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 .
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 13 November 2024 is being considered by the examiner.
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 2 and 12 contains the trademark/trade name OPENSTREETMAP. Where a trademark or trade name is used in a claim as a limitation to identify or describe a particular material or product, the claim does not comply with the requirements of 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph. See Ex parte Simpson, 218 USPQ 1020 (Bd. App. 1982). The claim scope is uncertain since the trademark or trade name cannot be used properly to identify any particular material or product. A trademark or trade name is used to identify a source of goods, and not the goods themselves. Thus, a trademark or trade name does not identify or describe the goods associated with the trademark or trade name. In the present case, the trademark/trade name is used to identify/describe “standardized tagging schema comprises OpenStreetMap (OSM) tags” and, accordingly, the identification/description is indefinite.
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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
[Broadest Reasonable Interpretation] The claim's recited simulating can be performed mentally because developers routinely look at the businesses, homes, utilities, population density, and traffic to determine what structure to build on a vacant plot. A lot of this can be done intrinsically by living in the area. A person would notice the traffic flow, notice the clusters of shops and restaurants that are constantly filled with people, notice a vacant plot, and have an idea of what shop or restaurant is missing from that area which is found at the observed busy clusters as they run their errands.
[Step 1] Representative claim 1 teaches a method for collecting and organizing information for points of interest in an area of interest as training data to predict land use. This falls under “process”, which is a statutory invention category.
[Step 2A: Prong 1] This is a mental process. But for the memory and the processing apparatus required to carry out the steps which are not explicitly recited in the claims, claim 1 is merely drawn to a series of steps:
accessing, from multiple data sources, information about points of interest (POIs) within an area of interest (AOI), wherein information about each POI comprises at least the POI’s semantic attributes and geolocation
harmonizing the POI information by representing the accessed POI semantics information using a unified format, removing duplicated POIs, and merging POIs from the different data sources based on the harmonized POI information
constructing a spatially explicit POI corpus by
accessing information about a road network, wherein at least a portion of the road network spatially overlaps the AOI, and wherein the road network information comprises hierarchical levels of the road network’s segments
partitioning the AOI into polygons constructed from segments at the same hierarchical level, wherein a polygon at a particular level is nested inside another polygon at a lower level
assigning each POI to the polygons that contain the POIs’ geolocations, such that each POI is associated with polygons across respective hierarchical levels
generating POI embeddings based on the constructed spatially explicit POI corpus
generating AOI embeddings based on the generated POI embeddings
using the generated AOI embeddings as input for training a classifier to predict land use types for an AOI
The steps are, essentially, a process of collecting land data and organizing the data. This is an abstract idea or ideas characterized under mental process.
[Step 2A: Prong 2] This judicial exception is not integrated into a practical application. Other than the above-cited abstract idea, claim 1 doesn’t explicitly claim a specific type of memory or processing apparatus that would be necessary to carry out the steps. There are no special hardware features of the process recited in the claims as presented. The hardware of a memory and a processing apparatus is recited in the specification at a high-level of generality, (see [Specification Para. 17]) such that it amounts to no more than mere instructions of the judicial exception linked to a particular technological environment. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they not impose any meaningful limits on practicing the abstract idea. These limitations essentially linking the use of a judicial exception to a particular technological environment or field of use (MPEP2106.05(h), MPEP2106.04(d)). This claim is directed to an abstract idea.
[Step 2B] This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a memory and a processing apparatus to no more than mere instructions of the judicial exception linked to a particular technological environment. There is no inventive concept in the memory and the processing apparatus. Mere linking the judicial exception to a particular technological environment cannot provide an integrated inventive concept. This claim is not patent eligible.
The dependent claims 2-10 have been rejected on the same grounds and recite substantially similar abstract ideas to the cited independent claim 1.
2. The memory of claim 1, wherein the unified format comprises a standardized set of tags, including OpenStreetMap tags.
3. The memory of claim 1, wherein tags associated with each POI are modeled as words, and are hierarchically grouped from lowest-level polygons to highest-level polygons, such that: groups of POI tags corresponding to highest-level polygons form POI-tag sentences, groups of POI-tag sentences corresponding to next lower-level polygons form POI-tag paragraphs, groups of POI-tag paragraphs corresponding to before-lowest level polygons form POI-tag documents, and groups of POI-tag documents corresponding to the lowest level polygons form a POI-tag corpus.
4. The memory of claim 1, wherein the generating the POI embeddings includes transforming POI tags into respective N-dimensional vectors, where N is greater than or equal to the number of hierarchical levels of the road network.
5. The memory of claim 4, wherein the producing the POI embeddings is performed using a neural network language model.
6. The memory of claim 1, wherein the generating the AOI embeddings comprises: calculating term frequency-inverse document frequency (TF-IDF) weights of the POI tags, and using the TF-IDF weights to calculate a weighted average of POI embeddings associated with an AOI.
7. The memory of claim 6, wherein the determining AOI embeddings is performed using a neural network language model.
8. The memory of claim 1, wherein the instructions cause the data processing apparatus to organize POIs into multi-level spatial hierarchies, allowing the neural network language model to analyze both spatial and semantic attributes of POIs.
9. A system for predicting a type of land use for an AOI, the system comprising: a data processing apparatus; and the memory of claim 1, wherein the land use type is one of a predetermined set of land use types.
10. The system of claim 9, wherein POIs in the AOI comprise at least one of schools, hospitals, and touristic sites.
The 101 analysis for claim 1 would apply similarly to the dependent claims above. Therefore, dependent claims 2-10 are also rejected under 35 U.S.C. 101.
[Step 1] Representative claim 11 teaches a data processing system for collecting and organizing information for points of interest in an area of interest as training data to predict land use. This falls under “machine”, which is a statutory invention category.
[Step 2A: Prong 1] This is a mental process. But for the memory and the processing apparatus of the data processing system required to carry out the steps which are not explicitly recited in the claims, claim 11 is merely drawn to a series of steps:
retrieving, from multiple geospatial data sources, information regarding points of interest (POIs) within a defined AOI, where the information includes spatial coordinates and categorical identifiers for each POI
applying a standardized tagging schema to normalize categorical identifiers across POIs from different data sources, creating a unified semantic format for subsequent processing
constructing a multi-level spatial hierarchy by:
accessing hierarchical boundary data representing physical infrastructure, such as road networks, associated with the AOI, the hierarchy comprising multiple spatial levels representing progressively broader regions within the AOI
segmenting the AOI into nested polygons according to hierarchical boundary levels, creating a spatial structure where each polygon at a given level is nested within polygons at higher levels
mapping each POI to a set of spatial polygons across hierarchical levels that contain the POI’s spatial coordinates, generating hierarchical associations that encode both local and regional spatial context
generating a high-dimensional semantic vector for each POI based on its standardized categorical identifier and assigned hierarchical polygons, wherein each vector captures both the spatial and semantic attributes of the POI
computing an aggregate AOI embedding by combining the semantic vectors of POIs located within the AOI, applying term frequency-inverse document frequency (TF-IDF) weighting to emphasize distinctive POIs relevant to the AOI’s land use characteristics
training a classifier model using the computed AOI embeddings from multiple AOIs labeled with land use categories, the model configured to predict land use type based on the spatial and semantic information encoded in the AOI embeddings
using the trained classifier model to predict a land use category for the AOI by analyzing the aggregate AOI embedding
The steps are, essentially, a machine that collects land data and organizes the data. This is an abstract idea or ideas characterized under mental process.
[Step 2A: Prong 2] This judicial exception is not integrated into a practical application. Other than the above-cited abstract idea, claim 11 doesn’t explicitly claim a specific type of memory or processing apparatus that would be necessary to carry out the steps. There are no special hardware features of the process recited in the claims as presented. The hardware of a memory and a processing apparatus is recited in the specification at a high-level of generality, (see [Specification Para. 17]) such that it amounts to no more than mere instructions of the judicial exception linked to a particular technological environment. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they not impose any meaningful limits on practicing the abstract idea. These limitations essentially linking the use of a judicial exception to a particular technological environment or field of use (MPEP2106.05(h), MPEP2106.04(d)). This claim is directed to an abstract idea.
[Step 2B] This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a memory and a processing apparatus to no more than mere instructions of the judicial exception linked to a particular technological environment. There is no inventive concept in the memory and the processing apparatus. Mere linking the judicial exception to a particular technological environment cannot provide an integrated inventive concept. This claim is not patent eligible.
The dependent claims 12-17 have been rejected on the same grounds and recite substantially similar abstract ideas to the cited independent claim 11.
12. The method of claim 11, wherein the standardized tagging schema comprises OpenStreetMap (OSM) tags to facilitate cross-source compatibility and semantic coherence.
13. The method of claim 11, wherein generating a semantic vector for each POI includes applying a neural network language model trained to encode geographic and functional attributes of POIs into N-dimensional embeddings.
14. The method of claim 11, wherein the TF-IDF weighting applied in the AOI embedding calculation emphasizes unique POIs with semantic importance within the AOI, improving representational accuracy for land use classification.
15. The method of claim 11, wherein the classifier model incorporates feedback data from user inputs or updated land use data to adapt and refine the classification predictions over time.
16. The method of claim 11, wherein the data processing system is configured to dynamically adjust the dimensionality of the POI embeddings to balance computational efficiency and classification accuracy based on the complexity of data within each AOI.
17. The method of claim 11, wherein the classifier model is trained to categorize the AOI into multiple land use categories, including residential, commercial, agricultural, recreational, and utility areas, based on the semantic and spatial attributes encoded within the AOI embedding.
The 101 analysis for claim 11 would apply similarly to the dependent claims above. Therefore, dependent claims 12-17 are also rejected under 35 U.S.C. 101.
[Step 1] Representative claim 18 teaches a system for collecting and organizing information for points of interest in an area of interest as training data to predict land use. This falls under “machine”, which is a statutory invention category.
[Step 2A: Prong 1] This is a mental process. But for the data processing apparatus and the user interface of the system required to carry out the steps which are not explicitly recited in the claims, claim 18 is merely drawn to a series of steps:
retrieving, from multiple geospatial data sources, information regarding points of interest (POIs) within a defined AOI, the information comprising spatial coordinates and categorical identifiers for each POI
applying a standardized tagging schema to normalize categorical identifiers across POIs from diverse data sources, creating a unified semantic format for subsequent processing, including the removal of duplicate POIs and integration of POIs based on their harmonized attributes
constructing a multi-level spatial hierarchy by:
accessing hierarchical boundary data representing physical infrastructure, including road networks, associated with the AOI, the hierarchy comprising spatial levels that represent progressively broader regions within the AOI, and
segmenting the AOI into nested polygons according to the hierarchical boundary levels, creating a spatial structure where each polygon at a given level is nested within polygons at higher levels
mapping each POI to a set of spatial polygons across hierarchical levels that contain the POI’s spatial coordinates, thereby generating hierarchical associations that encode both local and regional spatial context for each POI
generating a high-dimensional semantic vector for each POI based on its standardized categorical identifier and assigned hierarchical polygons, wherein each vector captures both spatial and semantic attributes of the POI
computing an aggregate AOI embedding by combining the semantic vectors of POIs within the AOI, applying term frequency-inverse document frequency (TF-IDF) weighting to emphasize distinctive POIs relevant to the AOI’s land use characteristics
training a classifier model using the computed AOI embeddings from multiple AOIs labeled with land use categories, the model configured to predict land use type based on the spatial and semantic information encoded in the AOI embeddings
a user interface configured to enable a user to: interact with an interactive map displayed on the user interface to navigate, zoom, and pan across different geographic regions to locate an AOI of interest
select and define the AOI within the map by specifying boundaries at varying spatial granularities through hierarchical polygon levels, each selection dynamically updating the classifier model’s analysis based on the harmonized POI data within the selected AOI
refine the AOI boundaries within the selected granularity level by adjusting the AOI’s spatial extent on the map, thereby customizing the area covered in the classifier model’s land use prediction
initiate a prediction operation to receive a displayed output of the predicted land use category for the selected AOI, generated by the classifier model and derived from the unified semantic and spatial embeddings of POIs within the AOI
display confidence metrics for the predicted land use category, save the selected AOI, its predicted category, and associated prediction details, facilitating comparative analysis across multiple AOIs at varying spatial granularities
The steps are, essentially, a machine that collects land data and organizes the data. This is an abstract idea or ideas characterized under mental process.
[Step 2A: Prong 2] This judicial exception is not integrated into a practical application. Other than the above-cited abstract idea, claim 18 doesn’t explicitly claim a specific type of memory and processing apparatus of the data processing apparatus, or the user interface that would be necessary to carry out the steps. There are no special hardware features of the process recited in the claims as presented. The hardware of a memory, a processing apparatus, and a user interface is recited in the specification at a high-level of generality, (see [Specification Para. 17, 119]) such that it amounts to no more than mere instructions of the judicial exception linked to a particular technological environment. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they not impose any meaningful limits on practicing the abstract idea. These limitations essentially linking the use of a judicial exception to a particular technological environment or field of use (MPEP2106.05(h), MPEP2106.04(d)). This claim is directed to an abstract idea.
[Step 2B] This claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a memory and a processing apparatus to no more than mere instructions of the judicial exception linked to a particular technological environment. There is no inventive concept in the data processing apparatus and the user interface. Mere linking the judicial exception to a particular technological environment cannot provide an integrated inventive concept. This claim is not patent eligible.
The dependent claims 19-20 have been rejected on the same grounds and recite substantially similar abstract ideas to the cited independent claim 18.
19. The system of claim 18, wherein the user interface provides a dynamic refinement tool enabling the user to interactively adjust the spatial extent and granularity of the AOI by zooming in or out on the interactive map, thereby updating the classifier model’s analysis in real-time based on the adjusted AOI boundaries, and displaying the refined predicted land use category as the user redefines the AOI. (These additional elements merely link the judicial exception to a particular technological environment.)
20. The system of claim 18, wherein the classifier model adapts the dimensionality of the POI embeddings according to the selected spatial granularity of the AOI to balance processing efficiency and prediction accuracy, and wherein the user interface further provides a visual breakdown of key semantic features within the AOI that contributed to the predicted land use category, enhancing user understanding of the classifier model’s output and improving interpretability across different spatial granularities. (These additional elements merely link the judicial exception to a particular technological environment.)
The 101 analysis for claim 18 would apply similarly to the dependent claims above. Therefore, dependent claims 19-20 are also rejected under 35 U.S.C. 101.
Claim 1 is rejected under 35 U.S.C. 101 because the claimed invention is directed to non-statutory subject matter.
The United States Patent and Trademark Office (USPTO) is obliged to give claims their broadest reasonable interpretation consistent with the specification during proceedings before the USPTO. See In re Zletz, 893 F.2d 319 (Fed. Cir. 1989) (during patent examination the pending claims must be interpreted as broadly as their terms reasonably allow). The broadest reasonable interpretation of a claim drawn to a computer readable medium (also called machine readable medium and other such variations) typically covers forms of non-transitory tangible media and transitory propagating signals per se in view of the ordinary and customary meaning of computer readable media, particularly when the specification is silent. See MPEP 2111.01. When the broadest reasonable interpretation of a claim covers a signal per se, the claim must be rejected under 35 U.S.C. § 101 as covering non-statutory subject matter. See In re Nuijten, 500 F.3d 1346, 1356-57 (Fed. Cir. 2007) (transitory embodiments are not directed to statutory subject matter).
The USPTO recognizes that applicants may have claims directed to computer readable media that cover signals per se, which the USPTO must reject under 35 U.S.C. § 101 as covering both non-statutory subject matter and statutory subject matter. In an effort to assist the patent community in overcoming a rejection or potential rejection under 35 U.S.C. § 101 in this situation, the USPTO suggests the following approach. A claim drawn to such a computer readable medium that covers both transitory and non-transitory embodiments may be amended to narrow the claim to cover only statutory embodiments to avoid a rejection under 35 U.S.C. § 101 by adding the limitation "non-transitory" to the claim. Cf. Animals - Patentability, 1077 Off. Gaz. Pat. Office 24 (April 21, 1987) (suggesting that applicants add the limitation "non\- human" to a claim covering a multi-cellular organism to avoid a rejection under 35 U.S.C. § 101). Such an amendment would typically not raise the issue of new matter, even when the specification is silent because the broadest reasonable interpretation relies on the ordinary and customary meaning that includes signals per se. The limited situations in which such an amendment could raise issues of new matter occur, for example, when the specification does not support a non-transitory embodiment because a signal per se is the only viable embodiment such that the amended claim is impermissibly broadened beyond the supporting disclosure. See, e.g., Gentry Gallery, Inc. v. Berkline Corp., 134 F.3d 1473 (Fed. Cir. 1998). Appropriate correction is required.
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 text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
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, 9-11, and 14-17 are rejected under 35 U.S.C. 103 as being unpatentable over Dongjie et al. (US Publication 2023/0394197 A1) in view of Yang et al. (US Publication 2018/0306594 A1).
Regarding claim 1, Dongjie teaches memory encoding instructions that, when executed by data processing apparatus, cause the data processing apparatus to perform operations comprising: accessing, from multiple data sources, information about points of interest (POIs) within an area of interest (AOI), wherein information about each POI comprises at least the POI’s semantic attributes and geolocation (Dongjie: Para. 24, 103-104; first, multiple data sources, such as urban-community related data (for example, housing prices), points-of-interest data, and human mobility data (for example, taxicab GPS traces) are collected; geographical area is visually defined by a set of POIs); harmonizing the POI information by representing the accessed POI semantics information using a unified format (Dongjie: Para. 152; graph data base contains the data that is provided to the generator module; trained encoder module converts that data to vector input data that can be understood by the generator module), ……. , and merging POIs from the different data sources based on the harmonized POI information (Dongjie: Para. 196; generated land-use tensor has multiple channels and that each channel has many blocks, these channels of the land-use tensor were merged into one by setting the dominated POI category; merged solution reflects POI distribution in geographical spatial space) …….. , partitioning the AOI into polygons constructed from segments at the same hierarchical level (Dongjie: Para. 91-92; spatial attributed graph database of nodes that define the areas surrounding the virgin territory; graph database includes respective arrays of data for each of the nodes), wherein a polygon at a particular level is nested inside another polygon at a lower level (Dongjie: Para. 100; a central area is a generally square geographical area that is centered on a geographical location, where there is an unplanned area), assigning each POI to the polygons that contain the POIs’ geolocations, such that each POI is associated with polygons across respective hierarchical levels (Dongjie: Para. 24; a given geographical area is visually defined by a set of POIs and their corresponding locations (e.g., latitudes and longitudes) and urban functionality categories (e.g., shopping, banks, education, entertainment, residential)); generating POI embeddings based on the constructed spatially explicit POI corpus (Dongjie: Para. 79, 93, 152; graph data base contains the data that is provided to the generator module based on which it generates the land use tensor); generating AOI embeddings based on the generated POI embeddings (Dongjie: Para. 197, Fig. 11; visualization of results of land-use plans; blocks represent POI categories); and using the generated AOI embeddings as input for training a classifier to predict land use types for an AOI (Dongjie: Para. 93, 97; converting the characteristics of the surrounding contexts into a low-dimensional vector (latent embedding) using a graph data encoder supported in the system).
Dongjie doesn’t explicitly teach removing duplicated POIs …… constructing a spatially explicit POI corpus by accessing information about a road network, wherein at least a portion of the road network spatially overlaps the AOI, and wherein the road network information comprises hierarchical levels of the road network’s segments.
However Yang, in the same field of endeavor, teaches removing duplicated POIs (Yang: Para. 101; identical POIs in each preferred travel route can be merged into one POI) …… constructing a spatially explicit POI corpus by accessing information about a road network, wherein at least a portion of the road network spatially overlaps the AOI (Yang: Para. 60; POI associated with the positioning terminal in the road networks, when an overlap degree between the positioning region of the positioning terminal and a positioning region of the at least one POI), and wherein the road network information comprises hierarchical levels of the road network’s segments (Yang: Para. 156; display layers can be superimposed with the geographical information to generate a heat map).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101) with a reasonable expectation of success because the number of times each POI appears determines the popularity of the POI and the navigational route (Yang: Para. 102).
Regarding claim 4, Dongjie teaches the memory of claim 1, wherein the generating the POI embeddings includes transforming POI tags into respective N-dimensional vectors (Dongjie: Para. 14; a land-use configuration is defined as a longitude-latitude-channel tensor, where each channel is a category of points of interest (“POIs”) and the value of an entry is the number of POIs).
Dongjie doesn’t explicitly teach where N is greater than or equal to the number of hierarchical levels of the road network.
However Yang, in the same field of endeavor, teaches where N is greater than or equal to the number of hierarchical levels of the road network (Yang: Para. 112; generating display layers in which weight values are differentiated in colors).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101) with a reasonable expectation of success because the number of times each POI appears determines the popularity of the POI and the navigational route (Yang: Para. 102).
Regarding claim 6, Dongjie teaches the memory of claim 1, wherein the generating the AOI embeddings comprises: calculating term frequency-inverse document frequency (TF-IDF) weights of the POI tags (Dongjie: Para. 158; total number of mobile check-in events of an area, denoted by freq, and the diversity of POI of an area, denoted by div, are calculated), and using the TF-IDF weights to calculate a weighted average of POI embeddings associated with an AOI (Dongjie: Para. 166; hyperparameter is adjusted to change the update frequencies of the weight of the discriminator).
Regarding claim 9, Dongjie teaches a system for predicting a type of land use for an AOI, the system comprising: a data processing apparatus; and the memory of claim 1, wherein the land use type is one of a predetermined set of land use types (Dongjie: Para. 24, 67; one or more processors and connected computer-accessible memory or data storage; urban functionality categories (e.g., shopping, banks, education, entertainment, residential)).
Regarding claim 10, Dongjie teaches the system of claim 9, wherein POIs in the AOI comprise at least one of schools, hospitals, and touristic sites (Dongjie: Table 1; 10 tourist attraction).
Regarding claim 11, Dongjie teaches a method implemented by a data processing system for characterizing land use within an area of interest (AOI), the method comprising: retrieving, from multiple geospatial data sources, information regarding points of interest (POIs) within a defined AOI, where the information includes spatial coordinates and categorical identifiers for each POI (Dongjie: Para. 24, 103-104; first, multiple data sources, such as urban-community related data (for example, housing prices), points-of-interest data, and human mobility data (for example, taxicab GPS traces) are collected; geographical area is visually defined by a set of POIs); applying a standardized tagging schema to normalize categorical identifiers across POIs from different data sources, creating a unified semantic format for subsequent processing (Dongjie: Para. 152; graph data base contains the data that is provided to the generator module; trained encoder module converts that data to vector input data that can be understood by the generator module); ……. ; and segmenting the AOI into nested polygons according to hierarchical boundary levels (Dongjie: Para. 91-92; spatial attributed graph database of nodes that define the areas surrounding the virgin territory; graph database includes respective arrays of data for each of the nodes), creating a spatial structure where each polygon at a given level is nested within polygons at higher levels (Dongjie: Para. 100; a central area is a generally square geographical area that is centered on a geographical location, where there is an unplanned area); mapping each POI to a set of spatial polygons across hierarchical levels that contain the POI’s spatial coordinates, generating hierarchical associations that encode both local and regional spatial context (Dongjie: Para. 24; a given geographical area is visually defined by a set of POIs and their corresponding locations (e.g., latitudes and longitudes) and urban functionality categories (e.g., shopping, banks, education, entertainment, residential)); generating a high-dimensional semantic vector for each POI based on its standardized categorical identifier and assigned hierarchical polygons, wherein each vector captures both the spatial and semantic attributes of the POI (Dongjie: Para. 79, 93, 152; graph data base contains the data that is provided to the generator module based on which it generates the land use tensor); computing an aggregate AOI embedding by combining the semantic vectors of POIs located within the AOI (Dongjie: Para. 197, Fig. 11; visualization of results of land-use plans; blocks represent POI categories), applying term frequency-inverse document frequency (TF-IDF) weighting to emphasize distinctive POIs relevant to the AOI’s land use characteristics (Dongjie: Para. 158; total number of mobile check-in events of an area, denoted by freq, and the diversity of POI of an area, denoted by div, are calculated); training a classifier model using the computed AOI embeddings from multiple AOIs labeled with land use categories, the model configured to predict land use type based on the spatial and semantic information encoded in the AOI embeddings (Dongjie: Para. 93, 97; converting the characteristics of the surrounding contexts into a low-dimensional vector (latent embedding) using a graph data encoder supported in the system); and using the trained classifier model to predict a land use category for the AOI by analyzing the aggregate AOI embedding (Dongjie: Para. 12; inputting planning input data comprising context data for a virgin geographical territory to the generator module after the training, and generating land-use data with the trained generator module that defines a land-use plan for the virgin territory).
Dongjie doesn’t explicitly teach constructing a multi-level spatial hierarchy by: accessing hierarchical boundary data representing physical infrastructure, such as road networks, associated with the AOI; and the hierarchy comprising multiple spatial levels representing progressively broader regions within the AOI.
However Yang, in the same field of endeavor, teaches constructing a multi-level spatial hierarchy by: accessing hierarchical boundary data representing physical infrastructure, such as road networks, associated with the AOI (Yang: Para. 60; POI associated with the positioning terminal in the road networks, when an overlap degree between the positioning region of the positioning terminal and a positioning region of the at least one POI ); and the hierarchy comprising multiple spatial levels representing progressively broader regions within the AOI (Yang: Para. 156; display layers can be superimposed with the geographical information to generate a heat map).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101) with a reasonable expectation of success because the number of times each POI appears determines the popularity of the POI and the navigational route (Yang: Para. 102).
Regarding claim 14, Dongjie teaches The method of claim 11, wherein the TF-IDF weighting applied in the AOI embedding calculation emphasizes unique POIs with semantic importance within the AOI, improving representational accuracy for land use classification (Dongjie: Para. 166; hyperparameter is adjusted to change the update frequencies of the weight of the discriminator).
Regarding claim 15, Dongjie teaches The method of claim 11, wherein the classifier model incorporates feedback data from user inputs or updated land use data to adapt and refine the classification predictions over time (Dongjie: Para. 157; quality hyper-parameter Q is provided for users so that they can set the value of Q to distinguish the quality of the land-use configuration solution).
Regarding claim 16, Dongjie teaches The method of claim 11, wherein the data processing system is configured to dynamically adjust the dimensionality of the POI embeddings to balance computational efficiency and classification accuracy based on the complexity of data within each AOI (Dongjie: Para. 13; generator receives this assessment value and generates a new land-use tensor to try to improve the assessment value; cycle continues until it converges, i.e., the generator produces a land-use tensor that the discriminator assesses as adequately good, i.e., it produces assessment data that reaches a threshold quality value).
Regarding claim 17, Dongjie teaches the method of claim 11, wherein the classifier model is trained to categorize the AOI into multiple land use categories, including residential, commercial, agricultural, recreational, and utility areas, based on the semantic and spatial attributes encoded within the AOI embedding (Dongjie: Para. 24-25, Table 1; each channel is a specific category of POIs that are distributed across the unplanned area).
Claims 5, 7-8, 13, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Dongjie et al. (US Publication 2023/0394197 A1) in view of Yang et al. (US Publication 2018/0306594 A1) and in further view Gratton et al. (US Publication 2021/0081559 A1).
Regarding claim 5, Dongjie and Yang don’t explicitly teach wherein the producing the POI embeddings is performed using a neural network language model.
However Gratton, in the same field of endeavor, teaches wherein the producing the POI embeddings is performed using a neural network language model (Gratton: Para. 101, 703, 896, 1027; neural networks; natural language processing; defining nearby POI; embedded).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101) and the user interface (Gratton: Para. 570) with a reasonable expectation of success because the user can insert and edit preferences, categories, locations, time, severity improving the data extract and store for the POIs (Gratton: Para. 302, 372, 404).
Regarding claim 7, Dongjie and Yang don’t explicitly teach wherein the determining AOI embeddings is performed using a neural network language model.
However Gratton, in the same field of endeavor, teaches wherein the determining AOI embeddings is performed using a neural network language model (Gratton: Para. 101, 208, 703, 896; neural networks; natural language processing; AOIs; embedded).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101) and the user interface (Gratton: Para. 570) with a reasonable expectation of success because the user can insert and edit preferences, categories, locations, time, severity improving the data extract and store for the POIs (Gratton: Para. 302, 372, 404).
Regarding claim 8, Dongjie teaches the memory of claim 1, wherein the instructions cause the data processing apparatus to organize POIs into multi-level spatial hierarchies (Dongjie: Para. 111; variational graph auto-encoder (VGAE), a computer-supported program, which may be generally referred to as graph embedding; geographical spatial relationship between the virgin area and its contexts).
Dongjie and Yang don’t explicitly teach allowing the neural network language model to analyze both spatial and semantic attributes of POIs.
However Gratton, in the same field of endeavor, teaches allowing the neural network language model to analyze both spatial and semantic attributes of POIs (Gratton: Para. 101, 896, 1027; neural networks; natural language processing and/or image analysis, geo determination module can infer an event location from the text and image; defining nearby POI).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101) and the user interface (Gratton: Para. 570) with a reasonable expectation of success because the user can insert and edit preferences, categories, locations, time, severity improving the data extract and store for the POIs (Gratton: Para. 302, 372, 404).
Regarding claim 13, Dongjie teaches the method of claim 11, …….. to encode geographic and functional attributes of POIs into N-dimensional embeddings (Dongjie: Para. 14; a land-use configuration is defined as a longitude-latitude-channel tensor, where each channel is a category of points of interest (“POIs”) and the value of an entry is the number of POIs).
Dongjie and Yang don’t explicitly teach wherein generating a semantic vector for each POI includes applying a neural network language model trained.
However Gratton, in the same field of endeavor, teaches wherein generating a semantic vector for each POI includes applying a neural network language model trained (Gratton: Para. 101, 896, 1027; neural networks; natural language processing; defining nearby POI).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101) and the user interface (Gratton: Para. 570) with a reasonable expectation of success because the user can insert and edit preferences, categories, locations, time, severity improving the data extract and store for the POIs (Gratton: Para. 302, 372, 404).
Regarding claim 18, Dongjie teaches a system for predicting land use categories within a user-selected area of interest (AOI), the system comprising: a data processing apparatus configured to perform operations comprising: (Dongjie: Para. 24, 67; one or more processors and connected computer-accessible memory or data storage) retrieving, from multiple geospatial data sources, information regarding points of interest (POIs) within a defined AOI, the information comprising spatial coordinates and categorical identifiers for each POI (Dongjie: Para. 24, 103-104; first, multiple data sources, such as urban-community related data (for example, housing prices), points-of-interest data, and human mobility data (for example, taxicab GPS traces) are collected; geographical area is visually defined by a set of POIs); applying a standardized tagging schema to normalize categorical identifiers across POIs from diverse data sources, creating a unified semantic format for subsequent processing (Dongjie: Para. 152; graph data base contains the data that is provided to the generator module; trained encoder module converts that data to vector input data that can be understood by the generator module), …… and integration of POIs based on their harmonized attributes (Dongjie: Para. 196; generated land-use tensor has multiple channels and that each channel has many blocks, these channels of the land-use tensor were merged into one by setting the dominated POI category; merged solution reflects POI distribution in geographical spatial space); ……. , and segmenting the AOI into nested polygons according to the hierarchical boundary levels (Dongjie: Para. 91-92; spatial attributed graph database of nodes that define the areas surrounding the virgin territory; graph database includes respective arrays of data for each of the nodes), creating a spatial structure where each polygon at a given level is nested within polygons at higher levels (Dongjie: Para. 100; a central area is a generally square geographical area that is centered on a geographical location, where there is an unplanned area); mapping each POI to a set of spatial polygons across hierarchical levels that contain the POI’s spatial coordinates, thereby generating hierarchical associations that encode both local and regional spatial context for each POI (Dongjie: Para. 24; a given geographical area is visually defined by a set of POIs and their corresponding locations (e.g., latitudes and longitudes) and urban functionality categories (e.g., shopping, banks, education, entertainment, residential)); generating a high-dimensional semantic vector for each POI based on its standardized categorical identifier and assigned hierarchical polygons, wherein each vector captures both spatial and semantic attributes of the POI (Dongjie: Para. 79, 93, 152; graph data base contains the data that is provided to the generator module based on which it generates the land use tensor); computing an aggregate AOI embedding by combining the semantic vectors of POIs within the AOI (Dongjie: Para. 197, Fig. 11; visualization of results of land-use plans; blocks represent POI categories), applying term frequency-inverse document frequency (TF-IDF) weighting to emphasize distinctive POIs relevant to the AOI’s land use characteristics (Dongjie: Para. 158; total number of mobile check-in events of an area, denoted by freq, and the diversity of POI of an area, denoted by div, are calculated); training a classifier model using the computed AOI embeddings from multiple AOIs labeled with land use categories, the model configured to predict land use type based on the spatial and semantic information encoded in the AOI embeddings (Dongjie: Para. 93, 97; converting the characteristics of the surrounding contexts into a low-dimensional vector (latent embedding) using a graph data encoder supported in the system); and …… ; initiate a prediction operation to receive a displayed output of the predicted land use category for the selected AOI, generated by the classifier model and derived from the unified semantic and spatial embeddings of POIs within the AOI (Dongjie: Para. 12; inputting planning input data comprising context data for a virgin geographical territory to the generator module after the training, and generating land-use data with the trained generator module that defines a land-use plan for the virgin territory); and display confidence metrics for the predicted land use category, save the selected AOI, its predicted category, and associated prediction details (Dongjie: Para. 13; resulting good land-use plan tensor is then output or displayed in a user-comprehensible report format).
Dongjie doesn’t explicitly teach including the removal of duplicate POIs ……. constructing a multi-level spatial hierarchy by: accessing hierarchical boundary data representing physical infrastructure, including road networks, associated with the AOI, the hierarchy comprising spatial levels that represent progressively broader regions within the AOI.
However Yang, in the same field of endeavor, teaches including the removal of duplicate POIs (Yang: Para. 101; identical POIs in each preferred travel route can be merged into one POI) ……. constructing a multi-level spatial hierarchy by: accessing hierarchical boundary data representing physical infrastructure, including road networks, associated with the AOI (Yang: Para. 60; POI associated with the positioning terminal in the road networks, when an overlap degree between the positioning region of the positioning terminal and a positioning region of the at least one POI ), the hierarchy comprising spatial levels that represent progressively broader regions within the AOI (Yang: Para. 156; display layers can be superimposed with the geographical information to generate a heat map).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101) with a reasonable expectation of success because the number of times each POI appears determines the popularity of the POI and the navigational route (Yang: Para. 102).
Dongjie and Yang don’t explicitly teach a user interface configured to enable a user to: interact with an interactive map displayed on the user interface to navigate, zoom, and pan across different geographic regions to locate an AOI of interest; select and define the AOI within the map by specifying boundaries at varying spatial granularities through hierarchical polygon levels, each selection dynamically updating the classifier model’s analysis based on the harmonized POI data within the selected AOI; refine the AOI boundaries within the selected granularity level by adjusting the AOI’s spatial extent on the map, thereby customizing the area covered in the classifier model’s land use prediction ……. facilitating comparative analysis across multiple AOIs at varying spatial granularities.
However Gratton, in the same field of endeavor, teaches a user interface configured to enable a user to: interact with an interactive map displayed on the user interface to navigate, zoom, and pan across different geographic regions to locate an AOI of interest (Gratton: Para. 474, 570; app interface can zoom in and center; clicking on navigation controls; clickable or hoverable e.g., with a mouse or other input device); select and define the AOI within the map by specifying boundaries at varying spatial granularities through hierarchical polygon levels, each selection dynamically updating the classifier model’s analysis based on the harmonized POI data within the selected AOI (Gratton: Para. 120, 506; user can select specific points that are connected to form a boundary that encloses a region of interest; cells of different geometries can be used); refine the AOI boundaries within the selected granularity level by adjusting the AOI’s spatial extent on the map, thereby customizing the area covered in the classifier model’s land use prediction (Gratton: Para. 122; hierarchical spatial data structure which subdivides space into buckets of grid shape; geohashes offer properties like arbitrary precision) ……. facilitating comparative analysis across multiple AOIs at varying spatial granularities (Gratton: Para. 122; hierarchical spatial data structure which subdivides space into buckets of grid shape; geohashes offer properties like arbitrary precision).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101) and the user interface (Gratton: Para. 570) with a reasonable expectation of success because the user can insert and edit preferences, categories, locations, time, severity improving the data extract and store for the POIs (Gratton: Para. 302, 372, 404).
Regarding claim 19, Dongjie and Yang don’t explicitly teach wherein the user interface provides a dynamic refinement tool enabling the user to interactively adjust the spatial extent and granularity of the AOI by zooming in or out on the interactive map, thereby updating the classifier model’s analysis in real-time based on the adjusted AOI boundaries, and displaying the refined predicted land use category as the user redefines the AOI.
However Gratton, in the same field of endeavor, teaches wherein the user interface provides a dynamic refinement tool enabling the user to interactively adjust the spatial extent and granularity of the AOI by zooming in or out on the interactive map, thereby updating the classifier model’s analysis in real-time based on the adjusted AOI boundaries, and displaying the refined predicted land use category as the user redefines the AOI (Gratton: Para. 474, 570; app interface can zoom in and center; clicking on navigation controls; clickable or hoverable e.g., with a mouse or other input device).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101) and the user interface (Gratton: Para. 570) with a reasonable expectation of success because the user can insert and edit preferences, categories, locations, time, severity improving the data extract and store for the POIs (Gratton: Para. 302, 372, 404).
Regarding claim 20, Dongjie teaches the system of claim 18, wherein the classifier model adapts the dimensionality of the POI embeddings according to the selected spatial granularity of the AOI to balance processing efficiency and prediction accuracy (Dongjie: Para. 13; generator receives this assessment value and generates a new land-use tensor to try to improve the assessment value; cycle continues until it converges, i.e., the generator produces a land-use tensor that the discriminator assesses as adequately good, i.e., it produces assessment data that reaches a threshold quality value), and wherein the user interface further provides a visual breakdown of key semantic features within the AOI that contributed to the predicted land use category, enhancing user understanding of the classifier model’s output and improving interpretability across different spatial granularities (Dongjie: Para. 13, 77; displayed in a user-comprehensible report format; land-use plan data that is output by the generator module of the system and that is assessed by the discriminator module constitutes stored data defining an array or tensor that is organized in a data structure).
Claims 2 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Dongjie et al. (US Publication 2023/0394197 A1) in view of Yang et al. (US Publication 2018/0306594 A1) and in further view Gratton et al. (US Publication 2021/0081559 A1).
Regarding claim 2, Dongjie and Yang don’t explicitly teach wherein the unified format comprises a standardized set of tags, including OpenStreetMap tags.
However Mangold, in the same field of endeavor, teaches wherein the unified format comprises a standardized set of tags, including OpenStreetMap tags (Mangold: Para. 64; bulk Geocoding approach based on OpenStreetMap; it supports advanced query logic with 1000s of location features (tags)).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101), and OpenStreetMap tags (Mangold: Para. 64) with a reasonable expectation of success because OpenStreetMap provides the bulk location geocoding needed for integrated solutions (Mangold: Para. 64).
Regarding claim 12, Dongjie and Yang don’t explicitly teach wherein the standardized tagging schema comprises OpenStreetMap (OSM) tags to facilitate cross-source compatibility and semantic coherence.
However Mangold, in the same field of endeavor, teaches wherein the standardized tagging schema comprises OpenStreetMap (OSM) tags to facilitate cross-source compatibility and semantic coherence (Mangold: Para. 64; bulk Geocoding approach based on OpenStreetMap; it supports advanced query logic with 1000s of location features (tags)).
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101), and OpenStreetMap tags (Mangold: Para. 64) with a reasonable expectation of success because OpenStreetMap provides the bulk location geocoding needed for integrated solutions (Mangold: Para. 64).
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Dongjie et al. (US Publication 2023/0394197 A1) in view of Yang et al. (US Publication 2018/0306594 A1) and in further view Chatterjee et al. (US Publication 2020/0004823 A1).
Regarding claim 3, Dongjie teaches the memory of claim 1, wherein tags associated with each POI are modeled as words (Dongjie: Para. 24; set of POIs and their corresponding locations (e.g., latitudes and longitudes) and urban functionality categories (e.g., shopping, banks, education, entertainment, residential)), and are hierarchically grouped from lowest-level polygons (Dongjie: Para. 93; vector to be input into the generator is derived from the graph database by converting the characteristics of the surrounding contexts into a low-dimensional vector) to highest-level polygons (Dongjie: Para. 24; land-use configuration plan of a given geographical area is visually defined by a set of POIs and their corresponding locations and urban functionality categories; land-use configuration is indeed a high-dimensional indicator).
Dongjie and Yang don’t explicitly teach such that: groups of POI tags corresponding to highest-level polygons form POI-tag sentences, groups of POI-tag sentences corresponding to next lower-level polygons form POI-tag paragraphs, groups of POI-tag paragraphs corresponding to before-lowest level polygons form POI-tag documents, and groups of POI-tag documents corresponding to the lowest level polygons form a POI-tag corpus.
However Chatterjee, in the same field of endeavor, teaches such that: groups of POI tags corresponding to highest-level polygons form POI-tag sentences, groups of POI-tag sentences corresponding to next lower-level polygons form POI-tag paragraphs, groups of POI-tag paragraphs corresponding to before-lowest level polygons form POI-tag documents, and groups of POI-tag documents corresponding to the lowest level polygons form a POI-tag corpus.
Chatterjee teaches point of interest processing device for extracting POI from natural language sentences (Chatterjee: Para. 5). Chatterjee teaches a raw corpus of natural language sentences is taken and each sentence is tagged with POI tags. Then the POI of the sentence is determined (Chatterjee: Para. 26). The system taught takes a corpus of data and tags each sentence. From this the corpus could be summarized down to the most relevant paragraphs, then the most relevant sentences, and finally the most relevant words. It would be obvious to one of ordinary skill in the art to us this format to take a corpus of data for a POI of a building and make progressively smaller tags until each POI is modeled as words.
It would have been obvious to one having ordinary skill in the art to modify the trainable land-use AI module (Dongjie: Para. 8) with merging identical POIs (Yang: Para. 101), and the natural language processing leading to tags (Chatterjee: Para. 5) with a reasonable expectation of success because the natural language processing through tags find the most vital information of a large body of information (Chatterjee: Para. 3, 5).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LAURA E LINHARDT whose telephone number is (571) 272-8325. The examiner can normally be reached on M-TR, M-F: 8am-4pm.
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, Angela Ortiz can be reached on (571) 272-1206. The fax phone number for the organization where this application or proceeding is assigned is (571) 273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at (866) 217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call (800) 786-9199 (IN USA OR CANADA) or (571) 272-1000.
/L.E.L./Examiner, Art Unit 3663
/ANGELA Y ORTIZ/Supervisory Patent Examiner, Art Unit 3663
Prosecution Insights