MFTB Holdco, Inc.

Techniques are described for using computing devices to perform automated operations involving, for an image acquired at a building and having visual data that shows portions of multiple separate rooms or other spatial regions at the building, automatically analyzing and manipulating visual data of the image to perform white balancing corrections separately for different parts of the image corresponding to the different spatial regions, such as to separately correct for different illumination levels in the different spatial regions. The described techniques may further include using one or more resulting modified images with white balancing corrections in one or more further automated manners, such as to determine one or more types of building information (e.g., a building floor plan) for an as-built multi-room building, and optionally further using the determined building information to provide navigational data for the building.

Techniques are described for performing automated operations involving automatically quantifying differences between pairs of dwellings based on differences between the dwellings'dwelling attributes and the assessed contributions of such differing dwelling attributes to differences in overall dwelling utility of the two dwellings of a pair, and using determined difference quantifications between various dwellings for providing search results or other automated functionality based on dwelling similarity. In at least some situations, a difference quantification between a candidate dwelling and a target dwelling is determined based on a cumulative total of the absolute values of positive and negative utility scores associated with the differing dwelling attributes'values for the target dwelling and that candidate dwelling, such as by using a predictive model (e.g., a neural network model) trained to predict an overall utility score for a dwelling based on a plurality of dwelling attributes and associated values for that dwelling.

Techniques are described for performing automated operations related to determining and providing information about buildings in multiple geographical regions in response to a query with partial descriptions of the regions and optionally partial descriptions of one or more additional locations in the regions, such as to automatically respond to a free-form natural language request having partial descriptions of names of multiple proximate geographical regions and of one or more point-of-interest (POI) locations by determining the intended geographical regions and POI locations and using them in generating corresponding response information. The described techniques may do inter-position distance filtering for at least some combinations of geographical region candidates and POI location candidates, and using a top-ranked combination that has a candidate for each geographical region and POI location designation in the query to determine responsive information for the received query.

Techniques are described for using computing devices to perform automated operations for automatically generating information about attributes of buildings from automated analysis of building information that includes floor plans and acquired building images and to subsequently using the generated building information in one or more further automated manners. In some situations, such automated generation of building information includes automatically determining objects in a building and other attributes of the building, and automatically generating descriptions about the determined building attributes. Information about such determined attributes and generated descriptions may be used in various automated manners, including for updating and/or validating information in existing building descriptions, for determining matching buildings that have similarities to indicated building descriptions or other specified criteria, for controlling device navigation (e.g., autonomous vehicles), for display on client devices in corresponding graphical user interfaces, etc.

Real-time offer negotiation assistance is provided. In examples, an offer negotiation engine receives a proposed offer from a user. An offer grading model trained on historical data regarding listings, offers, and sales of homes evaluates the proposed offer and generates an offer grade. An offer guidance generator generates guidance for the proposed offer, such as recommendations to improve the proposed offer. In further examples, the offer negotiation engine receives an offer prompt from the user. An offer generation model trained on the historical data generates a proposed offer based on the offer prompt.

A facility for estimating a subject home's value is described. For each of one or more direct home attributes, the facility determines the value of the direct home attribute for the subject home. For each of a plurality of arbitrary geographic regions of different sizes containing the subject home, the facility determines information relating to the geographic region as a whole. The facility then subjects the determined values and information to a statistical home valuation model to obtain an estimated value of the subject home.

Techniques are described for performing automated operations related to determining and providing information about dwellings for searches with search criteria combining data of multiple modes, such as at least free-form natural language text and one or more images. In some situations, the described techniques include training machine learning (“ML”) model(s) to encode semantic information about dwellings from multiple data modes into corresponding vector-based embeddings, using the trained ML model(s) to generate vector embeddings for dwellings in one or more geographical areas to represent dwelling data of multiple data modes, using the trained ML model(s) to generate vector embeddings for a search query with multiple search criteria including data of multiple modes, and determining one or more matching target dwellings for the query by matching generated vector embeddings of candidate dwellings to the generated vector embedding(s) for the query, with information about matching target dwelling(s) then further used.

Techniques are described for using computing devices to perform automated operations involving interactions between multiple computing devices and systems as part of automatically scheduling an in-person access to a physical property involving multiple unaffiliated users traveling from disparate locations to the physical property, such as for an access to a house or other building. In some situations, the automated operations include exchanging electronic communications between computing devices to provide multiple sequential telephone call interactions and concurrent in-application interactions with multiple candidate users regarding participation in the group.

Techniques are described for performing automated operations related to determining and using information about one or more user-specific predicted attributes of dwellings that users will occupy in the future. The described techniques may include generating one or more predictive models trained to provide information about one or more target dwelling attributes of interest, such as to analyze training data about interactions of one or more types by a plurality of users with a plurality of dwellings before those users select a final dwelling to acquire and/or occupy, and to generate and train the predictive model(s) based on the training data to predict a value of each of the one or more target dwelling attributes for a target dwelling that a user will later acquire and/or occupy, and may further include using predicted target dwelling attribute values to provide dwelling-related information to one or more other users.

Techniques are described for using computing devices to perform automated operations for using generated building information to further generate and present visual data enhancements on images that are captured by and displayed on a mobile device in the building (e.g., concurrent with capture of the images by a camera of the mobile device, such as in a real-time or near-real-time manner with respect to image capture), such as using descriptive information about a building that is generated from analysis of acquired building images and optionally other building information (e.g., floor plans), and such as to improve navigation of the building (e.g., for autonomous vehicles) and provide other functionality as the mobile device moves through the building. The descriptive building information may include structural elements and other objects identified in the building and other determined attributes of the building, and automatically generated textual descriptions of the objects and other attributes.