DETAILED ACTION
Status of Claims
This Action is in response to App. 19/206,813 filed 05/13/2025 with priority to Provisional Application 63/646,211 filed 05/13/2024. Claims 1-19 are currently pending and have been examined.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 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 1-19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites the steps of generating and sending prompts to users, receiving information in response to prompts, and either requesting additional information through additional prompts or generating a report.
The invention as claimed, the invention is directed towards a certain method of organizing human activity, specifically commercial interaction and marketing/sales activity. As currently claimed, the invention is directed towards the structuring and management of people to achieve commercial goals (similar to In re Ferguson), and generation of reports based on received information (similar to OIP Technology and Electric Power Group). But for the recitation of electronic communication with user devices and machine learning, the invention is directed towards management of people and activities, and mental process of creating reports based on received information. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. But for the utilization of the network communication, the invention further manages commercial activities. Accordingly, the claim recites judicial exceptions.
This judicial exception is not integrated into a practical application. In particular, the claim recites generic computer components performing the steps including utilizing trained learning models. The generic computer components are recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of providing/receiving information over a network, generating reports) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Furthermore, although the claims further recite a trained model, this is still a particular type of instructions for execution by generic computer processor. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The 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 practical application, the additional element of using a processor to perform the steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claim is not patent eligible.
The dependent claims are further directed towards the judicial exception without significantly more. The dependent claims provide limitations on the particular type of computer instructions (such as claim 2, 6), additional abstract ideas such as decision making and analysis (such as claims 3-4), extra-solution activity of receiving and outputting information (such as claim 5, 7-8). These are still directed towards the judicial exception as these further define the abstract elements such as further defining the information and relationship between the information or extra-solution activity. They are not significantly more as they do not further integrate the judicial exception into a practical application and the additional element amounts to no more than mere instructions to apply the exception using a generic computer component. The dependent claims is not patent eligible.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claim(s) 1, 9-10, 12 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Kwak et al. (US 11392998 B1) (hereafter Kwak).
As per claim 1:
A method for generating a real-estate property (REP) assessment report by a computing system, comprising:
a) generating, by the computing system, a customized instruction instructing a user to capture, using a user device, at least a further multimedia content associated with the REP, wherein the customized instruction is generated based on a multimedia content received from a user device; (See Kwak col. 12 line 11, “Based on the instructions that remote device 404 receives from server 403, remote device 404 may prompt the user to inspect the property structure at step 810. An example of such a prompt is depicted in FIG. 9. After identifying water heater 906, a prompt 905 is displayed to the user. Prompt 905 states that a water heater has been detected and provides further instructions for the user to move closer to the water heater and capture an image of the water heater's Rating Plate.” Kwak discloses a server generating and providing instructions for display on the user device for capturing multimedia content.)
b) transmitting, from the computing system, the customized instruction toward the user device; (See Kwak col. 9 line 7, “Once the remote device has helped a used navigate to a predetermined location, the remote device may prompt the user to collect data in step 508. Collecting data can include capturing images or other sensory information about local environment. In some cases, collecting data may also include receiving manual user input, such as selections from a drop-down menu, tags for images, notes or other information.” Kwak discloses generating and providing prompts to a user device for capture multimedia content.)
c) receiving, at the computing system, the at least a further multimedia content from the user device; (See Kwak col. 9 line 15, “In step 510, the captured data, including any image data, could be analyzed. In some cases, one or more analyses could be performed at the remote device. In other cases, the remote device could send image data and other kinds of data to a server for further processing. In either case, in step 512 the results of the analysis could be used to update property information in the virtual property notebook and/or in the property information storage system 102.” Kwak discloses the concept of receiving multimedia content from the user device.)
d) when additional multimedia content is not required by the computing system to develop a REP assessment report for the REP that reflects a current state of the REP, developing by the computing system, the REP assessment report for the REP that reflects the current state of the REP based upon all multimedia content received from the user device; and (See Kwak col. 5 line 11, “In a fourth step 208, users may receive customized reports of properties they visited. The report can help summarize and compare features across multiple properties the user visited. This reporting feature may be very helpful for would-be home buyers who often find it difficult to recall details about all the homes they've viewed in a short period of time. Optionally, of course, the report could also include one or more properties the user has not visited. In this way, the system can also be used to help users identify homes or other properties they would like to visit.” Kwak discloses generating an assessment report based on collected multimedia content.)
e) when additional multimedia content is required by the computing system to generate the REP assessment report for the REP that reflects the current state of the REP, generating by the computing system a subsequent customized instruction instructing the user to capture the additional multimedia content and repeating (b) through (e) using as the customized instruction the subsequent customized instruction and the additional multimedia content as the further multimedia content. (See Kwak col. 10 line 13, “Next, in step 604, the remote device may capture images of the surroundings and/or other sensory data corresponding to the surroundings. A remote device system may instruct a user to capture images or other sensory information about the local environment. For example, the remote device could prompt a user to “focus the camera on the kitchen countertop and take a picture.” Alternatively, the system could automatically take pictures (or video) of one or more physical structures as they are automatically identified by an image detection/recognition algorithm. In some cases, a user may be prompted to aim the camera at a particular physical structure, or in a particular direction, and the remote device may automatically capture images.” Kwak discloses the concept of iteratively prompting the user for additional multimedia content including particular customized instructions for additional content.)
As per claim 9:
A method for generating a real-estate property (REP) assessment report by a computing system, comprising:
a) generating, by the computing system, a plurality of customized instructions, each customized instruction being for instructing a respective one of a plurality of users to capture, using user devices that are associated with a respective one of the users, at least a further multimedia content associated with the REP, wherein each customized instruction is generated based on multimedia content received from each respective one the user devices; (See Kwak col. 12 line 11, “Based on the instructions that remote device 404 receives from server 403, remote device 404 may prompt the user to inspect the property structure at step 810. An example of such a prompt is depicted in FIG. 9. After identifying water heater 906, a prompt 905 is displayed to the user. Prompt 905 states that a water heater has been detected and provides further instructions for the user to move closer to the water heater and capture an image of the water heater's Rating Plate.” Kwak discloses a server generating and providing instructions for display on the user device for capturing multimedia content. See also Kwak col. 3 line 4, “By automatically capturing and analyzing image information about property structures (such as appliances or built-in features like cabinets), the system and method improve the efficiency of the assessment process. The system and method also provide tools for building a shared, and possibly open, database that can be accessed by multiple parties including buyers, sellers, real estate agents, inspectors, assessors and others, thereby making property information more readily available to all participants and improving the efficiency of real estate markets.” Kwak discloses managing multiple user devices.)
b) transmitting, from the computing system, each respective customized instruction toward a respective one of the user devices; (See Kwak col. 9 line 7, “Once the remote device has helped a used navigate to a predetermined location, the remote device may prompt the user to collect data in step 508. Collecting data can include capturing images or other sensory information about local environment. In some cases, collecting data may also include receiving manual user input, such as selections from a drop-down menu, tags for images, notes or other information.” Kwak discloses generating and providing prompts to a user device for capture multimedia content.)
c) receiving, at the computing system, each of the at least a further multimedia content from each of the user devices; (See Kwak col. 9 line 15, “In step 510, the captured data, including any image data, could be analyzed. In some cases, one or more analyses could be performed at the remote device. In other cases, the remote device could send image data and other kinds of data to a server for further processing. In either case, in step 512 the results of the analysis could be used to update property information in the virtual property notebook and/or in the property information storage system 102.” Kwak discloses the concept of receiving multimedia content from the user device.)
d) when additional multimedia content is not required by the computing system to develop a REP assessment report for the REP that reflects a current state of the REP, developing by the computing system, the REP assessment report for the REP that reflects the current state of the REP based upon all multimedia content received from the user devices; and (See Kwak col. 5 line 11, “In a fourth step 208, users may receive customized reports of properties they visited. The report can help summarize and compare features across multiple properties the user visited. This reporting feature may be very helpful for would-be home buyers who often find it difficult to recall details about all the homes they've viewed in a short period of time. Optionally, of course, the report could also include one or more properties the user has not visited. In this way, the system can also be used to help users identify homes or other properties they would like to visit.” Kwak discloses generating an assessment report based on collected multimedia content.)
e) when additional multimedia content is required by the computing system to generate the REP assessment report for the REP that reflects the current state of the REP, generating by the computing system, at least one subsequent customized instruction instructing at least one of the users to capture the additional multimedia content and repeating (b) through (e) using (i) the customized instructions as the at least one subsequent customized instruction and (ii) the additional multimedia content as the further multimedia content. (See Kwak col. 10 line 13, “Next, in step 604, the remote device may capture images of the surroundings and/or other sensory data corresponding to the surroundings. A remote device system may instruct a user to capture images or other sensory information about the local environment. For example, the remote device could prompt a user to “focus the camera on the kitchen countertop and take a picture.” Alternatively, the system could automatically take pictures (or video) of one or more physical structures as they are automatically identified by an image detection/recognition algorithm. In some cases, a user may be prompted to aim the camera at a particular physical structure, or in a particular direction, and the remote device may automatically capture images.” Kwak discloses the concept of iteratively prompting the user for additional multimedia content including particular customized instructions for additional content.)
As per claim 10:
The method of claim 9, wherein the at least one subsequent customized instruction is a plurality of subsequent customized instructions each of the plurality of subsequent customized instructions being for a respective one of the users to perform, and wherein instructing at least one of the users to capture the additional multimedia content instructs at least two of the users to capture respective additional multimedia content. (See Kwak col. 10 line 13, “Next, in step 604, the remote device may capture images of the surroundings and/or other sensory data corresponding to the surroundings. A remote device system may instruct a user to capture images or other sensory information about the local environment. For example, the remote device could prompt a user to “focus the camera on the kitchen countertop and take a picture.” Alternatively, the system could automatically take pictures (or video) of one or more physical structures as they are automatically identified by an image detection/recognition algorithm. In some cases, a user may be prompted to aim the camera at a particular physical structure, or in a particular direction, and the remote device may automatically capture images.” Kwak discloses the concept of iteratively prompting the user for additional multimedia content including particular customized instructions for additional content.)
As per claim 12:
A system for generating a real-estate property (REP) assessment report by a computing system, comprising:
a processing circuitry; and
a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:
(See Kwak col. 16 line 15, “The processes and methods of the embodiments described in this detailed description and shown in the figures can be implemented using any kind of computing system having one or more central processing units (CPUs) and/or graphics processing units (GPUs). The processes and methods of the embodiments could also be implemented using special purpose circuitry such as an application specific integrated circuit (ASIC). The processes and methods of the embodiments may also be implemented on computing systems including read only memory (ROM) and/or random access memory (RAM), which may be connected to one or more processing units. Examples of computing systems and devices include, but are not limited to: servers, cellular phones, smart phones, tablet computers, notebook computers, e-book readers, laptop or desktop computers, all-in-one computers, as well as various kinds of digital media players.” Kwak discloses processing unit and memory storing instructions.)
a) generate, by the computing system, a customized instruction instructing a user to capture, using a user device, at least a further multimedia content associated with the REP, wherein the customized instruction is generated based on a multimedia content received from a user device; (See Kwak col. 12 line 11, “Based on the instructions that remote device 404 receives from server 403, remote device 404 may prompt the user to inspect the property structure at step 810. An example of such a prompt is depicted in FIG. 9. After identifying water heater 906, a prompt 905 is displayed to the user. Prompt 905 states that a water heater has been detected and provides further instructions for the user to move closer to the water heater and capture an image of the water heater's Rating Plate.” Kwak discloses a server generating and providing instructions for display on the user device for capturing multimedia content.)
b) transmit, from the computing system, the customized instruction toward the user device; (See Kwak col. 9 line 7, “Once the remote device has helped a used navigate to a predetermined location, the remote device may prompt the user to collect data in step 508. Collecting data can include capturing images or other sensory information about local environment. In some cases, collecting data may also include receiving manual user input, such as selections from a drop-down menu, tags for images, notes or other information.” Kwak discloses generating and providing prompts to a user device for capture multimedia content.)
c) receive, at the computing system, the at least a further multimedia content from the user device; (See Kwak col. 9 line 15, “In step 510, the captured data, including any image data, could be analyzed. In some cases, one or more analyses could be performed at the remote device. In other cases, the remote device could send image data and other kinds of data to a server for further processing. In either case, in step 512 the results of the analysis could be used to update property information in the virtual property notebook and/or in the property information storage system 102.” Kwak discloses the concept of receiving multimedia content from the user device.)
d) when additional multimedia content is not required by the computing system to develop a REP assessment report for the REP that reflects a current state of the REP, develop by the computing system, the REP assessment report for the REP that reflects the current state of the REP based upon all multimedia content received from the user device; and (See Kwak col. 5 line 11, “In a fourth step 208, users may receive customized reports of properties they visited. The report can help summarize and compare features across multiple properties the user visited. This reporting feature may be very helpful for would-be home buyers who often find it difficult to recall details about all the homes they've viewed in a short period of time. Optionally, of course, the report could also include one or more properties the user has not visited. In this way, the system can also be used to help users identify homes or other properties they would like to visit.” Kwak discloses generating an assessment report based on collected multimedia content.)
e) when additional multimedia content is required by the computing system to generate the REP assessment report for the REP that reflects the current state of the REP, generate by the computing system a subsequent customized instruction instructing the user to capture the additional multimedia content and repeating (b)through (e) using as the customized instruction the subsequent customized instruction and the additional multimedia content as the further multimedia content. (See Kwak col. 10 line 13, “Next, in step 604, the remote device may capture images of the surroundings and/or other sensory data corresponding to the surroundings. A remote device system may instruct a user to capture images or other sensory information about the local environment. For example, the remote device could prompt a user to “focus the camera on the kitchen countertop and take a picture.” Alternatively, the system could automatically take pictures (or video) of one or more physical structures as they are automatically identified by an image detection/recognition algorithm. In some cases, a user may be prompted to aim the camera at a particular physical structure, or in a particular direction, and the remote device may automatically capture images.” Kwak discloses the concept of iteratively prompting the user for additional multimedia content including particular customized instructions for additional content.)
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.
Claim(s) 2-8, 11, 13-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kwak et al. (US 11392998 B1) (hereafter Kwak), in view of Tan et al. (US 11783574 B2) (hereafter Tan).
As per claim 2:
Although Kwak discloses the above-enclosed invention including the concept of utilizing machine learning and prompting the user for additional images, Kwak fails to explicitly disclose the concept of the machine learning model to further develop the prompt.
However Tan as shown, which talks about vehicle parking verification including image processing, teaches the concept of the machine learning model developing prompts for additional media.
The method of claim 1, wherein generating any of the customized instruction and the subsequent customized instruction further comprises supplying at least a last received multimedia content from the user device to a trained model that is adapted to generate a customized instruction for the user directing the user to capture multimedia content indicative of a further aspect of the current state of the REP using the user device. (See Tan col. 4 line 1, “In some embodiments, the server (140) may contain an image processor with a machine learning model, which may be a deep convolutional neural network that is configured to receive and process an image to generate a model output related to the validation of a PMV's parking, such as whether the PMV is validated as having good parking, an image error code indicating issues relating to the image being insufficient for proper analysis, and/or a vehicle parking error code indicating that the PMV parking is violating one or more parking rules. If the image processing machine learning model detects that the image data is still insufficient for proper analysis, because of poor lighting, improper orientation of view, or too close or too far from the vehicle in view, it may generate model output portion related to the image error code. The mobile device (120) may then prompt the user to capture additional image data with more or less lighting, and different orientation or viewing distance. If the image processing machine learning model detects that the PMV is improperly parked, due to being too close to the edge of the sidewalk, or being obstructing pedestrian traffic, then a vehicle parking error may be generated. The model may determine these factors by, for example, being trained on a dataset of images if improperly parked PMVs. For example, a PMV in the middle of a sidewalk rather than on the side may be assigned an identification if improper parking. The system may also assign values to determine an improper parking score. Example values can be on a 1-5 range for distance from an optimal parking location, e.g., not in the middle and not about to fall into a road. Other values can include how far the PMV is leaning, how close it is to a door or driveway, whether it is near a bike stand or tree, or whether it is near another high-traffic area, such as a park entrance. The values can be added to determine the improper parking score, and if they exceed (or do not meet) a predetermined score, the system may determine that the PMV is improperly parked.” Tan teaches the concept of the machine learning model to determine inadequacies of an image and further generating specific prompts to address the inadequacies.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Tan with the invention of Kwak. As shown, Kwak discloses the concept of prompting users to capture media for processing by a machine learning model to determine the characteristics of a property and providing additional prompts for media. Tan further teaches the concept of the machine learning model to further identify the issues with media which prevents processing such as angle or lighting, and further prompting for additional media to address the identified issues. Tan teaches this concept such that the prompts provided to users can specifically allow for the machine learning algorithm to process the information (See Tan col. 4 line 1). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Tan to further prompt a user based on the issues with previous media to further enable the learning model to process information.
As per claim 3:
The method of claim 2, wherein the trained model is further adapted to determine when additional multimedia content is not required by the computing system to develop the REP assessment report for the REP. (See Kwak col. 11 line 1, “In step 612, the remote device may guide the user to a new location to collect further data. This process can be repeated to gather further property information about at various locations within the property. It is contemplated that the system could guide a user through a property in a predetermined manner or in an ad hoc manner.” Kwak discloses the concept of not requiring additional information for a particular area of the property. See also Tan fig.2 and col. 11 line 59, “At block (260), if the PMV's parking is not validated, mobile device (120) may prompt the user to repark the PMV and/or recapture image data. For example, the app on the mobile device (120) may display a graphic indication, such as a flashing watermark in a specific color (red for example) or an error message text, or give off a sound pattern or a vibration pattern to indicate to the user that the parking validation was not successful, to prompt the user to repark the PMV and/or recapture image data.” Tan further teaches the concept of determining adequate media is received.)
As per claim 4:
The method of claim 2, wherein the trained model is further adapted to develop the REP assessment report for the REP. (See Kwak col. 11 line 60, “In step 806, server 403 may analyze the image information and identify any appliances or other kinds of property structures. Specifically, the image information may be processed by one or more machine learning and/or machine vision algorithms to detect and classify the state of one or more physical structures. As an example, FIG. 9 depicts a situation where remote device 404 captures images in a closet 902 of a home. This image is fed into a machine learning module configured to detect and classify property structures. After analyzing the image (in step 804), the system identifies water heater 906.” See also Kwak col. 5 line 62, “From the menu a user may select third option 314 to generate a property report. As used herein, the term “property report” refers to any collection of information about a property. Reports could include a raw listing of all data related to each property, a particular subset of information or an automated summary. A property report may help users to organize and compare properties. As an example, home buyers often go on a home viewing spree, seeing five, ten or even more homes for sale in one day. It may be difficult for the buyers to remember the details (the layout, the number of bedrooms, etc.) for each separate home.” Kwak discloses the model to be adapted to generate a report.)
As per claim 5:
The method of claim 2, wherein the trained model is further adapted to generate outputs, other than instructions, allowing management of interactions with the user. (See Kwak col. 10 line 40, “Next, in step 610, the remote device may optionally prompt a user to provide additional information about one or more identified features. As an example, in FIG. 7 the user is further provided with prompt 704 and asked to select a material for the countertop (granite, laminate or concrete). In other cases, a user could be prompted to apply custom tags or labels to images or identified features. Because obtaining good labeled training data for machine learning systems is often time consuming and expensive, the process depicted in FIGS. 6 and 7 may be especially helpful. Specifically, the method provides labeled training data that is generated from images and user given tags/labels.” Kwak discloses providing different types of outputs aside from prompts.)
As per claim 6:
The method of claim 2, wherein training the model comprises obtaining at least one training data set. (See Kwak col. 10 line 58, “It may be appreciated that the method described in FIG. 6 can be applied to a variety of physical structures. For example, a system could identify molding and prompt a user to input the type of molding (for example, crown molding or cove molding). Likewise, a system could identify flooring and prompt a user to input the type of material used in the floors. With time, as a system is trained on additional data, the system may learn to identify not only the type of physical structure (for example, a door or a water heater), but the system can also learn to identify materials or other features.” Kwak discloses obtaining training data set.)
As per claim 7:
The method of claim 2, wherein training the model comprises: receiving, from the user device, at least one indication regarding the REP; and supplying the indication to the model. (See Kwak col. 10 line 40, “Next, in step 610, the remote device may optionally prompt a user to provide additional information about one or more identified features. As an example, in FIG. 7 the user is further provided with prompt 704 and asked to select a material for the countertop (granite, laminate or concrete). In other cases, a user could be prompted to apply custom tags or labels to images or identified features. Because obtaining good labeled training data for machine learning systems is often time consuming and expensive, the process depicted in FIGS. 6 and 7 may be especially helpful. Specifically, the method provides labeled training data that is generated from images and user given tags/labels.” Kwak discloses receiving indications regarding the property and providing the indication to the model.)
As per claim 8:
The method of claim 2, wherein training the model further comprises: obtaining pre-inspection data about the REP. (See Kwak col. 7 line 64, “In a first step 502, a remote device could receive property identification information. The property identification information may be a street address (and, optionally, city and state). Alternatively, the property identification information could be an identification number, such as an MLS number or other unique identifier. This information could be obtained from manual input by the user, or by retrieving an address automatically using a navigation application running on the remote device. Next, in step 504, the remote device could retrieve any existing property information and populate the virtual property notebook with this information. In some cases, this step includes sending a request to a server that manages access to property information storage system 102. Once the virtual property notebook is populated with information, the remote device could display some of the information for the user, or provide options for displaying the information.” Kwak discloses obtaining pre-inspection data.)
As per claim 11:
Although Kwak discloses the above-enclosed invention including the concept of utilizing machine learning and prompting the user for additional images, Kwak fails to explicitly disclose the concept of the machine learning model to further develop the prompt.
However Tan as shown, which talks about vehicle parking verification including image processing, teaches the concept of the machine learning model developing prompts for additional media.
The method of claim 10, wherein generating any of the customized instructions and the subsequent customized instructions further comprises supplying at least a last received multimedia content from each of the user devices to a trained model that is adapted to generate a customized instruction for each of the plurality of users directing each of the plurality of users to capture multimedia content indicative of a further aspect of the current state of the REP using the respective user devices. (See Tan col. 4 line 1, “In some embodiments, the server (140) may contain an image processor with a machine learning model, which may be a deep convolutional neural network that is configured to receive and process an image to generate a model output related to the validation of a PMV's parking, such as whether the PMV is validated as having good parking, an image error code indicating issues relating to the image being insufficient for proper analysis, and/or a vehicle parking error code indicating that the PMV parking is violating one or more parking rules. If the image processing machine learning model detects that the image data is still insufficient for proper analysis, because of poor lighting, improper orientation of view, or too close or too far from the vehicle in view, it may generate model output portion related to the image error code. The mobile device (120) may then prompt the user to capture additional image data with more or less lighting, and different orientation or viewing distance. If the image processing machine learning model detects that the PMV is improperly parked, due to being too close to the edge of the sidewalk, or being obstructing pedestrian traffic, then a vehicle parking error may be generated. The model may determine these factors by, for example, being trained on a dataset of images if improperly parked PMVs. For example, a PMV in the middle of a sidewalk rather than on the side may be assigned an identification if improper parking. The system may also assign values to determine an improper parking score. Example values can be on a 1-5 range for distance from an optimal parking location, e.g., not in the middle and not about to fall into a road. Other values can include how far the PMV is leaning, how close it is to a door or driveway, whether it is near a bike stand or tree, or whether it is near another high-traffic area, such as a park entrance. The values can be added to determine the improper parking score, and if they exceed (or do not meet) a predetermined score, the system may determine that the PMV is improperly parked.” Tan teaches the concept of the machine learning model to determine inadequacies of an image and further generating specific prompts to address the inadequacies.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Tan with the invention of Kwak. As shown, Kwak discloses the concept of prompting users to capture media for processing by a machine learning model to determine the characteristics of a property and providing additional prompts for media. Tan further teaches the concept of the machine learning model to further identify the issues with media which prevents processing such as angle or lighting, and further prompting for additional media to address the identified issues. Tan teaches this concept such that the prompts provided to users can specifically allow for the machine learning algorithm to process the information (See Tan col. 4 line 1). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Tan to further prompt a user based on the issues with previous media to further enable the learning model to process information.
As per claim 13:
Although Kwak discloses the above-enclosed invention including the concept of utilizing machine learning and prompting the user for additional images, Kwak fails to explicitly disclose the concept of the machine learning model to further develop the prompt.
However Tan as shown, which talks about vehicle parking verification including image processing, teaches the concept of the machine learning model developing prompts for additional media.
The system of claim 12, wherein the system is further configured to supply at least a last received multimedia content from the user device to a trained model that is adapted to generate a customized instruction for the user directing the user to capture multimedia content indicative of a further aspect of the current state of the REP using the user device. (See Tan col. 4 line 1, “In some embodiments, the server (140) may contain an image processor with a machine learning model, which may be a deep convolutional neural network that is configured to receive and process an image to generate a model output related to the validation of a PMV's parking, such as whether the PMV is validated as having good parking, an image error code indicating issues relating to the image being insufficient for proper analysis, and/or a vehicle parking error code indicating that the PMV parking is violating one or more parking rules. If the image processing machine learning model detects that the image data is still insufficient for proper analysis, because of poor lighting, improper orientation of view, or too close or too far from the vehicle in view, it may generate model output portion related to the image error code. The mobile device (120) may then prompt the user to capture additional image data with more or less lighting, and different orientation or viewing distance. If the image processing machine learning model detects that the PMV is improperly parked, due to being too close to the edge of the sidewalk, or being obstructing pedestrian traffic, then a vehicle parking error may be generated. The model may determine these factors by, for example, being trained on a dataset of images if improperly parked PMVs. For example, a PMV in the middle of a sidewalk rather than on the side may be assigned an identification if improper parking. The system may also assign values to determine an improper parking score. Example values can be on a 1-5 range for distance from an optimal parking location, e.g., not in the middle and not about to fall into a road. Other values can include how far the PMV is leaning, how close it is to a door or driveway, whether it is near a bike stand or tree, or whether it is near another high-traffic area, such as a park entrance. The values can be added to determine the improper parking score, and if they exceed (or do not meet) a predetermined score, the system may determine that the PMV is improperly parked.” Tan teaches the concept of the machine learning model to determine inadequacies of an image and further generating specific prompts to address the inadequacies.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Tan with the invention of Kwak. As shown, Kwak discloses the concept of prompting users to capture media for processing by a machine learning model to determine the characteristics of a property and providing additional prompts for media. Tan further teaches the concept of the machine learning model to further identify the issues with media which prevents processing such as angle or lighting, and further prompting for additional media to address the identified issues. Tan teaches this concept such that the prompts provided to users can specifically allow for the machine learning algorithm to process the information (See Tan col. 4 line 1). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Tan to further prompt a user based on the issues with previous media to further enable the learning model to process information.
As per claim 14:
The system of claim 13, wherein the trained model is further adapted to determine when additional multimedia content is not required by the computing system to develop the REP assessment report for the REP. (See Kwak col. 11 line 1, “In step 612, the remote device may guide the user to a new location to collect further data. This process can be repeated to gather further property information about at various locations within the property. It is contemplated that the system could guide a user through a property in a predetermined manner or in an ad hoc manner.” Kwak discloses the concept of not requiring additional information for a particular area of the property. See also Tan fig.2 and col. 11 line 59, “At block (260), if the PMV's parking is not validated, mobile device (120) may prompt the user to repark the PMV and/or recapture image data. For example, the app on the mobile device (120) may display a graphic indication, such as a flashing watermark in a specific color (red for example) or an error message text, or give off a sound pattern or a vibration pattern to indicate to the user that the parking validation was not successful, to prompt the user to repark the PMV and/or recapture image data.” Tan further teaches the concept of determining adequate media is received.)
As per claim 15:
The system of claim 13, wherein the trained model is further adapted to develop the REP assessment report for the REP. (See Kwak col. 11 line 60, “In step 806, server 403 may analyze the image information and identify any appliances or other kinds of property structures. Specifically, the image information may be processed by one or more machine learning and/or machine vision algorithms to detect and classify the state of one or more physical structures. As an example, FIG. 9 depicts a situation where remote device 404 captures images in a closet 902 of a home. This image is fed into a machine learning module configured to detect and classify property structures. After analyzing the image (in step 804), the system identifies water heater 906.” See also Kwak col. 5 line 62, “From the menu a user may select third option 314 to generate a property report. As used herein, the term “property report” refers to any collection of information about a property. Reports could include a raw listing of all data related to each property, a particular subset of information or an automated summary. A property report may help users to organize and compare properties. As an example, home buyers often go on a home viewing spree, seeing five, ten or even more homes for sale in one day. It may be difficult for the buyers to remember the details (the layout, the number of bedrooms, etc.) for each separate home.” Kwak discloses the model to be adapted to generate a report.)
As per claim 16:
The system of claim 13, wherein the trained model is further adapted to generate outputs, other than instructions, allowing management of interactions with the user. (See Kwak col. 10 line 40, “Next, in step 610, the remote device may optionally prompt a user to provide additional information about one or more identified features. As an example, in FIG. 7 the user is further provided with prompt 704 and asked to select a material for the countertop (granite, laminate or concrete). In other cases, a user could be prompted to apply custom tags or labels to images or identified features. Because obtaining good labeled training data for machine learning systems is often time consuming and expensive, the process depicted in FIGS. 6 and 7 may be especially helpful. Specifically, the method provides labeled training data that is generated from images and user given tags/labels.” Kwak discloses providing different types of outputs aside from prompts.)
As per claim 17:
The system of claim 13, where the system is further configured to obtain at least one training data set when training the model. (See Kwak col. 10 line 58, “It may be appreciated that the method described in FIG. 6 can be applied to a variety of physical structures. For example, a system could identify molding and prompt a user to input the type of molding (for example, crown molding or cove molding). Likewise, a system could identify flooring and prompt a user to input the type of material used in the floors. With time, as a system is trained on additional data, the system may learn to identify not only the type of physical structure (for example, a door or a water heater), but the system can also learn to identify materials or other features.” Kwak discloses obtaining training data set.)
As per claim 18:
The system of claim 13, when training the model, is further configured to: receive, from the user device, at least one indication regarding the REP; and supply the indication to the model. (See Kwak col. 10 line 40, “Next, in step 610, the remote device may optionally prompt a user to provide additional information about one or more identified features. As an example, in FIG. 7 the user is further provided with prompt 704 and asked to select a material for the countertop (granite, laminate or concrete). In other cases, a user could be prompted to apply custom tags or labels to images or identified features. Because obtaining good labeled training data for machine learning systems is often time consuming and expensive, the process depicted in FIGS. 6 and 7 may be especially helpful. Specifically, the method provides labeled training data that is generated from images and user given tags/labels.” Kwak discloses receiving indications regarding the property and providing the indication to the model.)
As per claim 19:
The system of claim 13, when training the model, is further configured to: obtain pre-inspection data about the REP. (See Kwak col. 7 line 64, “In a first step 502, a remote device could receive property identification information. The property identification information may be a street address (and, optionally, city and state). Alternatively, the property identification information could be an identification number, such as an MLS number or other unique identifier. This information could be obtained from manual input by the user, or by retrieving an address automatically using a navigation application running on the remote device. Next, in step 504, the remote device could retrieve any existing property information and populate the virtual property notebook with this information. In some cases, this step includes sending a request to a server that manages access to property information storage system 102. Once the virtual property notebook is populated with information, the remote device could display some of the information for the user, or provide options for displaying the information.” Kwak discloses obtaining pre-inspection data.)
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Marsh (US 20220398762 A1), which talks about remote inspection and appraisal of buildings including image processing and analysis of buildings.
Gowda et al. (US 20220292549 A1), which talks about computer assisted appraisal including utilizing imaging system to determine property characteristics.
Wixson et al. (US 20220269885 A1), which talks about assessing real estate using imaging including retaking images.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VINCENT M CAO whose telephone number is (571)270-5598. The examiner can normally be reached Monday - Friday 11-7.
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, ILANA SPAR can be reached at (571) 270-7537. 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.
/VINCENT M CAO/Primary Examiner, Art Unit 3622
Prosecution Insights