thus, the simple substitution of one known element for another producing a predictable result renders the claim obvious. Motivation to do so comes from the teachings of Boudreau that doing so would provide for efficient classification of data elements of large data sets [0003].
As to claims 5, 14, and 23, Stewart in view of Boudreau and in further view of Bleakley teaches all of the limitations of claim 1 as discussed above. Stewart further teaches, where determining the target price comprises: assigning one or more weights to prices of the one or more related homes based on respective distances from locations of the one or more related homes to the location of the first home in the multi-dimensional feature space to generate a set of one or more weighted prices (“Third-party servers 130 may include a multiple listing service (MLS) server. This service is publicly accessible to real-estate brokers nationwide. A real-estate broker inputs property information [i.e., comps] to the MLS server (e.g., price information, property attributes, listing date of a property, date contract to sell the property was executed, closing date of the property, etc.) to list the property for sale and to complete transactions for the property …” and “At operation 402, the computing system identifies a plurality of comparable real-estate property listings based on attributes of the subject real-estate property listing information. For example, the value determination system 124 applies a trained machine learning technique to the address or other characteristics or attributes of the given subject property to identify comps (e.g., 10 different properties within a certain distance and having the same or similar attributes as the subject property).” and “The input vector or in some cases the three-dimensional tensor is applied to the Siamese Networks which estimates in tandem or jointly, a weight of each comp in the subset and a price adjustment for each comp in the subset …” [0030 and 0060 and 0052] (emphasis added)).
Stewart in view of Boudreau does not teach, and determining a weighted average of the one or more weighted prices. However, Bleakley teaches, and determining a weighted average of the one or more weighted prices (“… For example, multiple AVM valuations can be received for a property, and the valuation used by the valuation analyzer 128 can be an average of the multiple AVM valuations. In some cases, a weighted average can be used, with the weight of an individual AVM valuation based at least partly on an accuracy estimate for the AVM valuation (e.g., a forecast standard deviation for the AVM) …” and “… Column 212 also lists the arithmetic average AVM valuation of the homes for the four plans as well as a weighted average valuation (where the weighting is proportional to the number of units in each plan) …” [0033 and 0043]).
It would have been obvious to one having ordinary skill in the art at the effective filling date of the invention to include, and determining a weighted average of the one or more weighted prices, as taught by Moss with the home price prediction system of Stewart in view of Boudreau. Motivation to do so comes from the teachings of Bleakley that doing so would help determine which plan most closely meets (or exceeds) the developer's goal for the development [0058].
As to claims 6, 15, and 24, Stewart in view of Boudreau and in further view of Bleakley teaches all of the limitations of claim 1 as discussed above. Stewart further teaches, training the trained machine learning model by: extracting a second set of features from each home in the set of homes to generate a plurality of feature vectors (“As shown in FIG. 3, the machine learning technique training module 220 receives input vectors that include a subject real-estate property listing and a plurality of comps (e.g., comp 1-N). In some implementations, the input vectors are tensors of three dimensions. A first dimension of the tensors represents various subject properties, a second dimension of the tensors represent the comparable properties [i.e., each home in the set of homes] for each subject that is in the first dimension, and a third dimension represents the features of each comparable property and subject property …” [0051-0052]);
and providing the plurality of feature vectors to the trained machine learning model as training inputs (“… To train the machine learning technique training module 220, a plurality of previously closed listings for real-estate properties is retrieved, such as from the input tensors …” [0051-0052]).
As to claims 7, 16, and 25, Stewart in view of Boudreau and in further view of Bleakley teaches all of the limitations of claim 1 as discussed above. Stewart further teaches, where the respective set of home plan data includes a set of home plan dimension data and a set of home plan layout data, where the set of home plan layout data includes a bedroom count, a bathroom count, a garage option attribute, a home amenities attribute, a home type attribute, or a combination thereof (“… The MLS server may include a database of real-estate properties. Characteristics of each property stored in the MLS server may also be provided. Characteristics include a location of the property, a school district, a tax rate, a home owners association rate, interior conditions [i.e., a home amenities attribute] (e.g., whether the property has been renovated, whether the property has stainless steel appliances, whether the property has a pool, whether the property has granite countertops), whether the property is characterized as new construction, whether the property has previously been occupied, and so forth …” [0030-0031]).
As to claims 8, 17, and 26, Stewart in view of Boudreau and in further view of Bleakley teaches all of the limitations of claim 1 as discussed above. Stewart further teaches, where the first set of parameter values, the second set of parameter values, or both, further comprise, for the first home and each home of the set of homes, a respective set of geography attributes, where the respective set of geography attributes includes a school district attribute, a school district rating attribute, a city attribute, a state attribute, a country attribute, a community amenities attribute, an active adult attribute, or a combination thereof (“… The MLS server may include a database of real-estate properties. Characteristics of each property stored in the MLS server may also be provided. Characteristics include a location of the property, a school district [i.e., a school district attribute], a tax rate, a home owners association rate, interior conditions (e.g., whether the property has been renovated, whether the property has stainless steel appliances, whether the property has a pool, whether the property has granite countertops), whether the property is characterized as new construction, whether the property has previously been occupied, and so forth …” [0030-0031]).
As to claims 9, 18, and 27, Stewart in view of Boudreau and in further view of Bleakley teaches all of the limitations of claim 1 as discussed above. Stewart further teaches, where the instruction comprises an instruction to raise or lower a price of the first home, an instruction to make the price of the first home equal to the target price, an instruction to adjust an advertising effort for the first home, an instruction to increase or decrease a construction rate for the first home, a report of the target price, a report of the prices of the one or more related homes a report of a range of prices about the target price, or a combination thereof (“At operation 404, the computing system performs an action with respect to the subject real-estate property based on the predicted value of the subject real-estate property. For example, the estimated value [i.e., a report of the target price] is provided to a computing device to be presented to a user. In some cases, a distribution of values is presented to an operator or user along with the corresponding weights of the comps for each value along the distribution of values” [0062]).
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 STEPHANIE S WALLICK whose telephone number is (703)756-1081. The examiner can normally be reached M-F 10am-6pm.
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, Shannon Campbell can be reached at (571) 272-5587. 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.
/S.S.W./Examiner, Art Unit 3628
/RUPANGINI SINGH/Primary Examiner, Art Unit 3628