Systems and methods for industrial operations

Abstract

Devices, methods, and systems for cons traction resource operations are provided. The method includes receiving a first dataset including one or more first data, entries associated with at least a first construction resource and generating a spatio-temporal sequence for the first construction resource. The spatio-temporal sequence defines one or more operations configured to minimize the construction friction with a project associated with the first construction resource. The method includes outputting at least a portion of the data associated with the spatio-temporal sequence. The method may further include determining an interaction associated with the first construction resource and modifying the spatio-temporal sequence in response to the determined interaction.

Description

SYSTEMS AND METHODS FOR INDUSTRIAL OPERATIONS CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present international application claims priority to U.S. Provisional Patent Application No. 63 / 544,091, filed October 13, 2023, U.S. Provisional Patent Application No. 63 / 605,990, filed December 4, 2023, U.S. Provisional Patent Application No.63 / 663,989, filed June 25, 2024, U.S. Provisional Patent Application No. 63 / 669,054, filed July 9, 2024, and U.S. Provisional Patent Application No.63 / 670,047, filed July 11, 2024, the entire contents of which applications are incorporated by reference in their entirety. TECHNOLOGICAL FIELD

[0002] Embodiments of the present disclosure relate generally to industrial operations, such as those used in the construction of structures, and, more particularly, to methods, systems, and techniques for construction resource operations. BACKGROUND

[0003] Construction resources (e.g., building materials or the like) are widely used in the construction of structures (e.g., foundations, substructures, superstructures, tunneling, etc.) or other projects. These projects are further associated with various construction assets (e.g., equipment, transportation devices, curing ovens, storage locations, etc.) each of which may be subjected to varying environmental or contextual conditions. Through applied effort, ingenuity, and innovation, many of the problems associated with conventional construction resource methods and systems have been solved by developing solutions that are included in embodiments of the present disclosure, many examples of which are described in detail herein. BRIEF SUMMARY

[0004] Embodiments of the present disclosure therefore provide for methods, systems, apparatuses, and computer program products for construction resource operations. With reference to an example computer-implemented method for construction resource operations, the method may include receiving a first dataset comprising one or more first data entries. The first data entries may be associated with at least a first construction resource. The method may include generating a spatio-temporal sequence for the first construction resource where the spatio-temporal sequence defines one or more operations configured to minimize the construction friction with a project associated with the first construction resource. The methodmay further include outputting at least a portion of the data associated with the spatio-temporal sequence.

[0005] In some embodiments, the first construction resource includes a construction object that is a construction resource that is passive during a time period of an interaction associated with the construction resource. Additionally or alternatively, in such an embodiment, the construction resource may be a construction asset that is a construction resource that is active during the time period of the interaction associated with the construction resource.

[0006] In some embodiments, the construction friction includes one or more of a time cost, a financial cost, an energy cost, a utilization metric, a safety metric or a waste metric.

[0007] In some embodiments, the spatio-temporal sequence defines a set of one or more of a physical location of the first construction resource, a configuration of the first construction resource, or an operation of the first construction resource.

[0008] In some embodiments, the method further includes determining an interaction associated with the first construction resource.

[0009] In some further embodiments, the method includes modifying the spatio-temporal sequence in response to the determined interaction.

[0010] In some still further embodiments, the method further includes modifying one or more of a physical location of the first construction resource, a configuration of the first construction resource, or an operation of the first construction resource.

[0011] In some embodiments, generating the spatio-temporal sequence further includes deploying a machine learning (ML) model on the first dataset.

[0012] In some embodiments, in generating the spatio-temporal sequence, the method further includes determining a location of the first construction resource.

[0013] In some embodiments, in generating the spatio-temporal sequence, the method further includes determining a state of the first construction resource.

[0014] In some embodiments, the one or more first data entries may be associated with a second construction resource of the project. In such an embodiment, the method may further include determining an interaction between with the first construction resource and the second construction resource and modifying the spatio-temporal sequence in response to the determined interaction.

[0015] In any embodiment, the construction resource may be a prefabricated building element.

[0016] In any embodiment, the one or more first data entries may be generated by one or more sensor devices associated with the construction resource.

[0017] The above summary is provided merely for purposes of summarizing some example embodiments to provide a basic understanding of some aspects of the present disclosure. Accordingly, it will be appreciated that the above-described embodiments are merely examples and should not be construed to narrow the scope or spirit of the disclosure in any way. It will be appreciated that the scope of the present disclosure encompasses many potential embodiments in addition to those here summarized, some of which will be further described below. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Having thus described certain example embodiments of the present disclosure in general terms, reference will now be made to the accompanying drawings. The components illustrated in the figures may or may not be present in certain embodiments described herein. Some embodiments may include fewer (or more) components than those shown in the figures.

[0019] FIG. 1 illustrates an example system for construction resource operations in accordance with an example embodiment of the present disclosure;

[0020] FIG. 2 illustrates an example supply chain with which, in whole or in part, the example system of FIG. 1 may be implemented in accordance with one or more example embodiments of the present disclosure;

[0021] FIG. 3 illustrates a block diagram of example circuitry (e.g., server circuitry) that may be specifically configured in accordance with an example embodiment of the present disclosure;

[0022] FIG. 4 illustrates an example project logistics network in accordance with an example embodiment of the present disclosure;

[0023] FIGS. 5A-5B illustrate examples of construction friction in accordance with an example embodiment of the present disclosure;

[0024] FIG.6 illustrates the relationship and lifecycle of an example construction object in accordance with an example embodiment of the present disclosure;

[0025] FIG. 7 illustrates example chains and modular representations of interactions in accordance with an example embodiment of the present disclosure;

[0026] FIGS.8-14 illustrate example graphical representations of interactions and states in the generation of the spatio-temporal sequences described herein in accordance with an example embodiment of the present disclosure;

[0027] FIG. 15 illustrates an example solution stack in accordance with an example embodiment of the present disclosure;

[0028] FIG. 16 illustrates example proximity network configurations for construction resource operations in accordance with an example embodiment of the present disclosure;

[0029] FIG. 17 illustrates an example device implementation in accordance with an example embodiment of the present disclosure;

[0030] FIG. 18 illustrates an example graphical representation between gateway device data and location algorithm solution space in accordance with an example embodiment of the present disclosure;

[0031] FIG. 19 illustrates an example lift interact state machine in accordance with an example embodiment of the present disclosure;

[0032] FIG.20 illustrates example interaction characteristic curves mapped to an example state machine in accordance with an example embodiment of the present disclosure;

[0033] FIGS.21A-21B illustrate example lift interactions for multiple objects or elements in accordance with an example embodiment of the present disclosure;

[0034] FIG. 22 illustrates an example trilateration schematic for location tracking of a beacon on a construction resource carried by a crane in accordance with an example embodiment of the present disclosure;

[0035] FIG.23 illustrates example logic blocks for registration of an example construction resource to an associated device in accordance with an example embodiment of the present disclosure;

[0036] FIG.24 illustrates example logic blocks for management of storage of an example construction resource in accordance with an example embodiment of the present disclosure;

[0037] FIG.25 illustrates an example logic block for tracking of an example construction resource in accordance with an example embodiment of the present disclosure;

[0038] FIG. 26 illustrates an example state machine indicating shifting status, allowing only forward state changes in accordance with an example embodiment of the present disclosure;

[0039] FIG.27 illustrates an example state machine with associated segments of the value- chain toolkit in accordance with an example embodiment of the present disclosure;

[0040] FIG.28 illustrates an example logic block for status estimation in accordance with an example embodiment of the present disclosure;

[0041] FIG. 29 illustrates an example meta-state machine mirroring the value chain modules in the VC toolkit in accordance with an example embodiment of the present disclosure;

[0042] FIGS. 30A-30B illustrate an example graphical representation of the spatio- temporal sequences generated in accordance with one or more example embodiments of the present disclosure;

[0043] FIG. 31 illustrates a flowchart of an example method for construction resource operations in accordance with some embodiments of the present disclosure; and

[0044] FIGS. 32-33 illustrate example simulation outputs in accordance with some embodiments of the present disclosure. DETAILED DESCRIPTION Overview

[0045] Various embodiments of the present disclosure will now be described more fully hereinafter with reference to the accompanying drawings in which some but not all embodiments are shown. Indeed, the present disclosure may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather these embodiments are provided so that this disclosure will satisfy applicable legal requirements. Like reference numerals refer to like elements throughout.

[0046] The terms “illustrative,” “exemplary,” and “example” as may be used herein are not provided to convey any qualitative assessment, but instead merely to convey an illustration of an example. Thus, use of any such terms should not be taken to limit the spirit and scope of embodiments of the present disclosure. The phrases “in one embodiment,” “according to one embodiment,” and / or the like generally mean that the particular feature, structure, or characteristic following the phrase may be included in at least one embodiment of the present disclosure and may be included in more than one embodiment of the present disclosure (importantly, such phrases do not necessarily refer to the same embodiment).

[0047] Embodiments of the present disclosure may be described below with reference to block diagrams and flowchart illustrations. Thus, it should be understood that each block of the block diagrams and flowchart illustrations may be implemented in the form of a computer program product; an entirely hardware embodiment; an entirely firmware embodiment; a combination of hardware, computer program products, and / or firmware; and / or apparatuses, systems, computing devices, computing entities, and / or the like carrying out instructions, operations, steps, and similar words used interchangeably (e.g., the executable instructions, instructions for execution, program code, and / or the like) on a computer-readable storage medium for execution. For example, retrieval, loading, and execution of code may be performed sequentially such that one instruction is retrieved, loaded, and executed at a time. Insome exemplary embodiments, retrieval, loading, and / or execution may be performed in parallel such that multiple instructions are retrieved, loaded, and / or executed together. Thus, such embodiments may produce specifically configured machines performing the steps or operations specified in the block diagrams and flowchart illustrations. Accordingly, the block diagrams and flowchart illustrations support various combinations of embodiments for performing the specified instructions, operations, or steps. Definitions

[0048] As used herein, the term “project” may refer to any physical construction forming part of the built environment at any stage of its existence, including but not limited to its conception, design, construction, and operation. Examples of a project include but are not limited to a bridge project, building project, tunnel project, or other commercial or infrastructure project. As used herein, the term “site” may refer to any self-contained location associated with the project (e.g., a construction project). For example, a site may refer to a jobsite, a precast factory, a batching plant, and / or the like without limitation.

[0049] As used herein, the term “logistics setting,” “logistical setting,” industrial setting,” may be used interchangeably to refer to any location wherein industrial or logistical processes may occur. Examples include plants, factories, warehouses, jobsites and / or the like without limitation. As used herein, the term “construction setting” refers to a construction related setting. Examples of a construction setting includes as a prefabrication factory, a construction site, a batching plant and / or the like without limitation.

[0050] As used herein, the term “instance,” “logistical instance,” “logistics instance,” “industrial instance,” may be used interchangeably to refer to any physical or simulated occurrence or scenario within time and / or space associated with an industrial or logistical operation. Examples of an instance include but are not limited to the occurrence in space and time of a particular forklift travelling from one location to the next, all the operations on a specific prefabricated factory at one point in time over a specific timeframe, a construction yard alongside operations happening over time on the aforementioned yard which may include obstructions, and a construction project as it evolves over time.

[0051] As used herein, the term “spatio-temporal sequence,” “spatio-temporal plan,” “spatio-temporal representation,” “spatio-temporal path” and / or the like may refer to any set of events occurring over an interval of time and space, wherein that interval may be known or unknown. A spatio-temporal sequence may include a set of events as they occurred or have been executed but may also include a potential set of events as they could have happened inthe past or in the future. A spatio-temporal sequence may also include any set of steps indicative of a set of events occurring over an interval of time and space such as a set of instructions. The present disclosure contemplates that any format, visualization, style, configuration, etc. may be used to represent the spatio-temporal sequences, paths, etc. described herein. Examples of spatio-temporal sequences may include plans, schedules (e.g., Gantt chart), routes (optionally with associated estimated times of arrival), lists of states, videos, timelines, linear timelines, interactive timelines, maps, heat maps, animated maps, static maps, flow maps, graphs, charts, geospatial visualizations, dashboards displaying live data and planned data, space-time diagrams, 3D time evolving simulations, instructions, sets of steps. Additionally, these terms may refer to any set of events occurring over an interval of time and space or set of steps indicative of a set of events occurring over an interval of time and space, wherein the set of events occurring over an interval of time and space is associated with an expected or otherwise desired or planned to occur.

[0052] As used herein, the term “anomaly” may refer to any quantity or event that does not match an expected plan or a specification or other compliance requirement. Examples of anomalies may include delays in plans, unexpected weather conditions, a precast unit not meeting its design strength, a missing unit.

[0053] As used herein, the term “state” may refer to a defined condition of an entity at a particular time. In some embodiments, a state of a construction resource defines the progression state of the resource with respect to a wider construction process (often depicted graphically as state machines). Therefore, a state change may denote the evolution of a construction resource from one state to the next in the state machine or in general. The term state may be read broadly to include any characteristics, attribute, parameter, aspect, quality, and / or the like of an entity at a particular time without limitation.

[0054] As used herein, the term “simulation” may refer to any operation that mimics, reproduces, and / or replicates real-world events. By way of example, a simulation may include physico-chemical parameters designed to simulate physics and chemistry of real world events so as to accurately model these events. Simulations may be based upon a prompt and may, for example, model the evolution of entities, interactions, or other logistics instances without limitation.

[0055] As used herein, an “entity” may refer to any object, asset, device, system etc. that may be discretely identified in the context of an industrial or logistical setting (including construction settings in which case entities may reduce to construction resources, manufacturing plants, chemical plants, power plants and the like). By way of a non-limitingexample, an entity may refer to a precast unit, a forklift, a trailer, a shunter, a truck, a prefabricated unit, a package, an assembly line, a mixer, a batcher, a pump. Additionally, an entity may refer to transportation devices or systems (e.g., trucks, cranes, etc.), manufacturing equipment or systems (e.g. precast ovens, production lines, batching machines), harvesting devices or systems (e.g., raw material related devices located at quarries or the like), and / or the personnel that operate these devices and systems. Furthermore, a construction site resource may refer to the sensors, sensor devices, transducers and actuators used, in some embodiments, to perform the operations of the present disclosure. As such, the present disclosure contemplates that any of the assets described herein as associated with or otherwise related to the use of building materials to construct structures may be considered a construction site resource, without limitation. A passive construction resource may refer to a resource that is unable to drive forward an interaction while an active construction resource may be able to drive forward an interaction, although not required to do so.

[0056] As used herein, a “construction site resource,” “construction resource,” and “CR” may be used interchangeably to refer to any object, entity, asset, device, system, etc. that may be used in the construction of a structure (including the manufacturing, production or construction of any of its prefabricated components, readymix batches, or other constituent components). By way of a non-limiting example, a construction site resource may refer to raw materials, composite materials, support structure or formwork, etc. used in the formation of structures. Additionally, a construction site resource may refer to transportation devices or systems (e.g., trucks, cranes, etc.), manufacturing equipment or systems (e.g. precast ovens, production lines, batching machines), harvesting devices or systems (e.g., raw material related devices located at quarries or the like), and / or the personnel that operate these devices and systems. Furthermore, a construction site resource may refer to the sensors, sensor devices, transducers and actuators used, in some embodiments, to perform the operations of the present disclosure. As such, the present disclosure contemplates that any of the assets described herein as associated with or otherwise related to the use of building materials to construct structures may be considered a construction site resource, without limitation. A passive construction resource may refer to a resource that is unable to drive forward an interaction while an active construction resource may be able to drive forward an interaction, although not required to do so.

[0057] As used herein, the terms “construction object” or “CO” may be used to refer to a any construction resource in the context of a project that is used as a passive resource during the time period of a given interaction in which it is the object of the interaction. Examples ofconstruction objects include, but are not limited to, precast or prefabricated concrete units, façade elements, bundles of rebar, buckets of wet concrete, bags of cement, hammers and other tools, and / or the like.

[0058] As used herein, the terms “construction asset” or “CA” may be used to refer to any construction resource in the context of a project used as an active resource during the time period of a given interaction in which it is acting as the subject of the interaction. Examples of assets include, but are not limited to, forklift, trucks, human operatives, robots, tower cranes, lorries, barges, excavators, piling rigs, ovens, and / or the like.

[0059] As used herein, the term “factory” may refer to a type of source of construction objects which creates COs on its campus (e.g., prefabricated elements, units, objects) before delivering one or more COs at a time in loads. Examples of factories include but are not limited to precast factories, steel fabrication yards, MEP, and facade module factories, and / or the like. A prefabricated or precast element / unit may refer to a discrete prefabricated volume, produced at a factory, with the eventual goal of comprising a structure to be constructed. A “yard” or “storage yard” may refer to an area on a factory specifically designed for storage of prefabricated units.

[0060] As used herein, the term “transportation” may refer to the physical movement of construction objects and assets from any part of the construction value chain to another. A “load” may refer to a collection of construction objects grouped together in such a way that they are able to be transported for their source (factory or supply source) to the project site. A “source” may refer to an originator of construction objects that deliver one or more COs at a time in loads to another location in the supply chain, but that may be the destination of a COs delivery (e.g., when a CO is rejected from a project site and returns to the source for remedial operations). Example sources include but are not limited to staging yards, fly factories, factories, foundries, batching plants, construction sites, and / or the like.

[0061] As used herein, the terms “contextual material condition,” “contextual condition,” “context,” and “CC” may be used interchangeably herein to refer to any imposed state or attribute that at least partially defines the instantiated context in which a construction resource is used. The contextual condition may, for example, be associated with various characteristics, attributes, aspects, etc. of an external environment of the construction resource and / or may be associated with characteristics, attributes, aspects, etc. of the construction resource. With reference to an example construction resource, contextual material conditions may be associated with temperature data, insulation data, structural data, environmental data, structural burden data, batching plant data, pump contextual condition data, truck contextual conditiondata, kiln contextual condition data, temporal data, spatial data and / or the like. By way of continued example, insulation data may be indicative of a formwork type, a formwork coating, the presence or absence of blankets or other coverings. Example structural data as a contextual material condition may refer to data pertaining to the geometry, physical form, structure, layout, arrangement, configuration, and / or content (e.g., rebar or the like) of a pour. As such, the structural data may be indicative of or otherwise associated with element type data, geometry or dimensional data, exposure data (e.g., surface area of concrete exposed to air, surface area of concrete exposed to other materials, such as formwork, etc.), reinforcement geometry data (e.g., data entries associated with rebar or the like), and / or data associated with the external environment of the same. Example spatial data as a contextual material condition may refer to data pertaining to the global location (e.g., latitude, longitude and altitude), or relative location of a building material at a construction site or related location (e.g., location of a pour in relation to gridlines, or another pour, or location of a precast unit in a precast yard).

[0062] Environmental data as an example contextual material condition may include meteorological data, such as ambient temperature data, humidity data, precipitation data, and / or other atmospheric effects (e.g., wind data, storm data, lightning data, etc.). Environmental data may further include electromagnetic radiation data, data indicative of mechanical vibration and / or other mechanical disturbances, geological data (e.g., the type of soil surrounding foundations may impact its behavior), and / or oven data (e.g., instance in which ovens are used for curing, particularly in precast implementations).

[0063] Structural burden data as an example contextual material condition may include load data and / or load path data, stress data, strain data, and / or batching plant data (e.g., volume of batch, mixing data, mixing intensity data, rate of rotation, etc.). Truck or transport contextual condition data may be indicative of the volume of the load (e.g., one or more batches in transport), truck rotational data (e.g., rotational velocity or the like), etc. Kiln contextual condition data may include data indicative of the temperature inside the kiln, the raw materials inside the kiln, and / or the volume of materials (e.g., raw materials, desired output materials, waste materials, etc.) inside the kiln.

[0064] Temporal data as an example contextual material condition may include any information used to denote a time or timeframe. In some instances, the temporal data may be indicative of time in absolute terms or relative context dependent terms. For example, the temporal data may include data indicative of a date and time, a period of time or duration (e.g., time between two dates or the like), a season, a year, a construction stage, time stamp data, data stamp data, and / or the like. As described herein, the temporal data associated with an examplebuilding materials may be data that is associated with one or more processes or operations. For example, the temporal data may be indicative of a particular date and / or time at which one or more pours were poured.

[0065] As used herein, the terms “construction logistics, “industrial logistics,” and “manufacturing logistics” may be used to refer to operations associated with the coordination of the chain of inter-dependent interactions and processes that constitute the project, across the construction value chain, such as from element design to handover. A Logistics Optimization Solution Stack (LOSS) may refer to a family of algorithms that stack on top of each other with the aim of optimizing construction logistics, including locations and interactions of construction resources as described herein.

[0066] As used herein, the terms “construction friction” may refer to any phenomenon in the construction supply chain that results in energy being expended above a specified minimum level required to drive a certain interaction (e.g., excess energy expenditure on the planning or execution of construction logistics with respect to a theoretical minimum). In the context of construction logistics, energy expenditure may refer to any action, process, interaction or planning thereof, necessary to, or, undertaken with the goal of, completing the project at any part of the value chain. The state of a construction resource defines the progression state of the resource with respect to a wider construction process (often depicted graphically as state machines). These may also be understood to represent milestones relating to the construction process. A state change denotes the evolution of a construction resource from one state to the next in the state machine or in general. The embodiments of the present disclosure as described herein may be configured to minimize or reduce construction friction for a project based on any number of associated objectives, parameters, goals, etc. for the project.

[0067] As used herein, the terms “first dataset” and associated “first data entries” are used to refer to data that, in some embodiments, is received by the systems, models, etc. of the present disclosure as an input. By way of a non-limiting example, the first dataset may include data associated with various materials properties that are input by a user, generated by a sensor device (for example, a maturity or temperature sensor), other device, received from a database, received from a prior iteration of one or more of the models described herein, and / or the like, such as in the construction resource operations described herein. Additionally or alternatively, in some embodiments, the first dataset may include data generated by, received from or associated with a wave-based sensor (e.g. a mechanical or electromagnetic wave-based sensor configured to excite and / or measure a cementitious mixture, or configured to measure electrochemical or electromechanical parameters of a building material).

[0068] As would be evident to one of ordinary skill in the art in light of the present disclosure, the first dataset and associated first data entries may be associated with, indicative of, or otherwise related to any of the attributes, characteristics, parameters, metrics, etc. of the construction or construction resource operations, systems, devices, etc. described herein without limitation. Said differently, the first dataset and associate first data entries may refer to the data structure by which data associated with the embodiments described herein is stored, regardless of data type, model used, system deployed, etc. The present disclosure further contemplates that additional datasets (e.g., second dataset or the like) may include data entries associated with any of the same or different data types described herein with reference to the first dataset. In other words, the present disclosure contemplates that any number of different datasets of any type may be used by the embodiments herein.

[0069] As used herein, the terms “sensor,” “sensor device,” “transducer,” “smart device,” and “device” may be used interchangeably and / or collectively to refer to any hardware or circuitry component configured to generate data, such as first data entries, that is associated with a building material, construction resource, contextual awareness, and / or the like without limitation. As described hereinafter, a sensor device may include any relevant circuitry, components, etc. configured to generate data that is indicative of, for example, the material properties (e.g., static material properties, compositional material properties, contextual conditions, contextual material properties, etc.) of a building material. The present disclosure contemplates that each of the techniques, models, etc. of the present disclosure may be implemented with any number of the sensor and / or sensor devices and / or transducers and / or devices described herein, alone or in any combination.

[0070] Sensor devices may be used in association with “actuators” which as used herein may be used to refer to any element or circuitry component that is able to cause, generate, adjust and / or generally control any force, field or energy excitation or disturbance (including for example mechanical excitations, or electromagnetic excitations, and in particular wave- based excitations, through force or field couplings). In some embodiments, sensor, sensor device, transducer, actuator, and device may be used interchangeably to reference any of their respective meanings, in a context dependent way. In some embodiments, an example “transducer” may be intrinsically resonating in that the configuration of the transducer (e.g., by geometry or the like) produces or is otherwise associated with resonant behaviors (e.g., oscillatory resonance, wave-based resonance modes, etc.).

[0071] As used herein, “wave-based sensor” may be used to refer to any device which may generate, adjust, or control a time-varying excitation (based on an input signal) and / or sense aresponse to an excitation including, but not limited to, of a target material, or another material coupled (directly or indirectly) to the target material. Such a wave based sensor may be, used to generate or otherwise make use of and sense waves, excitations, and / or oscillations (such as electromagnetic waves, electric currents and / or mechanical stresses) as described herein. Furthermore, “wave-based” may refer to any device, technique, sensory, etc. that employs one or more actuators to excite a host material, or a second material that is coupled to the host material. The excitation may be a time varying signal (e.g., an oscillatory signal, a wave, etc.). Wave-based devices, techniques, and sensing may also employ sensors to measure the response of the host material (directly, or indirectly through the response of the second material, or another material coupled to the host material). For the avoidance of doubt, the “wave-based” techniques described herein may encompass, without limitation, excitations, oscillations, and waves, and may further encompass any device configured to take input signals and generate, adjust, control an excitation of a field, force, or form of energy, such as via an actuator defined herein, as well as a response (e.g., material response, coupled medium response, etc.) to such excitation, oscillation, or wave.

[0072] As used herein in respect of wave-based sensors (or other, related devices), a “frame” may be used to refer to refer to fixtures, surfaces, volumes, membranes, and / or shapes of any kind which may be disposed as part of, in, around or in proximity of wave-based sensors, actuators or device housings as described herein. In some embodiments, devices, including their sensors and / or actuators may be at least partially embedded within frames, disposed within their inner volumes, in proximity to them and / or the like. In some embodiments, the devices described herein, or their component parts (e.g., sensors or actuators) may be physically bonded to frames (e.g., to produce a sensor / actuator-frame composite) or otherwise coupled (e.g., through a field, at a distance). As such, a frame may span any geometry that may or may not be contiguous. In some embodiments, frames may be made of materials or configured in geometries to manipulate waves (including their waveforms and direction of travel), oscillations and / or excitations (for example, through wave reflections, absorption or diffraction, polarization, or oscillatory dampening, inertial, inductive, capacitive or elastic effects, and the like).

[0073] As used herein, a “data value” may include any piece of information relating to a measurable entity, such as an example temperature reading. A “data type” may refer to a categorization of data values, such as thermal data for the example temperature reading. The terms “data source” and “data entity” may be used interchangeably to refer to a data store that holds data values (e.g., a specific BIM model or the like). The terms “data source type” and“data entity type” may be used interchangeably to refer to a categorization or type of data source or data entity. For example, a data entity may refer to as an instantiation of a data source (e.g., BIM model may be a class of data entities).

[0074] As used herein, a “positioning device” may refer to as device that has capabilities (alone or as part of a system) to make positioning determinations or characterizations. A “gateway” may refer to a network connected device (e.g., Internet connected device, for example over LTE, 5G or NB-IoT) that is configured to locally communicate with beacons (over BLE, BLE Long Range, BLE Mesh, LoRa, Sigfox, and / or the like). A “beacon” may refer to a battery powered device that can send and receive wireless signals to other beacons and / or gateways and / or other devices (over BLE, BLE Long Range, LTE, GPRS, 2G / 3G / 4G / 5G, NB-IoT, LoRa, Sigfox and so on). In some instances, beacons may not be directly connected to the internet. In some instances, a beacon may include a cellular interface). To this end, “global position” may refer to the position of a device with respect to a global frame of reference (e.g., a latitudinal and longitudinal location) while a “relative position” as used herein may refer to a location with respect to two or more construction resources, with respect to gridlines, and / or the like. The present disclosure contemplates that the delineation between construction resources, construction assets, and / or construction objects may vary based on the intended application of the systems described herein. In some embodiments, two or more construction resources may interact.

[0075] An “interaction” as used herein may refer to a discrete instance of an event occurring within a continuous time interval that may evolve the state or attribute of an entity, the entity sometimes being a construction resource. Oftentimes, a location may evolve the location of an entity. In some instances, an interaction may involve two or more entities, oftentimes evolving location of one or more construction resources, and oftentimes with one resource being active (in that it can drive forward an interaction) and the other passive (in that it is unable to drive an interaction and is subjected to it). In other instances, interactions involve a single entity. An interaction of that nature may be referred to as “self-interaction”. Examples of interactions include but are not limited to an operative driving a nail with a hammer, a tower crane lifting a precast concrete until, an excavator lifting a bucket of soil, a robot painting a wall, etc. The present disclosure contemplates that the delineation between active and passive construction may vary based on the intended application of the systems described herein.

[0076] As used herein, the terms “data,” “content,” “information,” and similar terms may be used interchangeably to refer to data capable of being transmitted, received, and / or stored in accordance with embodiments of the present disclosure. Thus, use of any such terms shouldnot be taken to limit the spirit and scope of embodiments of the present disclosure. Further, where a computing device is described herein as receiving data from another computing device, it will be appreciated that the data may be received directly from another computing device or may be received indirectly via one or more intermediary computing devices, such as, for example, one or more servers, relays, routers, network access points, base stations, hosts, and / or the like, sometimes referred to herein as a “network.” Similarly, where a computing device is described herein as sending data to another computing device, it will be appreciated that the data may be sent directly to another computing device or may be sent indirectly via one or more intermediary computing devices, such as, for example, one or more servers, relays, routers, network access points, base stations, hosts, and / or the like. Building Material Determination Systems

[0077] FIG. 1 illustrates an example system for construction resource operations (e.g., system 100). It will be appreciated that the system 100 is provided as an example of an embodiment(s) and should not be construed to narrow the scope or spirit of the disclosure. The depicted system 100 of FIG. 1 may include a server 200 communicably coupled with one or more sensor devices 102a-n via a network 104. The server 200 may be configured to control or otherwise influence operations of the one or more sensors device 102a-n and as described hereafter and may be configured to receive from the one or more sensor devices 102a-n datasets comprising data entries associated with various measurements (e.g., measurement types) of a construction resource. Still further, the server 200 may comprise or be communicably coupled with one or more databases 108. In some embodiments, the system 100 may further include various user devices 106 (e.g., mobile phones, laptop computers, etc.) by which a user associated with the system 100 may interact with the system 100, such as via a user interface of the user device 106.

[0078] Although described hereinafter with reference to a server 200, the present disclosure contemplates that the operations described hereafter with reference to the server 200 may be performed by any computing device, system orchestrator, central processing unit (CPU), and / or the like. Furthermore, although illustrated as a single device (e.g., server 200), the present disclosure contemplates that any number of distributed components may collectively be used to form the server 200 and / or to perform the operations associated with the server 200. In some embodiments, the server 200 may comprise, in whole or in part, one or more of the sensor devices 102 and / or the user device(s) 106. In any embodiment, the server 200 may be configured to, based upon the data received from the various sensor devices 102a-n and / ordatabases 108, determine the location of a construction resource, determine an interaction associated with a construction resource, determine a state of a construction resources, and / or generate a spatio-temporal sequence associated with the construction resource as described hereafter.

[0079] To facilitate or otherwise enable this connectivity between devices, the communication network 104 may be any means including hardware, software, devices, or circuitry that is configured to support the transmission of traffic (e.g., data, signals, etc.) between components of the system 100. For example, the communication network 104 may be formed of components supporting wired transmission protocols, such as, digital subscriber line (DSL), Ethernet, fiber distributed data interface (FDDI), or any other wired transmission protocol obvious to a person of ordinary skill in the art. The communication network 104 may also be comprised of components supporting wireless transmission protocols, such as Bluetooth, IEEE 802.11 (Wi-Fi), or other wireless protocols obvious to a person of ordinary skill in the art. In addition, the communication network 104 may be formed of components supporting a standard communication bus, such as, a Peripheral Component Interconnect (PCI), PCI Express (PCIe or PCI-e), PCI eXtended (PCI-X), Accelerated Graphics Port (AGP), or other similar high-speed communication connection. Further, the communication network 104 may be comprised of any combination of the above mentioned protocols. In some embodiments, such as when one or more sensor devices 102a-n and the server 200 are formed as part of the same physical device, the communication network 104 may include the on-board wiring providing the physical connection between the component devices.

[0080] In some embodiments, the system 100 may include one or more databases 108 configured to store data generated by the server 200, the one or more sensor device 102a-n, or the like. The database(s) 108 may be accessible by the server 200, such as to retrieve data for comparison with data generated by the one or more sensor devices 102a-n. In some embodiments, the database(s) may operate as a repository for data generated by the sensor devices 102a-n, data associated with performance of the operations described herein, and / or any data associated with construction resources without limitation. Furthermore, the database(s) 108 may be configured to store data associated with performance of the machine learning models and artificial intelligence algorithms described herein (e.g., prior iterations, simulations, etc.). The present disclosure contemplates that the database(s) 108 described herein may be configured to store any of the data entries generated by the sensor devices 102a- n of the present disclosure, data associated with operations performed on the data entries generated by the sensor device 102a-n, and / or the like without limitation.

[0081] Although illustrated in FIG. 1 as separate entities, the present disclosure contemplates that the server 200 and the one or more sensor device 102a-n may, in some embodiments, include common components and / or functionality. By way of example, the embodiments of the present disclosure are described hereinafter with reference to the server 200 performing the various construction resource operations based on data entries generated by the sensor devices 102a-n. The present disclosure, however, contemplates that, in some embodiments, the sensor devices 102a-n may be configured to, in whole or in part, perform the construction resource operations described herein. Said differently, the present disclosure contemplates that each of the devices described herein may include the components necessary to perform one or more of the operations described hereinafter. Furthermore, although illustrated in FIG.1 with one or more sensors device 102a-n communicably coupled with the server 200 via the network 104, the present disclosure contemplates that the system 100 may include any number of intermediary devices communicably coupled within the system 100. By way of a non-limiting example, the system 100 may include various host devices, gateway devices, etc. that receive data generated by the sensor devices 102a-n and provide this data to the server 200. Example Supply Chain

[0082] As shown in FIG.2, an example supply chain 101 is illustrated with which, in whole or in part, the example system of FIG.1 may be implemented. As described hereinafter, various embodiments of the present disclosure are described with reference to an example prefabricated concrete element as an example construction object (e.g., a construction resource). As would be evident to one of ordinary skill in the art in light of the present disclosure, however, the construction resource operations described herein may be applicable to any construction resource in any stage of production.

[0083] As shown, the preparation and installation of a construction resource may occur in various stages. As such, the data described hereinafter (e.g., generated by applicable sensors or otherwise) may not be limited to use with ongoing or finished pours of a building material (e.g., cementitious mixture or the like) or prefabricated elements, objects, etc. For example, the supply chain 101 may include a first stage 110 in which raw materials (from which the cementitious mixture is derived) are acquired (e.g., harvested, mined, excavated, manufactured or gathered); a second stage 114 in which these raw materials are processed and / or combined to create the cementitious mixture or further parts thereof (e.g., in a cement plant / ready-mix batching plant); the final stage 116 of ultimately pouring the cementitious mixture; andtypically one or more intervening transit stages 112 in which the raw materials, intermediate products or final cementitious mixtures are transported from one stage to its subsequent stage.

[0084] At every such stage in supply chain 101, data may be generated (e.g., by the one or more sensor devices 102a-n) and transmitted to the server 200 indicative of measurements, properties, attributes, and / or characteristics of these raw materials (e.g., aggregates), intermediate products (e.g., Portland cement) and cementitious mixtures (e.g., concrete). For example, sensors 102a-n disposed on or in part of a site, such as a quarry or materials processing system or plant (such as a batching plant for processing aggregates like sand, crushed rock, or gravel), may be capable of measuring and outputting an indication of a raw material’s material properties (e.g., density, granularity, hardness, and / or the like) during first stage 110 or second stage 114. Additionally or alternatively, one or more sensor devices 102a- n may be disposed in, or on, one or more vehicles that are configured to make, mix and / or transport cementitious mixtures or their constituent raw materials as part of a transit stage 112. For instance, either a traditional barrel truck or a volumetric mobile mixer may contain sensor devices 102a-n configured to monitor properties of a cementitious mixture and / or pours thereof, or (e.g., in the case of a volumetric mobile mixer) properties of raw materials used in the cementitious mixture. The vehicle(s) may be configured to supply (e.g., transmit wirelessly in real time) the monitored properties for use by the server 200. The present disclosure contemplates that the system 100 may employ any number of sensor devices 102a-n at one or more of the stages 110, 112, 114, 116 illustrated in FIG.2 or otherwise based on the intended application of the system 100. Example Server Circuitry

[0085] With reference to FIG. 3, example circuitry components of the server 200 are illustrated that may, alone or in combination with any of the components described herein, be configured to perform the operations described herein, such as, for example with reference to FIG. 31. As shown, the server 200 may include, be associated with or be in communication with processor 202, a memory 206, and a communication interface 204. The processor 202 may be in communication with the memory 206 via a bus for passing information among components of the server 200. The memory 206 may be non-transitory and may include, for example, one or more volatile and / or non-volatile memories. In other words, for example, the memory 206 may be an electronic storage device (e.g., a computer readable storage medium) comprising gates configured to store data (e.g., bits) that may be retrievable by a machine (e.g., a computing device like the processing circuitry). The memory 206 may be configured to storeinformation, data, content, applications, instructions, or the like for enabling the apparatus to carry out various functions in accordance with an example embodiment of the present disclosure. For example, the memory 206 could be configured to buffer input data for processing by the processor 202. Additionally or alternatively, the memory 206 could be configured to store instructions for execution by the processor 202.

[0086] The server 200 may, in some embodiments, be embodied in various computing devices as described above. However, in some embodiments, the apparatus may be embodied as a chip or chip set. In other words, the apparatus may comprise one or more physical packages (e.g., chips) including materials, components and / or wires on a structural assembly (e.g., a baseboard). The structural assembly may provide physical strength, conservation of size, and / or limitation of electrical interaction for component circuitry included thereon. The apparatus may therefore, in some cases, be configured to implement an embodiment of the present disclosure on a single chip or as a single “system on a chip.” As such, in some cases, a chip or chipset may constitute means for performing one or more operations for providing the functionalities described herein.

[0087] The processor 202 may be embodied in a number of different ways. For example, the processor 202 may be embodied as one or more of various hardware processing means such as a coprocessor, a microprocessor, a controller, a digital signal processor (DSP), a processing element with or without an accompanying DSP, or various other circuitry including integrated circuits such as, for example, an ASIC (application specific integrated circuit), an FPGA (field programmable gate array), a microcontroller unit (MCU), a hardware accelerator, a special- purpose computer chip, or the like. As such, in some embodiments, the processor 202 may include one or more processing cores configured to perform independently. A multi-core processing circuitry may enable multiprocessing within a single physical package. Additionally or alternatively, the processing circuitry may include one or more processors configured in tandem via the bus to enable independent execution of instructions, pipelining and / or multithreading.

[0088] In an example embodiment, the processor 202 may be configured to execute instructions stored in the memory 206 or otherwise accessible to the processor 202. Alternatively or additionally, the processing circuitry may be configured to execute hard coded functionality. As such, whether configured by hardware or software methods, or by a combination thereof, the processing circuitry may represent an entity (e.g., physically embodied in circuitry) capable of performing operations according to an embodiment of the present disclosure while configured accordingly. Thus, for example, when the processingcircuitry is embodied as an ASIC, FPGA or the like, the processing circuitry may be specifically configured hardware for conducting the operations described herein. Alternatively, as another example, when the processor 202 is embodied as an executor of instructions, the instructions may specifically configure the processor to perform the algorithms and / or operations described herein when the instructions are executed. However, in some cases, the processor 202 may be a processor of a specific device configured to employ an embodiment of the present disclosure by further configuration of the processing circuitry by instructions for performing the algorithms and / or operations described herein. The processor 202 may include, among other things, a clock, an arithmetic logic unit (ALU) and logic gates configured to support operation of the processing circuitry.

[0089] The communication interface 204 may be any means such as a device or circuitry embodied in either hardware or a combination of hardware and software that is configured to receive and / or transmit data, including media content in the form of video or image files, one or more audio tracks or the like. In this regard, the communication interface 204 may include, for example, an antenna (or multiple antennas) and supporting hardware and / or software for enabling communications with a wireless communication network. Additionally or alternatively, the communication interface may include the circuitry for interacting with the antenna(s) to cause transmission of signals via the antenna(s) or to handle receipt of signals received via the antenna(s). In some environments, the communication interface may alternatively or also support wired communication. As such, for example, the communication interface may include a communication modem and / or other hardware / software for supporting communication via cable, digital subscriber line (DSL), universal serial bus (USB) or other mechanisms.

[0090] The communication interface 204 may provide for communications under various modes or protocols, such as the Internet Protocol (IP) suite (commonly known as TCP / IP). Protocols in the IP suite define end-to-end data handling methods for everything from packetizing, addressing and routing, to receiving. Broken down into layers, the IP suite includes the link layer, containing communication methods for data that remains within a single network segment (link); the Internet layer, providing internetworking between independent networks; the transport layer, handling host-to-host communication; and the application layer, providing process-to-process data exchange for applications. Each layer contains a stack of protocols used for communications. In addition, the communication interface 204 may provide for communications under various telecommunications standards (e.g., 2G, 3G, 4G, 5G, and / or the like) using their respective layered protocol stacks. These communications may occur througha transceiver , such as radio-frequency transceiver. In addition, short-range communication may occur, such as using a Bluetooth, Wi-Fi, or other such transceiver (not shown).

[0091] In some embodiments, the server 200 may deploy one or more machine learning (ML) models to perform the operations described herein. To this end, the server 200 may include a machine learning (ML) module 208 comprising circuitry configured to ingest data, such as a multivariate N-dimensional space of time-series data where N is the number of different measurement types (e.g., data of different types) and, via a various ML and / or artificial intelligence techniques described hereafter, and output location determinations, interaction determination, state determination, and / or spatio-temporal sequences. The ML module 208 may leverage the processor 202 to perform its associated operations and may, for example store any results in the memory 206 and / or databases 108.

[0092] Of course, while the term “circuitry” should be understood broadly to include hardware, in some embodiments, the term “circuitry” may also include software for configuring the hardware. For example, although “circuitry” may include processing circuitry, storage media, network interfaces, input / output devices, and the like, other elements of the server 200 may provide or supplement the functionality of particular circuitry. Example Sensor Device Hardware

[0093] As an initial matter, the present disclosure contemplates that any embodiment and / or any method described herein, in full or in part, of any device, sensor, actuator, transducer, accessory and / or any other component which may be described herein associated with any device herein may be used in combination to produce another embodiment of the present disclosure. Any embodiment and / or any method described herein may be used, in full or in part, for any part of any method described in any other section herein, in any of their embodiments, in full or in part.

[0094] As described above, a wave-based sensor may refer to any device which may generate, adjust, or control a time-varying excitation (based on an input signal) and / or sense a response to an excitation including, but not limited to, of a target material, or another material coupled (directly or indirectly) to the target material. Such a wave based sensor may be, used to generate or otherwise make use of and sense waves, excitations, and / or oscillations (such as electromagnetic waves, electric currents and / or mechanical stresses) as described herein. Furthermore, wave-based may refer to any device, technique, sensory, etc. that employs one or more actuators to excite a host material, or a second material that is coupled to the host material. The excitation may be a time varying signal (e.g., an oscillatory signal, a wave, etc.). Wave-based devices, techniques, and sensing may also employ sensors to measure the response of the host material (directly, or indirectly through the response of the second material, or another material coupled to the host material). For the avoidance of doubt, the “wave-based” techniques described herein may encompass, without limitation, excitations, oscillations, and waves, and may further encompass any device configured to take input signals and generate, adjust, control an excitation of a field, force, or form of energy, such as via an actuator defined herein, as well as a response (e.g., material response, coupled medium response, etc.) to such excitation, oscillation, or wave. Construction Resource Operations Overview

[0095] Embodiments of the present disclosure are directed to methods and systems for optimizing the logistics of industrial, manufacturing, construction, warehouse, and other such settings, and optimize the coordination of processes executed in such settings. The present disclosure discloses embodiments associated with sensor devices, real-time tracking, insight generation, machine learning methods, logistics optimization, logistical plan generation, simulations and other such matters. Many of the methods and systems herein are configured to optimize logistics by minimizing friction and / or construction friction when the setting is a construction-related setting, by using data associated with entities in such settings, including construction resources, and processes or interactions executed in those settings, including processes executed across the construction value chain. The optimization procedures may, in some cases, be carried out by one or more AI-implemented methods, such as via generative AI-implemented methods. The data described herein may, in some instances, be data collected and / or inferred by instrumenting construction resources and processes. For example, the data may include example position, interaction data, state data, and / or state change data gathered across the construction value chain.

[0096] There currently exists a tremendous lack of relevant, objective data in the construction industry when making logistical determination directly impacting the logistics of construction operations. For example, construction operations planners are unable to make the optimal decisions in the coordination of their operations, operatives in the field may carry out these plans with incomplete, often incorrect information, and stakeholders are limited in the way of tracking quality standards, and confirming these standards are being met. Furthermore, the logistics of construction operations involve navigating a complex intersection of space, time, and materials resulting in frequency human error and incorrect judgement.

[0097] Additionally, construction sites often suffer from delays from continuous inefficiencies over time. With reference to an example of a truck arriving on site with precast concrete elements or modular facade units, if the truck of these construction objects arrives 30 minutes late to the site, there would be at least two (2) crews of humans and tools affected. One unloads the truck objects to a construction asset such as a crane, and the other removes the object from the crane for installation. These crews are generally not aware of the larger objectives of the project but are instead instructed by a manager of their next task. As such, in the case of a late truck arrival, if the crews’ manager is unaware of this delay, the crews will be in place at the scheduled time of arrival, only to find by observation that the load has been delayed. In any event, the crew in these traditional instances is not fully utilized from the point of this delay forwards point onwards.

[0098] In the case a delta between plan and execution is observed, it results in two main issues. First, immediately after delta begins, the project loses energy to friction. Second, once this delta occurs, construction operatives often have to expend excess energy to determine the cause of the delta and track a course to fix this delta as best they can (e.g., needing to track construction resources down, typically through phone calls or text messages). Due to the inherent latency of this system that is driven nearly entirely by human observation and inputs, by the time a course of remedial action is chosen, the situation on site may have already changed, deprecating the remedial action and necessitating a new course of action. This simulation may repeat several times, resulting in a divergent spiral of friction for the example project. By providing live information about construction resources to field managers as described by the embodiment of the present disclosure, the latency between observing the delta and formulating corrective action may be reduced, thereby reducing the overall implied friction of the delta which has occurred.

[0099] As defined above, the construction friction of an example project is ubiquitous. Similar in theory to the concept of friction in mechanics, this friction in construction operations results in a loss of energy. This loss of energy contributes to a project’s overall performance that may be measured by metrics such as time, manpower, energy, and carbon needed to complete the project. Friction of the project may also arise through suboptimal planning. In this case, the friction is inbuilt by starting the project in a sub-optimal energy state. Such friction may exist in all types of industrial environments, wherein the friction comprises such friction associated with a construction project, the friction may be denoted construction friction.

[0100] One example source of construction friction results from the lack of real-time information and visibility relating to construction processes and resources across the valuechain. Industrial logistics is conventionally opaque from an information theory perspective in that a real time reality capture and / or tracking system is currently unavailable across the project value chain. This means operatives are conducting their operations with very limited information resulting in poor execution. Full visibility as provided by the embodiments of the present disclosure removes or minimizes these execution issues. The delta between the energy expended due to the lack of information and the work expended had information been present is a first type of construction friction.

[0101] Another source of friction results from suboptimal logistics planning (e.g., suboptimal resource and process coordination and allocation). Industrial Logistics, particularly construction logistics is highly complex and contains a large number of interdependencies. It is therefore difficult for operatives to generate optimal plans, and friction is thus inbuilt into projects due to suboptimal plan generation. The delta between an optimal plan and a suboptimal one, constitutes a second type friction.

[0102] Another source of friction results from the logistics plan uncertainty (e.g., it is currently often impossible to know how closely the plan created by operatives may match the eventual reality of executed timelines and events). In a given plan, operatives typically poorly estimate ahead of time how long that plan will truly take. This uncertainty produces a third type of friction. Other sources of friction exist, for instance, external weather or force majeure events. Any such source of friction which may cause disruption, uncertainty or suboptimal execution of logistical processes may be applicable herein.

[0103] The embodiments of the present disclosure address construction friction in a number of ways. For example, the embodiments described herein provide a number of solutions for real-time monitoring of construction resources in a project, including location monitoring, interaction monitoring, process monitoring, state monitoring, and state change monitoring using sensor device systems as well as data processing and inference. The embodiments provide a suite of sensor devices, software and AI-implemented methods that optimize aspects of the construction logistics value chain and generate spatio-temporal sequences for optimized logistical coordination of events. These methods may predict or simulate construction processes, select or recommend the optimal plan from a list of plans for undertaking construction logistics, adjust and optimize an existing plan, or generate an entirely new plan using generative methods. The methods described herein may also output any data associated with or indicative of such a plan, in whole or in part, for example, any attribute such as a state of any construction resource in space and time.

[0104] The techniques described herein provide data, visibility, and insights into the logistics of construction operations (e.g., construction resources and construction processes) through the use of logistics devices sensing and AI-based data processing techniques that were historically unavailable. The techniques herein also generate sensor and AI-based insights that may optimize these operations using this data, such that they are made more efficient (e.g., efficiency in this context may be understood as optimization of time, carbon and / or cost as described herein). Said differently, the embodiments of the present disclosure may provide a feedback loop in the planning and execution of logistics for construction projects that operate to minimize construction friction. Current Methodologies

[0105] With reference to the example project logistics network 400 illustrated in FIG. 4, no generative AI-enabled solutions exist today for construction logistics schedule generation, nor for construction logistics optimization for objectives such as cost, time and carbon. Currently little to no data is gathered in a way that would make it usable for future decisions or present construction logistics operations. When data is collected, it is generally subject to human error and subjectivity in that this data may not be accurately relied upon to make decisions.

[0106] Current methods associated with quality assurance (QA) include handwritten forms and visual inspection by operators. Handwritten forms are often ripe with human error / bias and hard to query en masse. Visual inspections by operatives are often stored as image files in an unstructured fashion, leaving little context as to where the picture was taken or allowing for any other metadata to be attached. Furthermore, an overall view of all the site’s interactions does not exist in current systems. Project sites are usually so large that not all interactions may be seen by a human. Therefore, decisions are made based only on the data that is visible to a particular user, meaning the vast majority of the larger picture of the project is disregarded when decisions related to where to invest resources (e.g., energy) on the project.

[0107] Current methods associated with location determination of entities or construction resources may include scanning QR Codes, manually typing updated locations into database, manually typing elements, and / or the like. These methods may heavily rely on manual human input that increases the risk of human error. For example, in precast factories, every time a unit is moved, an operative may need to correctly update the location of the element manually based on a paper labels with barcodes. These labels are prone to damage, often fall off, and are often not scanned. As a result, the overall error rate for the location of inventory in the factory ERPmay be as high as 20%. This lack of clarity around knowing foundational information of their product (its location) means factories may divert resources towards re-locating or re-making these elements. Additionally, this method of tracking only allow managers visibility of a snapshot in time making optimization of operations impossible or impractical.

[0108] The embodiments of the present disclosure provides benefits in all levels of the construction supply chain including the precast factory or batching plant for readymix embodiments, transportation between plant and project, and the project site itself. This may apply to non-construction environments as well, such as excavation sites for natural resources. Whilst all construction projects have a unique supply chain, nearly all have some aspect of the three elements illustrated in the project logistics network 400 of FIG. 4 with an ideal linear flow of material from source to site. The benefits of improved logistics may be provided over all three parts of the supply chain of FIG.4, each which will enjoy benefits that will feed into smoother overall logistical operations of the entire system. The systems and methods described herein provide a plurality of benefits for industrial settings logistical operations including the reduction or elimination of delayed deliveries, the reduction or elimination of late delivery charges from the transportation and site parties, the reduction of factory overheads, increased efficient use of resources, reduced time spent in unload / loading bays, automated and unbiased records of delivery timeliness and performance, transparency of what will arrive on site, reduced site delay; optimal logistics plan generation, increased reliable planning, predictive and diagnostic simulations for construction operations, among others. Construction Friction

[0109] With reference to FIGS. 5A-5B, the embodiments of the present disclosure are configured to coordinate resources to achieve a goal. Often, logistics may be associated with the coordination and organization of disparate entities that may seek to create a more ordered system from a disordered system. For example, in the context of a construction project or several inter-linked projects, the goal may be to create an organized, ordered structure from disparate raw materials such as cement, sand, water, assets, and / or the like.

[0110] This may, in some interpretations, be associated with the concept of thermodynamic entropy where logistical processes often aim to complete a locally entropy minimizing goal, within a globally entropy maximizing system. This may be executed by applying energy in the form of work done onto the localized system so as to bring the system from a disordered state (e.g., raw materials or the like) to an ordered state (e.g., a constructed building). Work done is not infinitely efficient and some of this energy may be lost. In mechanical systems, this energymay be commonly lost to friction. In the logistical context of the present disclosure, the term friction, as defined above, denotes the inefficiencies in logistical operations on industrial, manufacturing and other such settings. As shown in the graphical representation in FIG. 5A, controlled construction friction theoretically results in near exponential cost increase. The embodiment of the present disclosure, therefore, operate to minimize construction friction and maximally optimize logistical operations, such that logistical friction tends to zero.

[0111] With continued reference to FIGS.5A-5B, construction friction, f(t) may typically be measured by metrics such as time, manpower, energy, carbon, throughput, utilization, shortest paths, safety, material waste and other such objectives associated with the logistical instance. Friction may therefore be broadly defined as f(t, x) = μ(t, x) − μ0, wherein μ0is a target optimal logistics performance given no friction, and μ(t) is the true measure of performance at time t, as a function scoring against metrics such as the ones described above. The embodiments described herein generating improved plans for logistical operations thereby globally improving performance closer to the theoretical maximum as shown in FIG. 5B. Additionally or alternatively, the methods herein may dynamically and / or iteratively adjust and optimize plans that are deviating from a given performance trajectory, resetting the performance trajectory and reducing construction friction in the process. Interactions, Processes, and Operations

[0112] As defined above, interactions may be described as events that occur that may evolve the present state, condition, and / or any attribute indicative the condition of any resource, entity construction resource or other. Processes may be defined as a group or sequence of interactions that may result in the completion of a higher level operation (e.g. a process may be a crane moving a precast unit on site; an interaction may be the individual steps in the state machine of crane use such as "lift element"). Processes may involve a type, set, or group of entities, such as construction assets and construction objects. A process may also include a higher level goal. Operations may be used to denote sets of processes or a generalized term for high-level events occurring in a logistics instance.

[0113] With reference to the relationship and lifecycle of an example construction object 600 of FIG.6, any logistical process may be seen as a sequence of discrete events. Each discrete event may be represented mathematically as functions taking in certain inputs (e.g., including the initial state of every entity and contextual conditions involved in the event) and producing certain outputs (e.g., including the end state of every entity and contextual condition) as a resultof the event. These outputs may in turn become inputs for the next event or interaction. For instance, an interaction evolution function or operator ‘f’ may be represented mathematically as f(x), in which the interaction ingests “x” as an input and generates the output ‘y’. Interactions or events evolve the state of one or a plurality of entities, resources or construction resources, in this sense, interactions are conceptually akin to evolution operators in quantum mechanics where states may be akin to wave functions fully defining the state of a given system. A sequentially following interaction ‘g’ may be represented mathematically as g(y) and may depend semantically on process ‘f’ because ‘g’ cannot start without the result ‘y’. Once ‘y’ is available, g(y) may be executed. The construction logistics embodiment described herein may be defined as the coordination of the chain of inter-dependent interactions that constitute the project. These interactions may be sequential, parallelized, or a combination of both.

[0114] An example of f(x) and g(y) may be described in the process of painting a wall. The wall must first be primed (f(x)), before it may be painted (g(y)). Priming a wall requires certain inputs (e.g., priming paint, tools (COs), and a painter operative (CA)) to interact in order to arrive at the desired outcome state of a primed wall. Subsequently, to paint a wall involves an interaction of a primed wall, painting tools (COs) and painter operative (CA) to arrive at the desired outcome of a painted wall. The Prefabrication Value Chain and The Lifecycle of the Element

[0115] With continued reference to FIG.6, the methods and systems described herein may be applicable to any logistics instance in any setting. This may include settings such as warehouses, manufacturing plants, job sites such as excavation sites, as well as construction related settings including batching plants, prefabrication factories, construction sites, and deliveries between the two. Although the present disclosure describes methods and systems for logistics optimization across the stages of the prefabrication value chain, one of ordinary skill in in the art would appreciate that the methods and systems described herein may be applicable to the other settings herein as well. For example, these systems may be applicable to other implementations by modifying model parameters to analogous parameters on other settings (e.g., adjusting the forklift state machine from a prefab factory to a warehouse environment).

[0116] By way of example, as shown in the representation 600, the construction prefabrication value chain may include one or more of design (of prefabricated elements), manufacturing; storage at the factory (typically in a yard); collection / loading (of the prefabricated element), delivery; storage on site, installation, and / or handover. Additionally or alternatively, from the perspective of a unit or construction object, the methods and systemsherein may be used across the lifecycle of the unit. A generalized life cycle for construction objects may include one or more of creation, storage, retrieval, load assembly, load dispatch (from factory), load arrival (to site), load disassembly and / or installation. Logistics Solution

[0117] With reference to FIG.15, the Logistics Optimization Solution Stack (LOSS) 1500, as defined above refers to a family of methods, systems and / or algorithms or models used for logistics optimization. The LOSS 1500 is a system formed of connected sensor device(s), alongside data extraction and ingestion methods, and computer implemented methods as well as AI-implemented methods, for tracking, optimizing and generating optimal plans for the logistics of a project or industrial setting or other similar logistics-intensive environment, in some embodiments with the goal to reduce the friction of operations. To do so, the system, models, and / or methods herein may track the location and interactions of construction resources and processes (e.g., interaction may be a crane lift picking up a precast unit would be an interaction of two construction objects); infer, predict, and optimize the states of these entities’ resources and processes at any given point in space-time, generate optimal plans coordinating with these entities, construction, and operations relating to these construction objects (e.g., logistics of such objects in the construction project), dynamically iterate and updates these plans based on real-time data, and / or generate analytics associated with these operations and / or events. Tracking of the representation of construction objects in various information systems objects may also be leveraged to further enhance the system performance of use (e.g., tracking digital logs for QA, construction schedules, or integration with building information models (BIM)s) or schedule data. Sources of data may include sensor data, documentation data, human input, API integration, machine records, and / or other sources.

[0118] The system described herein may record and track interactions and states that in some embodiments enable real-time progress tracking (e.g., the determination that MEP is 25% completed on Level 2 of the project on day 45 of the project). Historical tracking of interactions may also allow for a deeper understanding of performance over time that may be extrapolated or used by the methods and / or models herein to predict future performance and the attainability of milestones within a certain timeframe. As shown in FIG.15, the solutions 1500 may be categorized into The Core Toolkit, Enabling Toolkit, and Value-Chain Toolkit. The data feeds are in the order from bottom (Core) to top (Value-chain). The horizontal axis provides a notional view of the data volumes where the core tools deal with sensor level data, whereas theenabling tools will use the processes to inform the essential technologies. Appropriate combinations of these technologies will then feed the value-chain toolkit. Example Core Toolkit

[0119] The core toolkit may include methods and algorithms based on construction resources instrumentation using sensor devices to track information. The enabling and value- chain toolkit methods then are able to use the data collected and output by the core toolkit for inferences on the state and / or attribute and / or history of entities, resources, construction resources or others, and make inferences, data aggregations, predictions, simulations, optimizations, recommendations and / or generations based on that data and / or other data from other sources. This includes inferences associated with construction friction to benchmark construction friction. The core toolkit include Devices and Physical Embodiments. For example, the core toolkit may include mechanical and industrial design, communication protocols attachment methods, device systems, devices for location and interaction tracking and / or other embodiments or attributes of devices, sensor devices and / or physical embodiments of these devices. The core toolkit algorithms may be divided into location (and time) determination methods for entities or construction resources, and interaction determination or inference methods associated with entities, resources, or construction resources.

[0120] With reference to the proximity network configurations for construction resource operations 1600 in FIG.16, this data may be gathered by sensor systems or distributed sensor systems of any configuration. These sensors may generally take the form of any hardware described in any of the sections herein. One instantiation of this sensor system takes the form of a battery powered Bluetooth low energy beacon (that may be embedded or surface mounted in building materials) and a battery powered Bluetooth and cellular gateway pair (that may be mounted onto a construction plant or machinery). In such an example, the beacon may contain an accelerometer and onboard temperature sensor. This system may be suited for 4D Location tracking (e.g., location and associated time tracking). In other embodiments, the location tracking may be an aspect of the device firmware rather than a separate logic. Other embodiments may also allow information flows and interactions to occur across device as well as within device types so as to provide self-healing applications. Example Enabling Toolkit

[0121] With continued reference to FIG.15, the enabling toolkit may form the basis set of methods that, in various combinations, feed the value-chain toolkit. The value-chain toolkitmay include registration of an element to a tagging device, entity storage location determination and optimization, entity tracking, state and state change determination, process determination; estimate time of arrival (ETA) estimation; route generation, and / or non-conformance determinations. The enabling toolkit may include methods that use signal processing for inferences, as well as machine learning based methods. For example, an unsupervised neural network fed tracking / inference data may be able to learn to recognize interactions and interaction nature to understand processes. Once learned, knowledge of prior trends in the construction object's lifecycle may enable the engine to predict future behavior and estimate consequences of particular construction operations. Given optimization parameters, such a model may be able to generate, optimize, or recommend optimal ways of coordinating construction logistics. This may be applicable during the construction process as well, in real- time, in response to anomalies and / or unexpected events. Multimodal machine learning approaches may also be used to ingest and interpret the various data streams that are being tracked and / or inferred to run optimization. Example Value Chain Toolkit

[0122] The value chain toolkit includes sets of methods that may output data indicative of instructions, plans, schedules or otherwise spatio-temporal evolutions of logistical instances, or otherwise manage and / or coordinate entities on industrial, construction, manufacturing, warehouse or other such contexts or settings. The value chain toolkit may ingest data from any data source herein, including data generated by the core toolkit methods, as well as any inferences, predictions, or other types of data generated by the enabling toolkit methods, but also data extracted from documentation and records, APIs, machinery (e.g., machine data) and others. The value-chain toolkit may evolve a given logistics instance from an initial state Pito a final state Pf, according to objectives defined in an objective function, as well as constraints. The value-chain toolkit algorithms, models, and / or methods may be used continuously such that their operation does not end once a state Pfis reached, rather, the models are tuned to continuously generate plans and iterate on plans such that for example a factory may continuously be optimized. Other types of methods exist in the value-chain toolkit such as design-stage or design methods. These comprise methods which generate optimal designs for entities and / or contextual conditions or settings entities exist in, in whole or in part.

[0123] The final section includes cross-value chain methods and / or models that may be applicable to any one or pluralities or combinations of stages in the value chain. The cross- value chain method also presents generalized methods and considerations that enableapplication to any logistics instance in any setting including construction settings, industrial settings, manufacturing settings, warehouse settings and / or others. Data Sources

[0124] The embodiment of the present disclosure may leverage any number of data sources based on the intended application of the systems and methods. For example, the core toolkit algorithms may include data output by core toolkit methods. This may include continuous position data and continuous interaction data that may be used to build the interactions sequence, with associated timestamps for entities or otherwise. In one embodiment, the COs and CAs may be instrumented so as to enable location and interaction tracking for all objects and assets from factory to site. In other embodiments, COs and CAs may be partially instrumented providing partial data. In such cases, generative methods may be used to fill in the missing data.

[0125] The state and state change determination algorithms may include data output by state and state change determination methods. This data may include the state as well as state change of any entity or group of entities described herein including CO, CA, CC, and sensor entities. In some embodiments, the state and state changes of entities are fully determined. Additionally or alternatively, the state and state changes of entities may be incomplete. In such cases, generative methods may be used to fill in the missing gaps.

[0126] The data used by these toolkits may include human input data that is inputted by humans manually into the system. This may include, for example, data indicative of whether a CO has been dispatched, target end installation location for a CO, failure or malfunction of a CA, and other such information.

[0127] The toolkits may further leverage documents, such as physical and digital documents. In one embodiment, documents may include documentation certifying the completion of an interaction, which may be used to infer state change (e.g., document showing the time and date that a precast unit left the oven and was created). Some document types includes data indicative of temporal progression such as schedules themselves in any format (e.g., Gantt chart, lookaheads, project schedules, and any other data indicative of processes undertaken for temporal progression, and any other format clear to someone skilled in the art as representative of temporal progression). Additionally or alternatively, documentation includes specification documentation. This may include specification documents for construction assets (which may include operational instructions and constraints on the asset if for example the CA is plant and machinery, and any other data found in specificationdocuments as would be clear to someone skilled in the art), specification documents for construction objects (which may include strength requirements for precast units, and / or other requirements, geometry data associated with the shape of COs, installation data associated with methods the unit may be installed in the final structure, and any other data found in specification documents as would be clear to someone skilled in the art).

[0128] In some embodiments, the toolkits may leverage sensor context awareness data as well as real time data gathered by sensors (e.g., real-time sensor data). The models described herein may take as input data from sensors in real-time. Additionally and / or alternatively, real- time sensor data may be the output of some methods and techniques herein. The sensors herein may include the sensor devices and systems defined above and described herein associated with location and interaction tracking (e.g., beacons, gateways and others). This enables the models to have continuous awareness of the real time location and the sequence of interactions (and / or processes) underwent / undertaken by COs and CAs, as well as CCs, when instrumented. Using sensor context awareness based methods, the models may also have information associated with the sensors themselves herein (e.g., internal temperature of sensors). In addition, real time sensor data may include data from wave-based sensor devices to monitor states and material properties of COs, CA, CCs, and sensors themselves (e.g., spectrum data gathered from photonics and / or spectroscopy based devices, or mechanical impedance data gathered from mechanical wave based sensor devices). Additionally or alternatively, imaging devices (e.g., cameras capturing video feed in the visible spectrum, as well as hyperspectral cameras may be instrumented in the setting of interest (e.g. prefab factory, site, warehouse, chemicals manufacturing factory, etc.) to monitor events and / or interactions as they occur in real time. This may be used for determination of state data as well as determination of other identifying and / or spatio-temporal data (e.g., for CO, CA, CC, sensor) as described herein. Such data may be further processed using machine learning techniques such as machine vision for identification of entities in the instance and / or setting.

[0129] The toolkits may further leverage machine data including information gathered from machine records. For example, this data may be used for determination of a given machine’s malfunction (e.g., concrete oven and / or any other CA). The toolkit may further include data from APIs and other systems. The models described herein may access data through interfacing with other systems. For example, the models of the present disclosure may use weather APIs to access live and historical weather data, as well as weather forecasts that may impact the outputs of the models herein. Generally, any method herein may be a data source such that data output from any method herein may be used for any other method herein.Object and Data Types

[0130] Many object and data types are considered by the embodiments described herein. For example, CO data includes data indicative of characteristics of a CO, as well as its evolution is space-time, such as CO identifying data and CO spatio-temporal data. CA data, for example, may include data indicative of characteristics of a CA, as well as its evolution is space-time including CA identifying data and CA spatio-temporal data. As defined above, contextual condition data may include data indicative of the context COs and CAs exist within, as well as the evolution of this context is space-time, such as contextual condition identifying data and spatio-temporal contextual condition data. Sensor device data may include data indicative of attributes of a sensor, such as sensor identifying data, sensor context awareness data, and sensor real-time data. State data may include data indicative of the state or current conditions and attributes of any entity or point in space time, and interaction data may include data indicative of interactions or events happening in space-time, including interactions and process data. Association data may include data indicative of any association between any entities identified herein, and demand data may include data indicative of any demand or orders for entities, including COs, as well as any data associated with this demand (e.g., deadlines by which the demand must be met).

[0131] Without loss of generality, identifying data of any type may be used to identify objects as discrete entities by the models herein. In some instances, the output that the model seeks is a spatio-temporal representation of an optimal set of events or path to reach a target progress state Pf from Pi. To do so, the model may be able to identify discrete entities. Spatio- temporal data (e.g., relevant for CO, CA and contextual condition data) may be used to instill a conception or embedding of time evolution and space into the models herein. Logistics deals with the coordination of processes within a given space, over a given timeframe, the models may need to therefore understand spatio-temporal processes. One may represent spatio- temporal events as sequences of interactions and / or processes. Using the interaction algorithms described herein, the models herein may be trained to understand events and evolutions in space time. The models herein may include internal representations of how entities associate, and interact with each other, as well as what dependencies exist between these entities, which illustrates the use of association data. Finally, the models herein may consider the demand that exists for COs, which will dictate processes across the value chain from manufacturing to installation.

[0132] All data types herein may be inputs or outputs of the methods, systems and / or models herein. Any hard requirement on any data type herein may be considered a constraint in any method, system and / or model herein. Example CO Data

[0133] In some embodiments, CO Data may include CO identifying data and CO spatio- temporal data. Examples of COs may include one or more of: precast slabs; curtain wall facade systems; prefabricated chimneys; elevator shafts; foundation systems e.g. precast concrete foundation blocks, precast concrete pile caps; bathroom pods; HVAC units; roof trusses; modular clean rooms; balcony modules; rebar elements; beams and columns e.g. precast concrete beams and columns, steel beams and columns, glue laminated timber beams (glulam); wall panels (e.g. insulated wall panels, timber frame panels, structural insulated panels, cross- laminated timber panels, glazed panels, metal panels); floor panels (e.g. precast concrete floor slabs, timber panels; roof panels e.g. precast roof panels, timber roof trusses and panels, metal roof panels; room modules (e.g. bedroom modules, living room modules); kitchen pods; office pods; bathroom pods; electrical distribution panels; plumbing risers and assemblies; power supply units; partition walls; railings and fences; prefabricated storage units; green roof modules; precast parking decks; stud wall frames; floor joists; windows; insulation panels; anchor bolts; and any other such entities. The methods and systems disclosed may be applicable to any CO listed herein and any such CO.

[0134] CO identifying data may include any information or attribute that defines wholly or partially a given CO as a discrete entity with properties. The CO identifying data may include CO ID (e.g., any identification tag (e.g. serial number, QR Code, name, registration identity on a digital platform and other)), and / or CO Type. In one embodiment, this may be selected from a pre-existing set of types. In another embodiment, the CO identifying data may be defined with more flexibility (e.g. using an LLM to identify the type of a given CO will not use a pre- existing list, but rather use language to attribute the CO a type).

[0135] This may also include CO specification data that may include any data typically found in specifications of COs, such as CO material composition (e.g., a full composition of the raw materials comprising a CO). This composition may be decomposed into chemical elements, molecules, compounds recipes, and other types of representation of material based composition. The CO specification data may further include CO installation mechanism type - data associated with the mechanism used to install COs into the building (e.g., latches on left corner of CO that attaches to another unit, adhesive based mechanisms, embedded rebar basedmechanisms and other) and CO 3D Geometry (e.g., full information regarding the geometry and dimensions of the CO in 3D space). The CO specification data may further include CO specified or derived properties including specified properties of the CO and / or other properties of the CO that may be derived by known information associated with the CO including, for example, compressive strength grading, density, homogeneity, average particle size, fineness, embodied carbon, shrinkage grading, tensile strength, flexural strength, stress, strain, specific surface area and other such defining properties (not measured in real-time, in this case, these are specified metrics). Any other data which may be found in CO specifications or identifying attributes associated with the CO.

[0136] CO spatio-temporal data may include any information or attribute indicative of the state definition of a CO at a given moment in time ti, as well as the evolution of that state over a time interval dt, which may represent a time interval of any scale. This may further include CO space discrete temporal data that is spatially discrete data that applies to the CO as a single entity of volume ΔV. This may be considered from the frame of reference of a discrete location L within the CA (e.g., discrete point location of the hook, if CA is a crane). CO spatio-temporal continuous data may include spatially continuous data which applies to the CO at any volume dV within the CO, wherein dV may represent an infinitesimal subsection of the CO’s volume, up to the full volume of the CO.

[0137] CO space-discrete temporal data may include the CO state that is the states and state changes of the CO from the set of possible states as outlined in the state and state change determination algorithm, or any other CO states as would be clear to one skilled in the art over any time interval dt. CO average location may refer to the position of a CO over any time interval dt, in 3D space, either in absolute (e.g., latitude and longitude) or relative terms (e.g. relative to a floorplans defined according to the center of mass or other), and CO average displacement may refer to the displacement of a CO over any time interval dt, in 3D space, either in absolute or relative terms. Other CO space-discrete temporal properties may includes spatially discrete physical properties of the CO such as bulk properties and / or other properties of the CO over any time interval dt (as opposed to specified or derived quantities mentioned elsewhere herein, these represent the real properties as the CO evolves through time) For example, these properties may include compressive strength, density, fineness, embodied carbon, shrinkage, tensile strength, flexural strength, stress, strain, and other such properties as they evolve in time, average temperature, velocity, acceleration and other such properties as would be clear to one skilled in the art. These may further include scalar, vector, or tensor quantities.

[0138] CO spatio-temporal continuous data may include CO location that refers to the position of any volume dV of a CO, over any time interval dt, in 3D space either in absolute or relative terms. Other CO spatio-temporal continuous properties may include properties of any volume dV of the CO over any time interval dt (e.g., density as a function of space and time, fineness, composition (e.g. may have different compositions of aggregates at different locations in a precast unit)), temperature as a function of space and time spatially within the CO, electric potential, pressure data, heat capacity, concentration, thermal conductivity, permittivity, permeability, speed of sound, EandM wave impedance, EandM Flux, Heat Flux, Electric Field, Magnetic Field, Stress Tensor, strain tensor, inertia tensor, elastic strain and other such properties as would be clear to one skilled in the art. These may in general include scalar, vector or tensor fields. In general any data described herein may be discrete or continuous time-series data. Example CA Data

[0139] CA Data may include CA identifying data and CA spatio-temporal data. Examples of CAs may include one or more of the following: tower crane; gantry crane; crawler crane; mobile crane; forklift; trailer; shunter; precast heat curing / precast oven / curing oven / oven; CNC machine; conveyor belt; assembly line; robotic arms; labelling machines; stamping press; batching mixer bm; transport wagon; beam and column casting machine; laser cutters; plasma cutters; waterjet cutters; hydraulic lifting table; trolleys; stacker cranes; side loader forklifts; rail carts; boom trucks; multidirectional forklifts; jib cranes; excavators; bulldozers; wheel loaders; concrete pumps; concrete vibrators; compactors; drilling rigs; pallet jacks; saws (e.g., panel saws, band saws, circular saws); automated saws; press brakes; roll formers; tube and pipe benders; sanders and polishers; powder coating equipment; planers and joiners (e.g., for wooden prefab elements); woodworking routers; mortise and tenon machinery; pipe benders and cutters; testing machinery and equipment (e.g., compressive strength testing machinery, tensile strength testing machinery, bend test machinery); tower crane; concrete mixer truck; dump truck; piling rig; scissor lift; welding machine; backhoe loader; grader; hydraulic breaker; skid steer loader; telehandler; trencher; road roller; asphalt paver; boom lift; laser level; air compressor; concrete saw; generator; water pump; chainsaw; jackhammer; laser screed; power trowel; stone crusher; hoist; pressure washer; electric drill; tile cutter; surveying equipment; rivet gun; nail gun; utility vehicle; concrete finishing machine; floor scraper; grout pump; material handler; pneumatic drill; rock drill; sandblaster; screed board; soil compactor; vibratory roller; wire saw; concrete spreader; pavement breaker; and any other such types ofplant, machinery, tools, equipment, and other such entities that may be used to evolve the state of a CO. The methods and systems disclosed in this application may be applicable to any CA listed herein, and any other such CA.

[0140] CA identifying data may include any information or attribute that defines wholly or partially a given CA as a discrete entity with properties. CA ID may be analogous to CO ID as well as CA Type which also include CA Specification data. CA Material Composition may refer to a full composition of the raw materials comprising a CA. This may be decomposed into chemical elements, molecules, compounds recipes, and any other types of representation of material based composition (e.g., steel, iron, silicon, concrete, plastic). CA interaction mechanism type may refer to data associated with the mechanism used to for CAs to interact with COs (e.g., COs loaded on top of CA; CA lifts CO (e.g., forklift)). CA 3D Geometry may refer to full information regarding the geometry and dimensions of the CA in 3D space.

[0141] CA specified attributes and capabilities may depend on the particular CA embodiment being considered. For example, a Forklift may have a maximum lifting / load capacity, mast height, load center, fork length and width, power source (electric, fuel), tire type and size, turning radius, maximum speed, dimensions and weight, operational controls, safety features (e.g. stability systems), attachments (side shifters, clamps, rotators), compliance information. An oven may have Temperature control (e.g. temperature range, controls and programmable settings for setting temperature, temperature ramping, temperature profile setting), heating capacity, power type, power consumption, heating method (e.g. radiant heat, convection current based heating), volume capacity (what volume of units can be inside at once), dimensions and weight, portability, operational requirements (e.g. voltage), steam heating, humidity settings, and / or safety features. A tower crane may have a lifting capacity, boom length, hook height and length, slew radius, hoisting speed, trolley travel speed, power source, power consumption, control system, hook mechanisms, transportation and assembly requirements. A trailer may include a maximum load weight, dimensions, maximum load volume, tire and wheel data, speed range data, suspension data, hitch or coupling type, axle configuration, trailer material composition. This may include any other information which may be found in specifications.

[0142] CA spatio-temporal data may include any information or attribute indicative of the state definition of a CA at a given moment in time ti, as well as the evolution of that state over a time interval dt. This may further include CA space discrete temporal data that is spatially discrete data which applies to the CA as a single entity of volume ΔV. This may be from the frame of reference of a discrete location L within the CA (e.g. the location of the hook, if CAis a crane). CA continuous spatio-temporal data may be data that applies to the CA at any location dL and any volume dV within the CA where dV may represent an infinitesimal subsection of the CA’s volume, up to the full volume of the CA.

[0143] CA space-discrete temporal data may include a CA state (as outlined by state machines, and any other state as may be clear to one skilled in the art), and CA average location, displacement, speed, velocity, acceleration, and CA work done (e.g., in work’s energetical sense). CA Carbon Emissions may be data indicative of the operational (or other) carbon emissions from a given CA in use over an interval of time dt. Other CA space-discrete temporal properties may include any of the properties outlined analogously for CO’s may be applicable here, as well as any other properties understood by one skilled in the art to be indicative of the state of a discrete CA entity in space and time.

[0144] CA continuous spatio-temporal data may include CA location that is the position of any volume dV of a CA, over any time interval dt, in 3D space either in absolute or relative terms. Other CA spatio-temporal continuous properties may include properties of any volume dV of the CA over any time interval dt. Contextual Conditions (CC) Data

[0145] CC Data may include CC identifying data and CC spatio-temporal data. Examples of entities that may include CCs for example include: shelving units; storage bins and containers; tools (e.g., wrenches, screwdrivers etc.); boxes; work platform; cleaning supplies; heating / ventilation / AC units; air; scaffolding; handrails; factories; site floors; storage yards; parking areas for lorries; routes and paths; storage buffers (e.g., areas used to temporarily store units); molds and / or formwork and / or formwork molds; doors; racks and shelves; walls; climate-controlled storage areas and any other entities which are likely to be found in an industrial setting surrounding COs and CAs. Most concrete elements are cast in molds, and different types of molds of different shapes and sizes, comprising different types of rebar and more may be used.

[0146] CC identifying data may include data associated with the identification of a discrete entity in a CO and / or CA’s instantiated context. Data type embodiments may include those listed for any other type of identifying data herein or that would be clear to one skilled in the art. This may include CC ID (in some embodiments, internally assigned by the models herein) or CC Type. In some embodiments, this may be categorized based on an existing database of types, which the model assigns to entities based on characteristics (e.g. shape, weight, geometry and others). Additionally or alternatively, the model may use AI methods to categorize CCtypes. Additionally or alternatively, the model may use LLM, GPT, or other language based methods to assign type. Additionally or alternatively, the models herein may generate the type assignment based on data collected from any data source herein. Additionally or alternatively, the data sources may be sensor devices. Additionally or alternatively, the data sources may be imagery based sensor devices (e.g., camera or hyperspectral imager). Additionally or alternatively, machine vision based methods may be used to categorize CCs. Additionally or alternatively, hyperspectral imaging techniques may be used for CC Data determination (e.g. temperature of a given CC entity, or of a coordinate in space-time (x, t)). The methods and techniques herein may be applicable to any other model or disclosure described herein, and particularly to the determination of CO and CA Data. CC specification data may refer to data relating to any CC entity which may be found in the CC’s specifications. Alternatively, when the CC entity is not one which includes a specification, this may be any identifying attribute of the entity. CC Spatial Data may include data associated with the any spatial feature of the contextual condition considered in the spatio-temporal instance, and additionally or alternatively the location and spatial limits of the factory, site, or other industrial setting for example.

[0147] In one embodiment, a model (e.g., an AI model) may be trained to identify discrete entities and generate identifying data based off of spatial data which may be collected through floorplans, drawings, BIM models as well as sensors such as cameras that may be installed anywhere within the instantiated context, or on drones and / or robots and any other spatial data sources as would be clear to one skilled in the art. These AI based techniques may be used to generate identifying data of any type (e.g., CO, CA, and CC identifying data).

[0148] CC spatio-temporal data includes any information or attribute indicative of the state definition of a CO and / or CA’s instantiated context, at a given moment in time ti, as well as the evolution of that state over a time interval dt. This may further include CC space discrete temporal data that is spatially independent attributes of the instantiated context and CC continuous spatio-temporal data that may apply to the CC at any location dL and any volume dV within the CC, where dV may represent an infinitesimal subsection of the CC’s volume, up to the full volume of the CC. The latter may take the form of any scalar, vector, or tensor field.

[0149] CC space-discrete temporal data may include date and time. Instantiated context type may refer to the type of location the instantiated context represents (e.g., precast factory, manufacturing factory, batching plant, cement plant, quarry, mining site, automotive factory, warehouse, electronics factory, textile and apparel factory and any other industrial setting as would be clear to one skilled in the art. Productivity or efficiency metrics associated with theinstantiated context type may refer to an efficiency of a factory that may be expressed as e.g. % of assets in use at any given moment in time. Rate of factory output may be expressed in terms of units delivered per unit time), aggregated location via latitude and longitude coordinates of the factory, average temperature, average humidity, any other data listed in analogous sections herein or that may be clear to one skilled in the art may be leveraged.

[0150] CC continuous spatio-temporal data may include for example temperature T(x, t) as a function of 3D space and time, geometry of a given context (e.g., 3D representation of factory); atmospheric humidity H(x,t); location L(x,t), and / or any other data listed in analogous sections herein or that may be clear to one skilled in the art. Device Data

[0151] Device data includes data associated with any device, sensor device or smart device in a logistics instance. In one embodiment, this may include device or sensor device identifying data, as well as sensor device context awareness data, and sensor or sensor device or device real-time data.

[0152] Device identifying data may include any data indicative of the identity of a device or sensor device. This may include, for example: device ID that is sequence of numbers, text string, and / or any other code or identifier which could be used to identify a device. In some embodiments, the identifier may be registered on a digital platform and exist as a digital twin. Device type may refer to the type of a sensor according to a type categorization. In one embodiment, categorization may be based on modality of the data sensed in the case of sensor devices (e.g., mechanical, electrical, magnetic, electromagnetic wave, spectral / photonic, temperature, positioning / movement). Additionally or alternatively, the categorization may be based on feature and / or property sensed (e.g., mechanical impedance, electromagnetic wave impedance, temperature, luminescence, spectral intensity, electric current, capacitance, location, phase shift, pH). Additionally or alternatively, any other method of typing (e.g., receiving device, actuating device, emitting device, and / or other). Device specifications data may include any data found in device specifications. This may include one or more of measurement range e.g., temperature measurement range (e.g., 0°C-100°C), frequency range (e.g., 1kHz-1MHz), frequency range, resolution, accuracy, precision, sensitivity, response time, hysteresis, voltage data (e.g., minimums, maximums, and / or recommended applicable voltage), operating conditions data (e.g., operating temperature range, operating humidity range, ingress protection rating (e.g., from water ingress)), shock and vibration tolerance, physical specifications (e.g., dimensions, weight, material, supported connector type, sensorattachment or mounting options) calibration data, compliance data, circuit diagram, bill of materials, supported communication protocols and others.

[0153] Device context awareness data may include data indicative of the state of a device or sensor device within its instantiated contextual conditions. This may include one or more of device metadata e.g. Name of a sensor (e.g. as provided by a user); device or sensor device context awareness data as described in other sections of the present disclosure, location of a device (relative and absolute) that may, for example, be determined using mesh network time of flight to position sensors relative to each other, orientation of a device; RF transmission of a device, battery consumption of a device; lifetime of a device since activation, etc. Device spatio-temporal data may be any data indicative of a spatio-temporal state or attribute of a device (e.g., its temperature). Example State Data

[0154] State Data is data indicative of the particular condition that an entity is in at any given time and / or of a milestone that an entity has reached. This may be data indicative of the state of any entity herein, including COs, CAs, CCs, and / or sensors, according to state machines. State machines may include sets and / or sequence of states indicative of key conditions entities may enter. State machines may be unidirectional or bidirectional (e.g., unit rejection or return may regress the state machine). State machines may comprise self-loops and / or any other graph structure or topology. State data may also be considered a part of CO Data, CA Data, CC Data and / or sensor device data.

[0155] Examples of states and / or state machines may comprise any herein and any other reasonably understood to denote states. The states listed herein are embodiments and / or examples of states and / or state machines entities considered herein may exist in, and the models, methods and techniques may consider. For example, the models herein may be used to generate a plan and / or spatio-temporal sequence for the evolution of any entity or plurality of entities (CO,CA,CC entity, device or sensor device entity), from any state herein to any other state herein. The methods and systems herein may also be used to consider other states not explicitly listed herein which may be characterized as states as understood by one skilled in the art. States may also in some instances be indicative of the completion progress of an instance, such as a construction instance. This may include any state characterized as such that may sit in between two states between any state in the state machine. Any state in any state machine herein may also exist independently from the state machine.

[0156] States may be associated with a construction project site. Example states may include, for example, project not started, foundations completed, substructure completed, superstructure completed, project completed, project X% completed, project sub-section X completed, all prefabricated elements have reached site, the set of prefab elements required to complete sub-section X have all arrived on site, load X has arrived, and / or the like. An example state machine relating to a concrete structure of a high rise tower of N Floors may include: not started, Floor 1 complete, Floor 2 complete, … Floor N complete where floor X complete may be understood as denoting that all concrete elements in the floor have been poured or installed in the case of precast elements. This may exist at any level of granularity.

[0157] States may be associated with a construction prefabrication factory. Examples may include: order X fulfilled (e.g., all elements from a given order have made their way to site), Yard X on factory floor is at full capacity, all precast ovens are in use, assembly lines are at 80% usage capacity, factory throughput is at X% capacity or utilization rate, Factory is closed, Factory is operational, among others.

[0158] Example states associated with COs, objects, and / or passive entities may include element created, element stored in factory, element in transit, element arrived at site, element installed. A more granular embodiment may include element created, stored in factory, assembled on trailer, dispatched to site, arrived on site, awaiting unloading, disassembled out of trailer, stored on site and awaiting installation, installed. A further granularity embodiment may include element created, in transit to storage, stored in factory, in transit to trailer, assembled on trailer, dispatched to site, in transit to site, arrived on site, awaiting unloading, disassembled out of trailer, stored on site and awaiting installation, installed.

[0159] Embodiments for other states may include element idle, element undergoing interaction, element rejected, element returned, element damaged, element has not been compliance tested, element is undergoing compliance testing, element has passed compliance test, element has failed compliance test, and / or the like.

[0160] Example embodiments for steel prefab elements may include element designed, raw materials sourced / ordered, raw materials dispatched to factory, raw materials have arrived to factory, prefab unit assembled, unit is quality tested, steel prefab-unit is stored, steel prefab unit is loaded, dispatched to site, arrived to site, stored on site, installed. Other examples of states or state machines may include steel has been cut (e.g., to required dimensions using CNC cutters, laser cutters, plasma cutters and other CAs), steel has been formed and welded (e.g., to shape them into required prefab element geometry using press brakes, welding machines and other CAs), steel prefab unit has undergone surface treatment (e.g., surface cleaning, coating,galvanization, powder coating, painting), unit pre-assembled, unit has completed visual inspection, unit has been bolted, unit has been welded, unit has been joined, unit is en route to location X.

[0161] Example embodiments for concrete precast elements may include mix has been designed, aggregates, cement, water, admixtures and / or other raw materials have been sourced, materials have arrived to the factory, raw materials have been stored on factory, concrete has been mixed, concrete has been batched, mold form is ready, concrete has been poured into mold, filled mold is transported to precast oven, precast unit is in oven, precast unit is cured, unit has undergone surface treatment, unit undergoes compliance testing, unit in transit to storage, unit storage, unit loaded, unit dispatched, unit stored on site, unit installed.

[0162] Example embodiments for Cross-Laminated timber prefab units may include timber has been sourced, timber has arrived at factory, timber unit has been assembled, timber unit has been packaged, timber unit has been loaded, timber unit has been dispatched, timber unit has arrived on site, timber unit has been installed. Other examples may include timber has been laminated, timber has been cut and shaped, timber has been pre-installed with MEP. Other states may include adhesives and fasteners have been sourced, cross-laminated timber panels have been assembled, timber unit has been tested.

[0163] In example embodiments for Readymix Concrete, the methods and systems herein may be applicable to non-prefabricated environments and used for logistics optimization of readymix concrete operations. the models herein may then consider precast concrete states mix designed, raw materials sourced, raw materials are on batching plant, raw materials are mixed, raw materials are batched, batches are loaded in truck, batch is in transit in truck, batch arrives to site, batch is pumped to pour, batch is poured, batch is curing, pour has reached design strength, and / or the like.

[0164] Some general states for CAs may include idle, in use; failure / malfunction, in motion, lifting, testing, active, free, in maintenance, on standby, shutting down, cleaning, calibrating, overload, and / or the like

[0165] States for precast ovens may include off, heating, heating at temperature T°C (hold temperature), contains units, units unloaded, cooling, off, and / or the like.

[0166] States for cranes may include off, activating, on, positioning for pickup (e.g., the crane is positioned such that it may pick up the relevant construction resource), lifting resource, positioning for drop-off, drop resource (in desired location), positioning for idling. Other examples of states may include under assembly, in use, idle, under disassembly, trolley travel, stopped, hoisting, attaching, loading, unloading, under maintenance, overload, on standby,positioning, relocating (e.g., for moving cranes such as crawler cranes), slewing, and / or the like.

[0167] Example states for forklifts may include off, on, idle, travelling, idle, rotating, lowering mast, loading, raising mast, rotating, travelling, idle, lowering mast, unloading, travelling, parking, idle, off, etc. Other examples of states may include hoisting, under maintenance, malfunction, charging, docking, and / or the like.

[0168] Example states for shunters may include on, off, idle, in use moving, coupling, uncoupling, accelerating, decelerating, loading, unloading, shunting, refueling, charging, docking. embodiments for excavators: idle, in use, digging, loading, dumping, swinging, travelling, levelling, trenching, lifting, refueling. embodiments for saws: cutting, blade stopped, blade must be changed, feeding materials to saw. embodiments for laser cutters: cutting, laser on, laser off, overheat, loading material, unloading material, beam aligning / aiming. embodiments for concrete mixers: mixing, batching, funneling. other state embodiments: welding, arc striking, and / or the like.

[0169] Example states associated with devices or sensor devices may include collecting data, calibrating, repositioning, reorienting, actuating, transmitting data, failure / failing, awake, calibrating, low battery, data logging, data processing / edge processing, in context awareness mode (in some embodiments, the sensor may enter a mode wherein it executes methods to gather context awareness data instead of its primary sensing purpose), sleeping, registered, standby, unable to connect, searching (e.g., searching for other devices in the vicinity), and / or the like.

[0170] The present disclosure contemplates that states and state machines may be combined together into larger state machines or may exist independently or in parallel. In some embodiments, mappings between separate states, which may be in separate state machines, may exist. This may include states for different entities which are evolving in parallel at the same time. State machine embodiments may exist at any level of granularity, and for any entity described herein or that may otherwise be characterized as a CO, CA, CC, sensor or other relevant entity in a logistics instance. Without loss of generality, any state listed herein as applicable to one or a plurality of entity embodiments may also apply to any other entity e.g. CO, CA, CC, sensor or other. In some embodiments, users may input custom states with associated conditions into the systems and / or methods and / or models herein.

[0171] In some cases, the word “state” in the present disclosure may also be used to denote any data indicative of an entity’s condition wherein this condition is associated with a spatio- temporal attribute of said entity (as opposed to the types of states listed herein). This mayinclude data akin to spatio-temporal data of entities as described elsewhere herein (e.g. spatio- temporal CA data, spatio-temporal CO data, spatio-temporal CC data). This may include data such as temperature of an entity as a scalar field function of space and time, velocity of an entity as a vector function of space and time, stress tensor of an entity, angular velocity of an entity and other such data that also defines the past, current or future “state” of an entity. Additionally or alternatively, state data may not be directly associated with an entity but rather with a coordinate point in space-time, or coordinate volume defined in space-time (e.g., dV or ΔV). For example, the state of a given point in space-time may be described by attributes such as temperature, pressure, and / or other parameters. The state of a factory floor may be described as the continuum state of all points in space-time in the factory. In some embodiments, these points may be represented as discrete volumes (akin to 3D pixels), defining a given space. Example Interaction Data

[0172] As defined above, discrete events in spacetime may be represented as interactions. Interactions may comprise a discrete occurrence of an event happening between two or a plurality of entities or construction resources. These entities may be any entity described herein or otherwise found in, construction, industrial and / or manufacturing logistics environments. Typically, the interaction evolves the state in part or in whole of at least one entity involved in the interaction (may include states in the state machine sense and / or in the attribute sense). Further classes of interactions may include actions, or self-interactions, that include an event involving a single entity (e.g. a sensor activating), a crane positioning itself and others, oven heating without having been loaded with any units, shunters shunting unloaded trailers, and / or any other such event. CA-CA interactions, CA-CO Interactions, CO-CO Interactions, moving interactions (e.g., many of the interactions considered herein are between movers and entities being moved), manufacturing interactions (e.g., an interaction that is part of a manufacturing process (e.g. a laser cutter cutting a steel element)), testing interactions (e.g., interactions associated with the testing of an entity), multi-entity interactions (e.g., interactions may occur between more than two entities) may also be included. For example, a trailer carrying many precast blocks may be an interaction between one CA and many COs (e.g., may be represented using tree graph structure).

[0173] Interactions may exist at varying levels of granularity. For example, an interaction may include a crane arm lifting a unit. An interaction may also include the full process between the crane and the unit from loading to unloading. In some embodiments, groups of interactions may be denoted a process. Processes often but not always have associated objectives. Forexample, the process where a tower crane loads and unloads a unit on site may often include installation of the unit as the objective.

[0174] Examples of interactions may include laser cutter cutting through a steel unit; crane lifting a precast unit; crane arm moving a precast unit; crawler crane moving a unit from location A to location B; crane loading a unit onto a trailer; molding machinery assembly mold; precast oven curing concrete; forklift lifting unit; excavator excavating soil; mixer mixing concrete; batching machine batching concrete; pump pumping concrete; pump pouring concrete; crane installing precast unit; Forklift storing unit; hydraulic press pressing on steel plates (e.g. to make them thinner); robotic arm picking CO up; forklift loading CO on trailer; CNC cutter cutting CO; welding machine used to weld two entities together; automated saw cutting CO (e.g. wooden unit); vibrators vibrating concrete; hammer hitting nail; drill drilling hole into CO; bolt being installed into CO; Two COs being joined together using anchors; CNC benders bending steel units; casting CO in a staircase mold; casting CO in a lintel mold; automated formwork system assembling molds / formwork; production of wall panels using a panel production line; concrete conveyor transporting concrete; Extrusion machines producing hollow core slabs; surface finishing machine texturing a precast element; assembly robots used to assemble particular COs; sandblasting machine texturing the surface of a concrete element; packaging machines being used to package units; 3D printers printing units or unit components; epoxy coating machine coating a CO; Load Testing Machine testing load bearing capacity of entity; forklift moving on its own; CA turning on; laser cutters activating for calibration; crawler crane relocating; tower crane arm rotating without carrying unit; One entity falling on another entity, these may be COs; oven preheating; sensor device re-orienting. The interactions examples herein may in general be applicable to any entity or construction resource herein.

[0175] In some embodiments, a set of spatio-temporal events through time in an industrial setting (e.g., prefabrication factory all the way through to the site) may be described as a sequence of actions and / or interactions. It is through interactions (and actions or self- interactions) that factories, sites and other industrial settings complete their objectives and / or may evolve from state A to state B (e.g. building a structure, manufacturing an automotive vehicle etc.…). Construction Interactions and Processes may be represented as graph networks of varying topologies. In some embodiments, the methods described herein may include searching for the shortest path on the graph network of interactions to seek the optimal sequence of interactions to reach a given state. Example Association Data

[0176] Association data may include data indicative of any associations between any or all of CO’s, CA’s and / or CC entities. In some embodiments, this data may be stored using graph networks or relational databases. Spatio-Temporal Entity Association Data may include, for example, the following or the answers to the following questions: Are COi and CAj part of the same interaction?; Is COibeing transported by CAj?; What is the spatio-temporal pressure exerted by CRi onto CRj; Heat transfer between CRi onto CRj; Work done by CAj onto COi; What route Riis CAjdriving on?; Pressure applied by entity A onto entity B; CO A is stored on shelf B; CA A is travelling on section B of route C; The set of COs {COi} comprises Load i, which is travelling to the site on Delivery Truck D; Steel element A is being cut by laser cutter B; Magnetic strength between sensor device enclosure A and Construction Asset (e.g., crane) B; Prefab Factory A has to deliver NB, NC, NDand NEunits to Project Sites B, C, D and E; Project Site A has requested units from factories B, C and D.

[0177] Dependency Data may include a data indicative of dependencies of two or more entities upon one another. Dependencies of COs on other COs may answer the following questions, such as Does COArequire COBto be installed before it?; Does type A of CO’s only attach to type B of CO’s?

[0178] Example dependencies of COs on CAs may answer the question Can COAonly be handled by a CA of type B? Dependencies of CAs on CAs may also exists. In one embodiment, a large site may be configured with a network of tower cranes. In such an embodiment, cranes may be able to transfer units to one another. One example of dependency of CAs on CAs is answering the question which intermediary cranes are accessible to Crane A, and / or which will be able to pass on a CO to Crane B? General dependencies and associations may further exist. For example, a storage Yard A may be designed to store entity type B; Assembly line A may be designed to manufacture precast element types B; prefab units A, B, C, D, E, and F are required to be combined (e.g. welded together, bolted together and / or other types of manufacturing and / or combination and / or assembly methods) in sequence G to form prefab unit H. Example Demand Data

[0179] Demand data may refer to data in any format that is indicative of the external demand on a unit outputting site (e.g., factory, warehouse or other plant). In one embodiment, this may be an order (e.g., formatted as a list or the like) of prefabricated units, including number of units required as well as CO identifying data detailing requirements for every unit, as well as other terms present in orders of this type such as expected order delivery deadline,safety guarantees, and other terms as would be evident to one of ordinary skill in the art. In another embodiment, this order may fluctuate over time. In another embodiment, this may be multiple orders from different stakeholders. In another embodiment, this order may be fulfilled by a number of unit outputting sites. In a further embodiment, the demand may be generated and continuously re-adjusted by an AI Model.

[0180] Examples of demand data may include: Demand from Site A: 500x precast unit A, 200x precast unit B, 10x staircase, 50x steel units A; by date A. Demand from Site B: 50x window panels; 50x facade panels; by date B. Demand from Site C: 100x cross-laminated timber units; 20x steel beams; 40x precast foundation units; by date C. The models described herein may be configured to ingest this demand as inputs, and generate plans that fulfill and balance these demands based on the deadline constraints and objectives. Data and Object Formalism

[0181] In some embodiments, the Logistics Tools (LT) of LOSS collection uses object and object compositions to define a hierarchical system of datatypes (over and above in-built datatype such as: int, float, list, map) that may uniquely define the operational space. These may represent the internal representations the models, systems and methods herein use when considering the data, datatypes, and data classes herein.

[0182] As described in this section, datatypes may denote data that may be compositionally uniform in their representations. For example, position datatypes may be formed of a set of tuples that allow various representations. A data class (e.g., CO data class) may refer to an object of higher complexity that may include a collection of several objects, that are either attributes (that may be defined by other datatypes) or methods (that may be defined by operations on a set of datatypes) and may be directly pertinent to the definition or operations associated with the entities under consideration (e.g. construction objects). Some LT objects considered by the systems are described hereinafter.

[0183] Position datatypes may denote the position of a point P in a coordinate system relative to an origin O (that may be local to a site or global to the Earth). The type of position datatypes may be tuple of usually 3-dimensional position vector but may be generalized to N dimensions (polymorphisms will be invoked to enable spanning of multiple coordinates systems). Representations may include cartesian (x, y, z) or spherical polar coordinates (r, theta, phi) (or elevation, latitude, longitude). Generalized coordinates may include (p, q, r) in an arbitrary frame of reference (e.g., a factory floor space with levels for the height dimension or graph coordinates in a grid network).

[0184] Spatio-temporal datatypes may operate to map time to position (represented as a key-value pair). The type of spatio-temporal datatypes may be map (or dictionary) with Date Time type as key and Position datatype as value. Interaction-pair datatypes may create an association between a set of datatypes (may include positions, entities, CO, CA…). The type for spatio-temporal datatypes may be tuple (for undirected interactions) or a map (for directed interactions). LT Routing datatypes may be an ordered sequence of nodes (e.g., positions), representing a route (or a sequence). More generally this may be viewed as a chain of interactions. The type for LT Routing datatypes may be an ordered list representing the path wherein a set of nodes (e.g., positions) connected via edges (e.g., journey between positions) may be traversed. Attributes of this datatype may be distance, duration, with the option to encode directionality (directed graph).

[0185] LT Graph class may refer to networks of connected entities that may include positions, interactions, routes, graphs (for graphs-of-graphs) and / or any other attribute. The type for LT Graph class may operate on a defined set of nodes (e.g., positions) with edges (e.g., paths between positions). Attributes for LT Graph class may be spatial bounds that may in some embodiments limit the scope of the graph. The methods for LT Graph class may include route generating methods such as BFS, LFS, shortest paths (such as Dijkstra), max flows and other such methods.

[0186] CO class may refer to a collection of attributes and methods associated to Construction Objects in the LT. The type of the CO class may be a class that combines a set of CO attributes and CO methods. The attributes may be the following: CO_ID: String type: Identification tag (e.g., serial number, QR Code, name, registration identity on a digital platform etc.); CO_type: Categorical type may indicate the type of CO (e.g., beam, column etc.), and this may be a method for auto-classification (e.g., ingesting visual inputs that invoke an object identification module with CNN using NLP / LLM for text interpretation from the image); The CO_material may be a tuple type, indicating composition of raw materials including a CO. This may also include a map type, where composition identifier will provide attributes (e.g., weight, volume, consistency). The CO_Installation_Mechanis may be a map type, data associated with the mechanism used to install COs into the building. The CO_Geometry_HighLevel may be a Tuple type that will contain high level details that define the weight and form-factor. The CO_Geometry_Detailed may be a string type, Identification tag relating to a BIM ID or STEP Instance Name that may be used to extract, geometry, and dimensions. The CO_SpProperties may be a Map type and contain specified properties of CO, such as compressive strength grading, density, homogeneity, average particle size, fineness.The CO_DiscreteTimeData may be a map type and encode properties that track or evolve after a distinct event has occurred for example, key: (ti, t{i+1}), value: state of manufacturing for CO (mixing, curing, cured). This may be a meta-state attribute that includes several state machines: manufacturing, interaction, transport, installation with a meta-state tag tracking evolution from one state to the next. Other properties may include site association, location, displacement, and other bulk properties that may be tracked and evolve discretely.

[0187] CO_DeProperties may refer to a set of procedures for properties derived from known CO_SpProperties attributes. For example, eEmbodied carbon (with known manufacturing method, composition etc.) may be used. CO_TimeSeriesData may refer to a set of procedures, one for each attribute that is tracked temporally. For example, the Location method may be sent as input a CO-ID and an interval of time, from which the method constructs a query to a timestream database to return the locations for the object in that time interval. As output the method will return a vector of position datatypes. CO_DerivedTimeSeriesData may refer to a set of procedures, that ingest one or more sources of time varying data and apply logic to extract a derivative piece of information. For example, internal stress during curing: may be used and the method may ingest geometric details of the CO along with oven time- series data and the recipe to analyse the 3d-stresses generated in the slab. This procedure may be defined in functional form as a method in this class or encode logic to launch an FEM model to extract the 3d-stress tensor. For example, the method may take as input the CO-ID and a time (or time interval), the function will call the CO_TimeseriesData Class and apply an operator (such as mean) to provide the location at the specified time / time-interval.

[0188] The interactions class may refer to a collection of attributes and methods associated to Interaction Pair datatypes in the CLT. This may include pairings between any or all of COs, Cas, and / or CC entities as well as pairs of interactions. This method may encode dependencies as well through a directionality metric between pairs of interactions.

[0189] The interaction class may combine a set of Interaction-pair attributes and methods. The attributes may include Int_ID: String type, Unique identifier that associate the Int_pair with Int_Starttime and Int_Duration. Int_Pair may refer to interaction-pair datatypes, where each member of a pair may belong to a set of CO or CA. Int_EdgeWeight may refer to integer type, encodes the strength of the relationship if needed (e.g., a CO_i stacked under another CO_j may be compressed under its weight, invoking a strong association and high edge weight). Int_EdgeDirectivity may refer to a string type, indicating directionality of the edge (in the above example, the CO_j being stacked on top is not affected by the CO_i weight and therefore the edge points from CO_j to CO_i). Int_StartTime may refer to a Date Time type,start of interaction Int_Duration may refer to a TimeDelta type, time in seconds, minutes, hours, days, weeks, months, and / or years that the interaction continues. Int_Type may be a Categorical type. For example, a stacking interaction between COs or a Lifting interaction between CA- CO. Int_State may refer to a categorical type indicating the intermediate states of the interaction (e.g., rigged, lifted, dropped). Int_Location may refer to a tuple pair of Position datatype, indicating start and end locations of interaction. Int_metadata may refer to a Map type that includes information such as contractor associations, risk estimates of interactions composing schedule. Int_Forbidden may refer to a map type with key forbidden pairs with a Boolean value. For example, cranes on two different sites may not be allowed to interact and are therefore added to facilitate error checking. This may also be written as a method where inter-site dependencies for static assets may be forbidden.

[0190] Some example methods include: Int_WorkDone that is a method to extract the work done by CA_j on CO_i. Int_Pressure may be a method to extract the pressure exerted by CO_j on CO_i in a time interval. Int_Route may be a method that uses the interaction attributes and returns a LT Routing datatypes. A schedule class may refer to a collection of attributes and methods that operate on a set of nodes (CA, CO, CE…), or a set of Interaction-pairs or a set of Interactions or a set of CL Routes. A class that ingests a set of nodes, or sets of Interaction- pairs, or a set of Interactions or a set of CL Routes, their attributes and methods to derive a schedule may be used.

[0191] Example attributes are provided hereafter. A Sched_ID may refer to a string type, unique identifier to extract the schedule. Sched_nodes may refer to a set type, of ‘nodes’ for which a schedule is to be generated. Sched_InteractionPair may refer to a set of interaction pairs from the set of Sched_nodes. Sched_Interactions may refer to an interaction datatype that complements the Sched_InteractionPair. Sched_route may refer to a CL Routing datatype that stores the sequence (or a set of parallel sequences) of operations / organization of Sched_nodes. The Sched_Times may refer to a date time pair that timeboxes the schedule. Sched_Schedule may refer to a map type, and / or collection of interactions with imprinted times with a key Int_ID (from Interactions class), value: tuple of start, end times) of interaction. Sched_metadata may refer to a map type that may include information such as contractor associations, risk estimates of interactions composing schedule.

[0192] Example methods are provided hereinafter. Sched_Generator may refer to a method that will ingest the Sched_times and either Sched_nodes, Sched_Interactions or Sched_route to produce as output a Sched_Schedule. As an example, the most general method that ingests specified Sched_nodes and Sched_times may be considered in which compute theSched_InteractionPair, Sched_Interactions and generate the Sched_route occur. Time boxes may be used to act as constraints to specify times or generate reroutes (reorder the sequence) to produce the schedule.

[0193] With reference to the graphical representation 700 of FIG.7, construction resources may be represented as nodes and interactions as edges. A sequence of interactions (e.g., processes) may therefore be represented as a graph network. Further information may be encoded into the nodes of the graph to denote whether a given construction resource acts as a construction asset or construction object in any given interaction. Other properties or attributes of graph networks, or types of graph networks which may be used by the methods herein for data representation, inference, extraction or for the models herein to execute their methods may For example, network degree; transitivity; scale-free networks; centrality; connected graphs; unconnected graphs; directed graphs; undirected graphs; loops; adjacencies; path nodes including trails, and / or cycles (e.g., for representing routes; connected graphs, weighted graphs) may be used. For example, the data above may be arranged into a database where each row denotes a different interaction, and data relating to the ID, States, routes and paths, CO2 emissions etc. associated with every CO and CA for the given interaction are listed. With reference to FIGS.7-8, the constructions logistics representations 700, 800 may occur as (a) a graph where each process P_i has an interaction with a subsequent process P_(i+1), or as (b) a sequence of modular processes where output of a process P_i serves as input to the next one in the chain (P_(i+1)) and so on. The feedback loop is represented as sub-process P'_i, with an allowance for self-loops. This graphical r

[0194] With reference to FIGS.9-14, example graphical representations of interactions and states in the generation of the spatio-temporal sequences are illustrated. In FIG. 9, a state and interaction graph 900 is illustrates with all intermediate states between the initial state P1 and the final state P12. The systems and methods described herein may generate an example first spatio-temporal interaction sequence 1000, an example second spatio-temporal interaction sequence 1100, an example third spatio-temporal interaction sequence 1200, and / or an example fourth spatio-temporal interaction sequence 1300. As shown in FIG. 14, the systems and methods may then select an optical sequence based on an objective function associated with the particular project, asset, object, etc. Although described herein with reference to a first, second, third, and / or fourth sequence 1000, 1100, 1200, 1300, the present disclosure contemplates that any number of spatio-temporal sequences may be generated for selecting an optical sequence without limitation.

[0195] Additionally or alternatively, the methods herein may employ further properties or attributes of graph networks, and / or types of graph networks for data representation, inference methods, extraction methods, and / or for model execution across any type of model herein. Examples of graph properties and / or graph types that may be used include but are not limited to the following: network degree; transitivity; scale-free networks; centrality; connected graphs; unconnected graphs; directed graphs; undirected graphs; loops; adjacencies; path nodes including trails, cycles (e.g. for representing routes; connected graphs, weighted graphs). In some embodiments, the methods herein may use a plurality of graph networks to store data associated with different attributes e.g. a graph network for representing paths or routes taken by entities, a graph network for representing spatio-temporal sequences, a graph network for store state and state changes associated with entities, a graph network for representing interaction sequences. Additionally or alternatively, the methods herein may include connecting a plurality of graph networks with each other, such that graph networks may be associated. In some cases, this may be a 1-1 mapping, or many-to-many mappings. For example, state graphs may be mapped onto spatio-temporal sequence graphs to create a data structure which captures data indicative of the state of entities along the spatio-temporal sequence. Additionally or alternatively, any of the methods and / or disclosure associated with graph networks, including methods (e.g. graph neural networks), and / or data storage features, may be applicable to any other method elsewhere herein.

[0196] Additionally or alternatively, any data described herein, in any method or model described herein (e.g. core toolkit, value-chain toolkit, enabling toolkit, simulations), may be stored in a relational database structure. Additionally or alternatively, association data may be represented by the relations in this relational database. Additionally or alternatively, the relational database includes tables for each entity herein, which contains information associated with entity state, entity identifying data and / or entity spatio-temporal data such as IDs, state data, route data, path data, interaction data, CO2 emission data and / or any other data described in the data section herein. Additionally or alternatively, the data associated with any entity may be accessed and / or extracted using keys which may act as identifiers, for example, primary keys, foreign key, unique keys. Additionally or alternatively, the database may include the complete or partial version history, which comprises any historical data associated with an entity at time ti in the past. Additionally or alternatively, the database may continuously update based on real-time data. At each time ti+1, the database may include an evolution protocol wherein data associated with this discrete time may be adjusted. The output may then be a version history of databases or relational databases, which comprise individual databasestructures for every time tiin the past. Additionally or alternatively, a key may be used to access historical versions of data, such that the database may be queried with the key and output data associated with a given point in time. Additionally or alternatively, the relational database may include tables for each interaction herein, which contains data associated with interactions such as start time, end time, entities associated with the interaction, entity states during the interaction and / or spatio-temporal data associated with the interaction. Additionally or alternatively, the relational database features described for entity based databases may apply for interaction based databases (e.g. keys or identifiers for accessing interactions or groups of interactions or categories of interactions, version histories of interactions etc.). Other relational database properties or attributes or features which may be used by the models and / or systems and / or methods herein to store data may include any of the following: atomicity; consistency, isolation, durability, normalization, indexing. Additionally or alternatively, entities may be COs, CAs, devices, and / or CC entities.

[0197] Table 1 below provides an example of a data structure schema to store entity data herein. When querying an entity ID, this allows the system to retrieve and output any and all data associated with the entity. Similarly, an interaction based data schema may also be used. Additionally or alternatively, one such table may exist for every discrete time ti, wherein the values in the table may update for each time. TABLE 1: Entity ID Type State location Interaction state Weight Dimension …Data Features and Processing

[0198] The following data processing and feature engineering disclosure may classify, clean, fuse, and extract features that may enable the models herein to perform specified actions. These may be classed into the following, non-exhaustive categories. It is to be understood that other classifications may be applicable. Data Processing

[0199] Input data streams may be cast into categories. This may include, for example: CO classes (CA, CC) will include Interaction datatypes, related dependencies (or conflicts) and times (targets / milestones). The data processing step may analyze data (real-time, historical, contextual) to automate the categorization of data types. The Ingestion of historical data may be used to identify patterns, such as sources of delay, throughput deviations from targets. Data cleaning may be used such as Anomaly identification and data imputation which includes infilling data (for example with ensemble averages, mean in interval), flagging intervals with anomalies, or entirely removing intervals with missing / incorrect data.

[0200] Ingesting and fusing various data sources may be used. This may include, for example, crane telemetry and usage metrics. The feature engineering step may fuse real-time data streams, which include imaging streams with location (GPS and accelerometers for motion) and orientation sensor streams obtained from gyroscopic and magnetic sensors. Image detection methodologies may be fused with data from these position / motion / orientation sensors provide an accurate reference of the GPS coordinates as well as height of the crane hook at a given time. In addition, operational considerations may be bolstered by information from instrumented hook block where load cells on lifting arm will indicate when a load is lifted. The specifications of these construction assets are also ingested to account for lifting scope and range.

[0201] Feature engineering may also be used. This step may include data integration methods to extract pertinent data into a unified dataset for analysis. Normalization and preprocessing of the data may be required for compatibility and accuracy. Sensor stream specific actions may also be involved as well. The final product may be a generated dataset that is a derivative or transformation of the dataset conditioned for lift sequence table population such as to enable further analysis. Data Features

[0202] Data features of interest may be classed into the following categories for data / information processing and feature extraction. In some embodiments, these data features may be associated with data from core toolkit devices such as beacons and / or gateways or others. Generally, these data features may be associated with data collected by any device and / or sensor device herein. These features may also be associated with data collected from any source herein.

[0203] Ensemble Methods may be used such as timeboxed, static estimates. Example features may include signal strength (e.g., mean, variance, min / max, median, percentile,bounds over the interval of time) and / or GPS (Lat / Lon) (e / g., mean, variance, bounding-box (area) estimation over the interval of time). Rate methods may be timeboxed, dynamic estimates. Features may include signal strength (e.g., rate of change of signal strength in an interval, loss of signal intervals, etc.) and / or GPS (e.g., distance, speed, orientation of travel).

[0204] Temporal features may be used in which seasonality (periodicity) patterns may be understood, typically applied to individual series such as signal strength or derived GPS data (e.g., proximal distance from a mean in a given interval), Average tracked by hour of day, day of week, month, season, time since an event (e.g., manufacture), and / or the like.

[0205] Variation Analysis may be used. For signal strength, features may include signal strength change. Pre-processing often requires smoothing using rolling statistics (e.g., mean, std dev, sliding window). For GPS, clustering may be to identify common coordinates (indicative of parking area, used to filter out), proximity to target areas, and / or density in target areas. Combined streams may be used with signal strength at specific locations, mean signal strength at targets locations, signal strength variation between locations, and / or variability of signal strength between specified locations. Anomalous features may be used. For outliers, these may be identified and flagged in signal strength (loss of signal) or GPS coordinates (such as out-of-bounds, or low accuracy). Granularity of Data

[0206] A highly granular plan may outline every given step in high specificity, whereas a non-granular plan may outline only a few steps. For example, consider a scenario where the model should output a plan for a forklift currently at location L, to bring a precast unit CO1from location A to B. One generated plan may take the following form (with associated timestamps for each step).

[0207] The forklift is activated / turned on, and Forklift travels across route R1from location L to location A, at speed S1. This may be carried out by an operative, or autonomously in the case of an autonomous vehicle. All methods described in this disclosure may also be applicable to embodiments of factory / industrial settings comprising autonomous plant and machinery or CAs, in whole or in part. In such an embodiment the models herein may communicated directly, through wired or wireless connection, with the relevant autonomous units to issue directives. The forklift stops at coordinates c1, 1 meter adjacent of CO1; Forklift rotates such that it positions itself facing CO1directly; Forklift mast is lowered; Forklift loads CO1 onto its mast; Forklift lifts mast carrying CO1 by 0.5meters; Forklift rotates back towards path; Forklift travels across route R2from Location A to Location B at speed S2(which willlikely be slower than S1, given the forklift is now carrying a load); Forklift stops at location B; Forklift lowers mast; Forklift unloads unit onto desired location B.

[0208] Another generated plan may take the following form (with associated timestamp with each step). Forklift travels across route R1 from location L to location A, at speed S1; Forklift loads CO1; Forklift travels across route R2from Location A to Location B at speed S2; Forklift unloads CO1 at B. The former is of higher granularity than the latter. The plans generated by the models herein may without loss of generality, be associated with construction instances as a whole (as opposed to a single CO. The concept of granularity may be applicable to any data type or entity, beyond plan data. This includes but is not limited to spatial data, state data, spatio-temporal data, association data, dependency data, demand data and others. Data Extraction Pipeline Methods And Embodiments

[0209] The systems and / or methods herein may ingest or extract data from any one of the following list of records, documents, and / or machine data sources. Production records may hold information associated with the manufacturing process of each precast element. This may include detailed manufacturing details such as batch numbers, production dates, and specifications. Additionally, these records encompass quality control reports, which contain data on quality checks, inspections, and test results for each element. Inventory records may hold information or data associated with the current stock levels of precast elements, specifying the quantities and types of elements available. They also may include information about storage locations, detailing where each element is stored within the factory premises.

[0210] Tracking and movement records involve data captured from various sources to monitor the movement of entities. This may include beacon data, which may include unique identifiers for beacons attached to each precast element, and / or gateway data, detailing the locations of gateways and their coverage areas within the site. Additionally, movement logs may offer real-time tracking data of the elements as they progress through different stages of production, storage, and loading. Additionally or alternatively, data from any device or sensor device, or smart device type herein may be used as tracking and movement records.

[0211] Logistics records may include documentation and / or records and / or data associated with the transportation of precast elements. This may include for example loading logs, which may contain data associated with when and where an entity is loaded onto a truck. Dispatch records offer information on trucks, including identifiers, departure times, and destination details. Furthermore, delivery confirmation data confirms the delivery of elements to their respective sites.

[0212] Operational records may include comprehensive site layout maps and / or floorplans, which may contain spatial data associated with factory and storage areas and may indicate the placement of gateways and pathways for element movement. Additionally, these records may contain equipment and machinery data, providing information on the machinery used in production, including maintenance schedules and operation logs. Compliance and regulatory records or documentation may include data associated with industry standards and / or guidelines. This may include safety standards documentation environmental regulations records, and / or other such compliance documentation, which may be ingested by the systems and / or methods herein, which may extract compliance constraints and / or requirements on for example any spatio-temporal sequence that it generates. Maintenance and support records and / or documentation may include the upkeep and troubleshooting of the tracking system. System maintenance logs may contain data associated with maintenance performed on the tracking system, while support tickets document any issues reported by users and their resolutions.

[0213] Any method herein may be executed on the basis of any of the records and / or data source types or examples described herein. For example the state and state change determination methods may output or update state information associated with any entity on the basis of information sourced or otherwise ingested from any document or record described herein and any other such data source from documentations as would be clear to one skilled in the art. Data Ingestion Embodiments

[0214] The systems and / or models herein may ingest documentation, data and / or records through various methods. These may include the following. Data Ingestion from devices such as beacons and gateways may generate raw data and / or pre-processed data that may be ingested by the systems herein. For example, Bluetooth beacons may be attached to each precast element, while gateways are installed on site and receive signals from these beacons. These gateways collect data on the location and movement of each element and may transmit the collected data to a central server using Wi-Fi, Ethernet, or cellular connections, which may then be ingested by the systems and / or models herein.

[0215] In some embodiments, the methods and / or systems herein include automated data collection from production machinery. Production machinery may be equipped with sensors and / or communication devices that capture data on manufacturing details, quality control, and operational parameters. Machine-to-machine (M2M) communication enables directcommunication between machines and the central system, facilitating real-time data transmission, and enabling the systems and methods herein to be executed based on production machinery data.

[0216] In some embodiments, data may be manually entered into the systems herein by users. This may include the use of mobile apps or tablets to manually enter data such as loading logs, shift schedules, and quality control reports and / or any other data type or data record or data source described herein. Barcode or QR code scanners on devices may be used to quickly capture data about each entity during different stages of production and transportation and access the unique device identifiers associated with each entity. In some embodiments, the models and / or systems herein may integration with other systems. This may include integration with existing enterprise resource planning (ERP) systems for example, to ingest inventory records and compliance documentation. Database synchronization techniques may be used to consolidate data from different sources into a central repository.

[0217] GPS and geolocation data collection may be utilized for position, interaction, and / or state determination as well as any other determination method herein. In some embodiments, trucks may be equipped with GPS trackers to capture dispatch and delivery information. The methods herein may include geofencing based methods to automatically log when elements enter or leave specific areas. Data Aggregation and Preprocessing: In some embodiments, data aggregation and preprocessing techniques may be implemented to handle data from multiple sources, including beacons, sensors, and manual entries. ETL (Extract, Transform, Load) processes are used to clean, transform, and load data into a central data warehouse. In some embodiments, real-time data processing is executed by the systems herein, for example through the use of stream processing platforms, which may process data as it is collected. An event- driven architecture may be implemented to trigger specific actions or analytics based on real- time data events, ensuring timely and accurate decision-making. Data Extraction

[0218] The system may include methods that use automated extraction methods to gather data from a variety of digital records. The following describe embodiments of such methods that any model or method in described in any section herein may use to gather data.

[0219] Logistics settings and / or industrial settings, sites, plants, factories and / or other such locations may include documents associated with production, quality control, inventory management, and / or logistics. In some embodiments, these may be paper-based or stored as PDFs or other such document formats. These documents can include production logs, qualityinspection reports, delivery receipts, and inventory records. The systems and methods herein may include extraction of data from these documents. The disclosure herein below describes embodiments for ways that the methods herein extract this data. These methods and / or embodiments may be used for data extraction or determination for any model or system herein. For example, any state determination methods may include OCR data extraction from documentation, from which the state determination models may infer or determine and assign a state to an entity.

[0220] Extraction Methods from paper records and PDFs may include Optical Character Recognition (OCR) based methods. This method may be used for converting scanned images of text from paper documents or PDFs into machine-readable text. This process digitizes historical and / or ongoing records in a precast concrete factory. Implementing OCR based methods into the systems herein may involve scanning paper records into PDFs or image formats using high-resolution scanners. OCR methods then may be used by the systems herein to convert scanned images or PDFs into editable text formats. The models herein may include features that allow for manual review and correction of any OCR conversion.

[0221] Document Parsing based methods may be used. Template-based parsing may be used for standardized documents that follow a consistent structure. This approach is effective for extracting specific data fields from regularly formatted forms. In one embodiment, this method may include designing and hard coding templates into the system for different types of standardized documents (e.g., production logs, inventory sheets), alongside the definition of exact location and format of each data field within the document template. The template is then used to parse and extract data fields from each document. For instance, production logs can be parsed to extract data such as element ID, production date, batch number, and materials used.

[0222] Additionally or alternatively, the following parsing methods may be used by the methods and / or systems herein. Machine Learning-based Parsing involves training models to recognize and extract data from varied and unstructured documents. Tools like Natural Language Processing (NLP) libraries, deep learning frameworks, and specific ML-based tools may be included in the methods herein to extract data from records herein. The method may include collecting a diverse set of documents as training data and / or labelling these documents to highlight data fields of interest. Machine learning models are then trained to recognize and extract the annotated fields. Once trained, the model is deployed to parse new documents and extract data fields. An example application is the extraction of data from delivery receipts, capturing information such as delivery date, recipient name, truck ID, and list of delivered elements from varied formats and handwritten notes.

[0223] During the Casting Stage, production logs are parsed using template-based parsing to extract data such as element ID, production date, batch number, and materials used. This data is stored in the production management system for real-time monitoring. In the Curing Stage, curing reports are processed using OCR followed by template-based parsing to extract data such as element ID, curing start and end times, and environmental conditions. This information is analyzed to optimize the curing process and predict defects. At the Storage Stage, inventory sheets are parsed using template-based parsing to extract data such as element ID, storage location, and date of storage. This updates the inventory management system for real-time tracking of stored elements. During the Picking and Loading Stage, loading logs are processed using OCR followed by template-based parsing to extract data such as element ID, loading date and time, truck ID, and destination. This data is used to optimize truck loading and manage logistics efficiently. In the Transportation and Delivery Stage, delivery receipts are processed using machine learning-based parsing to extract data such as delivery date, recipient name, truck ID, and delivered elements. This information updates delivery status and optimized route planning for future deliveries. By implementing these extraction methods, the precast concrete factory can digitize and integrate paper records and PDFs into its digital systems, enabling comprehensive tracking, analytics, and optimization across all stages of production and logistics.

[0224] Additionally or alternatively, methods and / or procedures or techniques which may be used by the systems herein to extract data from any relevant record may include any of the following as well as any other such methods as may be clear to one skilled in the art. Additionally or alternatively, the following data extraction methods may be used as part of the execution or implementation of any method described in this disclosure (e.g. this may include value-chain methods such as spatio-temporal sequence generation or dynamical adjustment, core toolkit methods such as location and determination, enabling toolkit methods such as state determination, non-compliance determination, simulations based methods including simulations reality matching and 4D-SBIM reality matching based methods or predictions and / or any other such method described herein): Pattern Matching Algorithms; Optical Character Recognition (OCR); Natural Language Processing (NLP); Table Extraction Algorithms; Semantic Extraction Algorithms; Metadata Parsing Algorithms; Convolutional Neural Networks (CNNs) for entity determination from videos or imaging; Feature-based Detection Algorithms; Segmentation Algorithms; Frame Sampling Algorithms for extracting data from video or imaging feeds; Object or Entity Tracking Algorithms; Motion Detection Algorithms; Spatio-Temporal Analysis Algorithms to extract data from video feeds forexample (which may be generated from cameras, hyperspectral imaging devices, LIDAR based devices and / or other such imaging devices), including the use of Recurrent Neural Networks, LSTMs and / or 3D-Convolutional Neural Networks; Machine Learning methods including supervised and unsupervised and reinforcement learning; image processing methods; text processing methods; natural language processing based methods such as transformer based methods e.g. GPTs or LLMs; generative based methods; multimodal machine learning based methods including multimodal fusion techniques to extract and / or match and / or fuse data from varying data sources or modalities such as early, late or hybrid fusion based methods; cross- modal retrieval methods including image-to-text retrieval and / or text-to-video retrieval for example.

[0225] Manual data entry may be used for the models and systems herein to ingested data. This may include the use and / or generation of data entry forms, such as custom web forms, which may be used for users to enter data into the system herein. Mobile applications may also be used to facilitate data entry in the field or on the factory floor. Additionally, spreadsheets may be employed for manual data entry, with data subsequently extracted using scripts or APIs.

[0226] Data extraction from communications devices, for example connected devices with communications capabilities, may be achieved through the use of communications protocols. For example MQTT, may be used for real-time data extraction. Devices may be configured to transmit data directly to servers using HTTP / HTTPS protocols. Email parsing may be used to automate the extraction of specific data points from email bodies and attachments. This method ensures that relevant information contained in emails is efficiently captured and integrated into the central system. In some embodiments, data may be extracted through database dumps. Flat files, such as CSV or XML files, may be extracted from other systems and imported into the systems described herein, ensuring that historical data is preserved and accessible for analysis and integration. Models List of Models, Techniques and Algorithms

[0227] Some Models Types, Techniques, and Algorithms used herein by the disclosed system and / or set of methods may include the following techniques. Physical / chemical models; Tree-based methods e.g. Decision trees, Bagging trees, Random forests, Gradient boosted trees; Bayesian probability theory; Artificial Neural Networks e.g., Convolutional networks, Recurrent neural networks, Transformers, Generative Adversarial Networks, Diffusion Systems; Clustering Algorithms e.g. K-means clustering, Hierarchical clustering, Densitybased spatial clustering, Spectral clustering, Affinity propagation, Gaussian mixture models; Embedding / Dimensionality reduction methods e.g. Principal component analysis (PCA), Independent component analysis (ICA), Multi-dimensional compression methods; Bayesian networks; Causal graphs; Ensemble Models; Generative Models; Parametric Design Models; Evolutionary and / or Genetic Algorithms; Multi-Modal Models; LLM Models; NLP Techniques; Machine Vision Techniques; Deep Learning and ML Techniques; Hyperparameter Optimization Techniques may be used alone or in combination. Any other model, technique and / or algorithms as clear to one skilled in the art may be used to implement the methods and systems disclosed herein. Models Training

[0228] The model training techniques, datasets and all other content described herein may be used to train any other model associated with any other software implemented method described in this disclosure.

[0229] In one embodiment, the methods herein may be implemented using one or a plurality of Artificial Intelligence (AI) Models. This may be any kind of Model named herein and / or any model one skilled in the art may understand to be an AI Model. In such a case, the methods herein may comprise training the AI Model to generate desired outputs. Training may include two parts: preparing a training dataset for ingestion; and the implementation of one or a plurality of training techniques, methods or procedures, which in some embodiments may comprise a training utility function. Choice of the latter may include any technique described herein and / or any training technique recognized as such by one skilled in the art. The description of these methods herein is non-exhaustive, and further embodiments obvious to one skilled in the art may apply.

[0230] The training dataset may include historical data associated with the industrial construction operations at factories, site and anywhere in between (including delivery). The training dataset may also include simulation data, generated to replicate construction operations at any part of the value chain. Any data listed herein may include associated errors and uncertainties. In some embodiments, the training dataset may include historical plan data as well as associated historical events execution data, wherein both of these may include CO Data; CA Data; CC Data; Interactions Data; Association Data; Demand Data. Historical plan data may include any data indicative of how the events including a logistics instance were planned, at any stage of the instance’s unfolding and at any level of granularity. Historical events execution data may comprise any data indicative of how the events including a constructioninstance were really executed, at any stage of the instance’s unfolding, and at any level of granularity.

[0231] Additionally or alternatively, the training procedure may involve one or a plurality of the following steps in any sequence: the model ingests unlabeled historical plan data and / or historical events execution data; the model ingests labelled historical plan data and / or associated historical events execution data; the model pre-processes unlabeled historical plan data and / or historical events data. In some embodiments, pre-processing may include extracting the data from associated data sources, linking the data, and generating a 4D spatio-temporal representation indicative of a 4D plan associated with the construction instance; the model is trained on the data to generate a prediction indicative of the most probable events likely to occur succeeding any construction instance; the model ingests pairs of spatio-temporal; the model ingests labelled data comprising prompt and desired output pairs, wherein the desired output may take the form of a spatial representation (e.g. floor plan or layout document), temporal representation (e.g. schedule), or spatio-temporal representation of a construction instance; reinforcement learning from human feedback; the model may be trained using human feedback during the training phase; the model may learn and continuously improve whilst in execution through human feedback in real-time, or retrospectively from operatives associated with a construction instance the model is used on; the model training may have a cost or utility function associated with training; the model training may aim to minimize or otherwise optimize the utility or cost function; the model training may involve an iterative loop, the iterative loop comprising the model outputting a set of outputs based on training inputs described herein, the outputs being evaluated against a cost or utility function, and the loop starting again. The outputs herein may include predictions of most probable next spatio- temporal events in any format (4D render, schedule, linked schedule, sequence of events, digital twin, set of instructions or other); generation of an answer to a prompt - the inputs and / or outputs may be multi modal and may comprise textual data, image data, video data, 3D simulation data (e.g. BIM), 4D simulation data, audio data (e.g., speech) and any other data modality. This may be true of any model and / or method and / or system described herein; the generation of an optimal spatio-temporal event sequence for reaching a state Pf from initial state Pi; the predictions and / or generation of the states of any entity (CO, CA, CC, Sensor) at any point in the logistics instance or construction instance; the models may be trained to generate outputs at any level of granularity. In some embodiments, this may be taught through reinforcement learning through human feedback; the models may be trained using one or a plurality or combination of the following methods: supervised, unsupervised, semi-supervised,reinforcement, transfer, self-supervised and active learning methods as well as any other learning method as clear to one skilled in the art; additionally or alternatively, part of the training procedure involves using methods such as generative AI methods, multi-modal methods, simulations, procedural methods and / or other, to output a 4D Spatio-Temporal representation of the set of events from schedules and spatial data such as BIM Models

[0232] In one embodiment, distinct model modes may be trained based on different specializations or different objectives. The training procedures may be altered to generate these specialized or focus models. Non exhaustive examples of alterations may comprise limiting the input training dataset, altering the utility or cost function, and / or using human feedback reinforcement learning, as well as altering any other parameter involved with the training mechanisms. In some embodiments, a pre-trained model may undergo a transfer learning based method, wherein this model may be retrained for another use case. For example, a generalized model trained on data from the full value chain and any use case undergo a transfer learning procedure wherein it is re-trained on a smaller dataset including only a particular part of the value chain, or comprising data associated with interactions between one class of CAs and one class of COs (e.g. precast ovens and precast concrete blocks), such that the model becomes specialized for that use case.

[0233] Models may be trained to generate outputs by value-chain stage. In some embodiments, this comprises limiting the input dataset to include data only or primarily pertaining to this stage (e.g. Manufacturing). Additionally or alternatively, this may comprise altering the utility or cost function used in training such that only or mostly outputs pertaining to the stage of interest are rewarded by the function. Additionally or alternatively, this may include using reinforcement learning through human feedback to train the model to generate outputs pertaining to one stage of the value chain. Additionally or alternatively, models may be specialized to any combination of value-chain stages, at any granularity e.g. a model may be trained to consider Manufacturing, Storage at the Factory, and Collection and Loading, and generate plans associated with evolving the construction instance from a state wherein no units have been manufactured, to a state wherein for every respective order, units have been loaded and are ready for delivery. This will be a continuous process, as increasing demand from sites may come in, which means the model is likely to adjust the plan every time the demand changes (this may be the case for any model herein) - in this embodiment, the model may be considered a Factory Focused Model; Additionally or alternatively, a model may be trained to consider Storage at the Factory, and Storage on Site - this this embodiment, the model may be a Storage Focused Model; Additionally or alternatively, a model may be trained to consider Storage atthe Factory and Installation; Additionally or alternatively, a model may be trained to consider a subset of Storage at Factory and / or a subset of the events that happen at the storage part of the value chain. For example, a model may be trained to generate a plan for storing a subset of all elements for a given order; additionally or alternatively, the model may be trained to generate a stacking sequence rather than a full plan; additionally or alternatively, the model may be trained to generate plans that specifically evolve the routes of individual assets, or of assets in aggregate.

[0234] Models may be trained to generate outputs by type of interactions and / or events through any of the methods herein. For example, this may include specializing to generating plans involving a particular type of construction asset e.g., CNC cutting machines. The model may be trained on historical data pertaining to CNC cutting machine plans and executions to output an optimized plan for the usage of CNC cutting machines at the prefabrication factory. This may include generating a sequence of cut events for a variety of COs, for every CNC cutting machine at the factory. Additionally or alternatively, the model may be trained to output an optimized plan for usage of precast ovens, forklifts, crawler cranes, gantry cranes and / or any other construction asset. Additionally or alternatively, this may include specializing to generating plans involving a particular type of construction object e.g. prefabricated chimney units. The model may be trained on data associated with prefabricated chimney units (e.g. sensor data from instrumented chimney units) to generate an optimized plan for the fulfilment of prefabricated chimney unit orders. Additionally or alternatively, the model may be trained to output plans comprising events associated with any other type of CO herein. Additionally or alternatively, this may comprise specializing to generating plans for events occurring in a particular setting and / or instantiated context. This may include, for example, events happening in a variety of general settings for example natural gas excavation sites; mining and natural resource excavation sites; packaging warehouses; delivery warehouses; chemical factories; rubber and plastics production plants; electronics manufacturing production plants; automotive parts manufacturing plants and or others. The models may be trained or retrained on data from such settings This may also include, for example, events occurring in more granular settings or instantiated context such as events occurring in storage yards; events associated with a particular manufacturing assembly line.

[0235] By ingesting pairs of historical plan data and historical events execution data, the model is able to construct an internal representation of the relationship between plan and execution in logistics settings. For example, the models herein may determine statistical correlations in the training data between storing units that are soon to be delivered in locationsthat are not easily accessible (e.g., that are far from the loading area or that are underneath other units), and delays in expected load deliveries. This information may then be internally embedded in the models herein by altering the weightings of its internal parameters and / or hyperparameters to account for this. In turn, when generating plans, the model will therefore learn to select storage locations that are more optimal e.g., the models may be inclined to store units that need to be delivered sooner, in more accessible locations on the factory floor or factory yard. This also enables the models to dynamically adjust their plans to real-time anomalies and deviations and regenerate plans based on such perturbations.

[0236] Data associated to CO2 emissions for every interaction, COs and CAs, including eCO2 contained within a given CO, CO2 emitted as part of a CO’s manufacturing process, and operational CO2 emitted by CA’s expending energy upon CO’s may all be ingested in training. Ingesting data associated with carbon in training may enable the models herein to predict expected CO2 emissions for types of interactions and processes on site and / or based on plans.

[0237] Any data collected on any logistics instance or construction instance through the use of the core toolkit, enabling toolkit, value-chain toolkit, and / or any data gathering or outputting method described herein may be added to the training dataset for continuous model training and improvement. Training Dataset - Historical Plan Data

[0238] Historical plan data may include any data indicative of how the events forming a logistics instance were planned, at any stage of the instance’s unfolding and at any level of granularity. This may include data indicative of the set of events as represented in 4D Space and Time, for example, through a digital twin format, or spatio-temporal rendering format. Additionally or alternatively, this may include data from schedules representative of initial timelines, event sequences, schedules and other temporal data as well as spatial data as they were planned including any one of 3D BIM Models, floorplans, spatial drawings, photographs, and / or other records of spatial data; data from factory layouts illustrative of storage yard spatial dimensions, routes, and other spatial data; demand data e.g. extracted from an initial purchase order form representative of a given order of COs with or without an associated deadline by a contractor or other stakeholder, and other data associated with the planning for the execution of a construction instance; the planned temperature in the factory (if regulated); the planned usage data associated with the use of a precast oven, including oven temperature settings, heating settings, ventilation settings, usage start and end time, and other; expected factory throughput metrics (e.g. as implied by the plan or schedule and computed by the modelsherein); The sequence of all CA-CO interactions; The state and state changes of all COs; The state and state changes of all CAs; The continuous location of every CO and CA; The sequence of routes and paths taken by all COs and CAs; The procurement and / or disposal of any CA; The creation and / or disposal or rejection of any CO; The demand for COs for a given project; Meteorological Data; Real-Time CO2 emission Data; expected productivity metrics; Spatial representation of CA; spatial representation of CO; spatial contextual conditions. The former two encode the spatial information associated with the 3D shape of CAs and COs, which may be represented in 3D. The latter data type encodes spatial information associated with the context the COs and CAs operate within.

[0239] In some embodiments, this may be a digital spatial representation of the factory or part of the factory (e.g., storage yard); the site or part of the site (e.g., floor X); or the delivery route from factory to site and any other such associated data, data types, data cases, parameters and / or metrics. In some embodiments, some or all of these may be generated, or extracted based on an input schedule or spatio-temporal sequence using generative methods, scraping methods, or other. By using historical plan data, the models are able to gain an understanding of the elements that comprise schedules, as well as how processes relate to one another, and relate to COs and CAs in time and in space. This also sets the baseline for the models to understand how planned schedules differ from actual events. Historical Events Execution Data

[0240] Historical events execution data may include any data indicative of how the events including a construction instance were really executed, at any stage of the instance’s unfolding, and at any level of granularity. This may include data associated with the real-time execution of the events planned out in a schedule, including for example, the real time and location a given interaction has started, occurred, and ended; the real time a unit was installed; the real time a load was delivered and reached the site; the true dimensions of the factory yard; the real usage data (e.g. usage rate) of a given precast oven; 4D spatio-temporal representation of real execution of events; Real-time data from wave-based sensors and / or other types of sensors; real-time data, insights, or outputs from any method herein. Without loss of generality, this may be any data associated with events as they occurred in reality in a given logistics instance.

[0241] For any given spatio-temporal construction instance, this may also include Real Spatio-Temporal Events Data of preceding and subsequent data. This enables the models to build an internal representation of the causal relationships between the logistical coordination of events in the past and the future, enabling it to learn about bottlenecks and their source,temporal dependencies, and any other temporo-spatial relationships. This empowers the models to identify how past events will influence the spatio-temporal schedule it may be generating, as well as predict the impact of a spatio-temporal schedule on the future. Historical events execution data may also include attribute data associated with a given instance. This may include data indicative of any attribute not directly indicative of spatio-temporal progress between Pi and Pf. This may represent attributes of entities such as CAs and COs, CC entities, and sensor entities.

[0242] Attributes may include the following, as well as other attributes clear to one skilled in the art including: Maximum load and / or weight carrying capacity (e.g., what weight can be carried) ; maximum spatial capacity (e.g., what volume can be carried on the back of a trailer); Energy data including, but not limited to, energy type data (e.g., electricity, gasoline, fuel etc.…), Energy usage data (e.g., this CA uses X Joules of electricity per second, or this CA uses Y gallons of fuel per hour); Routing and path data - data associated with the type of routes the CA may be able to use (e.g., forklifts travels along the ground where paths are laid out; tower cranes are static but may route COs vertically along their hook, and in arcs); Speed data - data associated with the speed at which CAs are able to move along these paths (e.g., maximum crane speed along arc, maximum speed of shunter with and without trailer attached); Any other data specific to particular construction assets which may not be described herein but may be clear to one skilled in the art. In one embodiment, this may be precast oven (e.g., plant and machinery used for heat curing of precast concrete units) attribute data (e.g., data associated with any attribute of precast ovens such as oven temperature data) that may include data indicative of the allowable oven temperature range for a given oven type and / or any other data type associated with oven temperature attributes; oven settings data that may include data indicative of the allowable settings the oven may be used in (e.g. settings relating to the intensity of the air convection within the oven; oven humidity data; oven ventilation data, and / or the like. Training Dataset - Simulations

[0243] In some embodiments, the training datasets described above may comprise simulated data as opposed to real-time historical data. 3D simulations of factories, sites and others evolving in time, alongside simulated CO entities with associated CO attributes and / or identifying data and / or spatio-temporal data, simulated CA data, simulated CC data, in some instances simulated sensor data, association data, state data, and / or demand data. The simulation may include physico-chemical parameters designed to simulate physics andchemistry of real world events. This may allow the simulations for example to accurately simulate curing times for units, machine failures or malfunctions, impacts which may cause CO damage. Simulations may be used to engineer synthetic data associated with many different scenarios, including scenarios meant to teach the model the impact of certain bottlenecks (e.g. sub-optimal crane placement), common delay sources to avoid, storage configurations (e.g. stacking order and placement) which may be optimal for certain use cases and any other such learnings. In some embodiments, these simulations are created using generative methods, by generative models trained to simulate industrial and / or construction environments. In some embodiments, these simulations may be generated in BIM format.

[0244] Additionally or alternatively, a set of historical plan and events execution data pairs may be simulated or generated and included as part of the training dataset. In some embodiments, this may be done using generative methods. In some embodiments these generative methods may be multimodal methods, or transformer based methods. Additionally or alternatively, this may be done using finite element based methods and analysis. Additionally or alternatively, this may be done using geometrical based rendering based methods. Additionally or alternatively, this may be done using physical simulation based methods. Model Types

[0245] In some embodiments, the models herein may include prediction models, selection or recommendation models, adjustment and / or optimization models, and generation models. This include the spatio-temporal generation models herein. Additionally or alternatively, the methods herein may be used in different modes, including predictive mode, selection mode, adjustment mode, and generation mode. For example, the methods in the value chain toolkit may be used to generate spatio-temporal sequences. In other modes or configurations, they may also be used to predicted a likely expected spatio-temporal sequence, select an optimal spatio- temporal sequence based on objective criteria, from a predetermined set of sequences and / or select a starting state scenario which is most likely to produce an optimal spatio-temporal sequence (e.g. starting state scenario may include assigning 5 forklifts to one storage yard and 3 forklifts to another storage yard, for picking up stored units), adjust or optimize an existing spatio-temporal sequence based on objective parameters and constraints wherein the adjustment may in some embodiments be generated on the basis of real time data including real time state data, CO data, CA data, interaction data, association data and / or any other data or data type herein (e.g. adjusting a pick list such that the new pick list is most likely to be executed faster).

[0246] Prediction models may be used to predict or estimate any future quantity associated with any data gathered herein. This may include, for example, predicting the likely future spatio-temporal sequence of an entity (e.g. future path), based on a past spatio-temporal sequence. In some embodiments, this may include predictions based on location algorithm data, interaction algorithm data, state determination data, route data, and / or spatio-temporal sequence data as described or generated in the value-chain toolkit (plans, paths, schedules, routes etc). Prediction models may also be used for scenario analysis. For example, a scenario may be digitally simulated e.g. an order of 300 precast elements need to be sent from factory X to site Y, and the prediction models herein may predict the expected timelines for the order fulfilment. Examples of predictions which may be executed by the prediction models herein may include the following: prediction of location based on current location, state and elapsed time; prediction of estimated arrival time for an entity travelling on a predetermined path given speed data, and target location and path data; prediction of likely delays, based on state data for entities associated with the process likely to be delayed; prediction of likely bottlenecks, based on detected overuse of plant and machinery for example; prediction of expected state evolution for an entity from present time to future, based on the current and historical state of other entities, current and historical set of interactions and position data. Selection models may be used to select an optimal option or scenario based on a predefined list of options or scenarios and objectives. This may include for example, selecting the best crane path for a particular lift based on possible paths.

[0247] In some embodiments, adjustment models may be used continuously and in real- time, following an initial generation for a spatio-temporal sequence. This may comprise dynamically iterative features. Spatio-temporal sequences may be updated based on real-time events that occur and / or real-time changes. For example, the path a forklift should take may be adjusted in real-time based on an obstruction which falls onto the expected route. Additionally or alternatively, a planned delivery may be postponed due to harsh weather conditions, and / or similarly for a tower crane lift. Adjustments models may include any one or combination of the following methods or features: (i) anomaly detection - has an anomaly been detected, wherein an anomaly may be defined as a spatio-temporal event which was not expected to occur according to a predefined sequence (e.g. delay, harsh weather conditions not previously known. The output may be a Boolean yes / no - indicating whether an anomaly has occurred, as well as anomaly data, data showing the anomaly (e.g. showing the deviation from the expected spatio-temporal sequence); (ii) perturbation impact determination - This may be defined as the impact the perturbation will have on the spatio-temporal sequence (e.g. how is the perturbationreflected in the sequence, including how knock-on and dependency effects may affect the sequence e.g. schedule); (iii) dynamical analytics - may output analytics as described in the simulations section as well as inferred anomaly cause in human readable format; (iv) dynamical recommendation / iteration / regeneration - this may include an update to the spatio-temporal sequence. This may include an update to one part of the spatio-temporal sequence, such as a change to an immediate sequence, or a completely re-generated spatio-temporal sequence including knock-on effects. Additionally or alternatively, adjustment models may be applicable for adjusting the states of entities in real-time.

[0248] Generation models may generate spatio-temporal sequences, plans, schedules, routes, lists of instructions, tables of interaction sequences and / or any other data indicative of spatio-temporal sequences. Any model type described herein may be trained using the same or similar training procedures and datasets as described above herein, in whole or in part. Model Features AI-Generated Handover Report

[0249] A feature of the models described herein may include generating a handover report using generative methods. The methods herein including the core toolkit, enabling toolkit and / or value chain toolkit methods and any other method herein are in part designed for tracking real-time logistics operations. In construction environments, when the structure to be built has been completed, handover denotes the process by which the builder / contractor returns the asset to the developer / owner and denotes the shift from the construction phase to the operational phase of the structure’s lifecycle. This process includes the documentation of a handover report, detailing the full details of construction operations including compliance information. The models herein may be used in conjunction with generative methods to generate handover report documentation in whole or in part. This may take as input the real- time events execution data tracked by the models herein and output the handover report documentation. Additionally or alternatively, data from any data source herein may be fed and ingested by any model to output handover report documentation in whole or in part, including records information such as delivery tickets and / or prefabricated elements compliance records.

[0250] Examples of documentation that the systems and / or models herein may generate includes any documentation associated with the following: project scope description; project as-built timelines; project key milestones associated with dates these milestones were reached; project objectives; inspections reports (showing work has been completed according to specification; permits and approvals; certificates of completion); As built-drawings e.g.detailed drawings and plans showing completed structure’s layout and construction details; specifications for all construction resources; operations and maintenance manuals; warranty documentations outlining types of warranties and / or warranty periods; testing results and certifications such as MEP testing certificates; certification of compliance; construction resource list of all resources installed or otherwise integrated in the project / in the structure; serial numbers and specifications for such construction resources; health and safety files including safety audits and / or incident reports; environmental compliance documentation including sustainability certifications (e.g. EPD compliance), and environmental impact assessment reports; legal documentation. The models and / or systems herein may integrate any one or any combination of these into a complete handover document. The models described herein may be trained on documentation and records data to learn how to generate such records. Additionally or alternatively, the models herein may ingest any record herein and / or any other type of record associated with a logistics instance of interest, and scrape data or information out of these documents, including through AI-based methods. Information may include information associated with the state of any entity considered in the instance. The features described herein may also be used in other instantiated contexts and / or logistics instances or settings, such as any other industrial environment, manufacturing plant, batching plant, storage warehouse, jobsite and / or other such logistical environments.

[0251] The features and / or methods herein may be features of any model or method described herein including the models and / or methods described in the value chain toolkit, enabling toolkit, and / or core toolkit. Additionally or alternatively, the methods herein may include generation of any logistics documentation in whole or in part, such that they may be generated on the basis of any data collected from any data source herein, including real-time sensor data. Automated Procurement of Entities

[0252] In some embodiments, the models herein may comprise an automated procurement method as a feature. Additionally or alternatively, the methods herein may include a procurement model which acts as a procurement control system. The procurement methods or features herein are able to output procurement or order requests and integrate into external software and / or procurement tools to execute orders. Examples of automated procurement may include the following: based on real-time state data associated with the state of a prefabrication factory (including how many units are being created and / or are expected to be created based on demand data), as well as predictions based on prediction models herein (e.g. outputpredictions using machine learning models trained on historical or simulated data associated with spatio-temporal sequences as described), the models herein may determine that it is likely that precast ovens may become a bottleneck and that it may be useful to order another precast oven to speed up operations. The model may automatically order an oven based on integration with an oven procurement platform. In some embodiments, a budget may be allocated to the model herein for orders. Additionally or alternatively, the model herein may request approval by a user before carrying out the order. Additionally or alternatively, the model may order or rent additional delivery trucks based on an unexpected surge of units to be delivered. Additionally or alternatively, the model may ingest order data for prefabricated units in varying quantities and procure the required raw materials for fulfilling that order. In some embodiments, the model may search for raw materials providers online and find the cheapest, but highest quality option. Path Integral Formalism

[0253] The models described herein may use path integral formalism and associated techniques when generating spatio-temporal sequences. This may be extended further to consideration of interactions in a Feynman-Diagram sense. In some embodiments, the methods herein may involve casting a given logistical system in a Lagrangian form or associated form and solving this Lagrangian using function optimization methods. Location and Time Tracking of Precast Concrete Elements

[0254] By way of example, precast elements may be equipped with a beacon that emits Received Signal Strength Indicator (RSSI) signals, which are picked up by local gateways to determine each element's location and time-based movement. Bayesian probability methods may be employed to enhance location accuracy, generate comprehensive reports on the location and time tracking of the elements, and generate predictions and insights associated with the behavior of the elements.

[0255] In such an embodiment, each precast concrete element on the factory floor may equipped with a beacon that continuously emits an RSSI signal. The strength of the signal decreases with distance, allowing an estimate of the distance of each beacon from each gateway to be determined. Local gateways may be strategically placed to pick up RSSI signals from beacons. RSSI data from all gateways is aggregated, and the system uses AI algorithms to determine the precise location and time-stamped movements of each precast element. Data Generative Models utilize the location and time data to simulate and predict movementpatterns, optimize placement, and generate detailed reports on the location and time tracking of elements.

[0256] Bayesian Probability Methods are used to enhance the accuracy of the location estimation. By considering prior knowledge of the factory layout and the typical noise in RSSI signals, the system updates its belief about the most probable location of each beacon over time. The system initializes with a prior distribution representing the initial belief about the locations and expected sitting times of all precast elements based on the factory layout and production schedule. As RSSI signals are received, the system calculates the likelihood of each possible location and corresponding idle time given the new data using likelihood functions. This function models the probability of receiving the observed RSSI values at various distances from the gateways over time. The system updates the prior distribution with the likelihood function to produce a posterior distribution, representing the updated belief about the locations and times. This process repeats iteratively as new RSSI data comes in, continually and dynamically refining the location and time estimates. The Bayesian framework allows for handling uncertainties and incorporating new information dynamically.

[0257] Machine learning algorithms process the location data to correct any inaccuracies due to signal interference and to predict future movements of the precast elements. The time component of the data is used to track how long each element stays at various locations. Historical location and time data are analyzed to identify patterns and optimize the workflow. This analysis helps in understanding the efficiency of each stage in the production process and may be done using AI-based methods for pattern recognition for example. Generative models may be used to generate reports detailing or summarizing current and historical locations and dwell times of each precast element. Interaction Tracking of Construction Resources Using Ensemble Methods

[0258] In some embodiments, a method for tracking interactions between construction resources in a factory setting using ensemble methods, specifically tree-based methods is provided. A precast concrete element may be equipped with a beacon that emits an RSSI signal. Local gateways pick up these signals to determine the locations and how this element interacts with other resources within the factory setting. Ensemble methods, including decision trees and random forests, are employed to analyze the interaction data and generate comprehensive reports.

[0259] In this embodiment, ensemble methods, particularly tree-based methods like decision trees, random forests, and gradient boosting machines, are used to process and analyzethe interaction data. The system provides real-time tracking of interactions between precast elements, such as proximity events, co-location of machinery and materials, and tool usage patterns as well as historical data analysis to identify recurring interaction patterns, such as frequent co-locations of certain elements or common usage sequences. Individual decision trees are used to model and understand simple interaction rules based on the RSSI data. Each tree splits the data based on signal strength thresholds to predict interactions. A collection of decision trees, known as a random forest, is used to improve the accuracy and robustness of the interaction predictions. By averaging the results of multiple trees, the random forest reduces the risk of overfitting and enhances generalization. These models are used to further refine the interaction analysis by sequentially building trees that correct the errors of previous trees. This approach provides highly accurate interaction tracking and prediction. Genetic Algorithms

[0260] In some embodiments, genetic algorithms may be used for generating spatio- temporal sequences and / or or paths. Additionally or alternatively, wherein the method may include any one of the following steps: (i) internally representing paths e.g. as graph networks; (ii) initializing candidate paths, for example based on route constraints (e.g. a crane with a rotating arm and raising or lowering hook, may access paths according to a cylinder (excluding both ends of the cylinder), therefore the genetic algorithm may be used to initialize paths on that cylinder. This may be true for any path initialization procedure, beyond those using genetic algorithms; (iii) defining a fitness function which evaluates each path, for example based on the following variables: time taken to travel through path, length of path, carbon emitted by asset travelling on path, safety of path and / or other such parameters as described elsewhere herein; (iv) selecting a subset of paths from the current generation, based on selection algorithms such as roulette wheel selection, tournament selection or rank-based selection; (v) Combining or executing crossover based methods which combine segments of paths from path pairs to generate new paths. Crossover methods may include single-point crossover, multi- point crossover, order crossover ; (vi) Mutating paths such that random changes may be introduced to each individual path, mutation operators may include swap mutations, insertion mutations, inversion mutations; (vii) replace the current generation with a new generation in whole or in part; (viii) select a termination criteria, for example termination after a fixed number of generations, termination based on a fitness criterion being met, or termination based on the marginal or null improvements over multiple generations.The Logistics Core Toolkit

[0261] The logistics solution hinges on the real-time and historical tracking of construction resources and their associated interactions. The rest of the system may be realized using these fundamental elements, including other data gathered or related to systems described herein and any other information / data and information / data sources and / or entities mentioned within this description such as construction plans and schedules, specifications, machine records and more. the core toolkit includes hardware devices and physical system implementation; 4D- location (time + 3dDlocation) tracking algorithms; and interaction tracking algorithm. The latter two together may be referred to as the Core Toolkit Algorithms. Hardware Devices and Physical System Implementation

[0262] Considerations and embodiments associated with the mechanical and industrial design of the devices including sensor devices herein are provided. Without loss of generality, these considerations, systems and embodiments, in whole or in part, may be applicable to any device, sensor, sensor device, system and / or other part of the disclosure listed herein. Mechanical and Industrial Design Considerations Device Geometry, Size and General Hardware Considerations

[0263] The methods and / or systems herein may be applicable to any other part of the present disclosure including but not limited to construction assets with suspended hooks such as cranes or gantries. In some embodiments, devices (including sensor devices, gateways or beacons) are integrated into existing crane blocks. In this embodiment, any solution may need to ensure the sensor's functionality without hindering the crane's operations.

[0264] Additionally or alternatively, in one embodiment the sensor has a mass of less than 15% of the crane block (to avoid weighing down the crane or adding wind load). Additionally or alternatively, in another embodiment the surface area of the sensor is smaller than that of the crane block (so as not to create any further surface area exposed to wind). Additionally or alternatively, one or more antennas which form part of the sensor is / are directed away from the crane block. Additionally or alternatively, the attachment method that secures the sensor to the crane block is able to withstand accelerations higher than 1 m / s^2. Additionally or alternatively, device housings (including beacons or gateways, or sensor devices) may include one or more magnets that are able to snap-on to the crane block. Additionally or alternatively, in another embodiment the device housing includes four magnets (which may be disc shaped,rectangular). Additionally or alternatively, the magnets are bound to the device enclosure through screws, glue, clamps or the like.

[0265] The design of devices can take various forms, considering their intended attachment to construction resources like crane hooks. This includes cylindrical, polyhedral, cuboidal, spherical, or 2D plates or more generally any 3D volumes. They may also feature concave or convex elements to facilitate better adherence to the host structure. Devices may also include textures and patterns (e.g. Straight Grooves, Parallel lines, Cross-hatch (grid pattern)), Diagonal lines, Knurling, Straight knurling, Diamond knurling, Spiral knurling, Dimple Patterns, Round dimples, Hexagonal dimples, Square dimples, Textured Surfaces, Matte finish, Sandblasted finish, Pebble grain, Raised Patterns, Checkerboard, Raised dots, Raised ribs, Geometric Patterns, Honeycombs, Fish scales, Wave patterns, Perforated Patterns, Circular holes, Slotted holes, Mesh, Tactile Patterns, Micro-Patterns, Microscopic grooves, Micro-dots, Nano-textures, Lattice structures, Drainage channels, Anti-slip ridges). Additionally or alternatively, the sensor devices may be adaptive in nature, with the ability to adapt over time (changing their shape or geometry, as well as mode of operation based on changes in their operational environments). This may be implemented through adaptive materials or metamaterials.

[0266] Additionally or alternatively, shape-molding materials (e.g., foams) may be included which imprint the shape of their host structure. Additionally or alternatively, devices may feature one or more straps for attachment. Additionally or alternatively, devices may have internal or external swappable batteries, which may be rechargeable. Additionally or alternatively, devices may include energy harvesters, such as solar cells to ensure continuous operation. Additionally or alternatively, devices may include motion-based energy harvesters (e.g., piezo-electric or triboelectric elements) which exploit the motion and acceleration of construction assets to which the device is associated to power the device (or charge a battery contained within the device). Such energy harvesters may exploit translational or rotational kinetic energy, vibration, potential energy of a variety of fields (e.g., the electromagnetic field). Additionally or alternatively, devices may employ duty cycling or other ultra-low power techniques to further extend battery life (or enable continuous operations with no charging).

[0267] Additionally or alternatively, devices (including sensor devices, beacons or gateways) may be installed underneath the crane hook and may be integrated with load-cell sensing solutions to measure load. Such devices would further comprise an additional crane hook onto which lifts would be loaded (so sits in the load path of the crane). Additionally or alternatively, devices (including sensor devices, beacons and gateways) may be mounted ontomobile construction resources such as forklifts, cherry pickers and mobile cranes, or other moving platforms on worksites or factories (e.g., hoists). For devices mounted onto vehicles, power may be obtained from the vehicle’s power system (e.g., CAN Bus or the like). Materials

[0268] All or parts of the devices described herein (including all sensor devices, beacons or gateways) may also be made, in whole or in part, of metals (including aluminum, stainless steel, carbon steel, titanium, brass, bronze, copper, magnesium), plastics and polymers (including ABS (acrylonitrile butadiene styrene), polycarbonate, polyethylene, polypropylene, PVC (polyvinyl chloride), PTFE (polytetrafluoroethylene), PEEK (polyether ether ketone), nylon, acrylic, conductive polymers), composites (including fiberglass, carbon fiber, wood, composites), ceramics and glass (including ceramic, glass, optical glass, sapphire, quartz, infrared glass, chalcogenide glass), elastomers and rubbers (including silicone, rubber, elastomers, thermoplastic elastomers (TPE)), resins (including epoxy resin, phenolic resin, silicone molding compounds), metamaterials and smart materials (including metamaterials, shape memory alloys, nitinol, piezoelectric materials, electroactive polymers, smart materials, adaptive materials, superconductors), magnets (including neodymium magnets, ferrite magnets, alnico magnets, samarium cobalt magnets), optical materials (including optical fibers), conductive and electromagnetic materials (including silver, gold, graphene, carbon nanotubes, dielectric materials, mu-metal), foams (including polyurethane foam, polystyrene foam, melamine foam, metal foams), shape-forming materials (including thermoplastic materials, thermoforming plastics, clay, putty, thermosetting plastics), concrete and cementitious materials (including concrete, cement).

[0269] Aspects of the device (e.g., the concave or convex elements of a device, or any strap) may be over molded with elastomers (e.g., rubber or other elastic materials). Potting compounds such as resins may also be used to protect the electronic components (e.g., in the case of devices designed for embedding in concrete). Installation

[0270] Devices (including sensor devices, beacons or gateways) may be installed by mounting them on, directing them at, or embedding them in any construction resource, or placing them in proximity of a construction resource. This may include resources such as construction assets or also directly onto construction elements. Similarly, devices (e.g., gateways or beacons) are physically attached or coupled to construction resources. Theseresources may be construction elements, in which case beacons or gateways may be attached on or inside elements. Installation methods may vary but may include using a strap (rubber or steel) attached to reinforcement cage, a curved device with a grip that fits different rebar configurations or other embedded element for “mounted on” type installations (screwed in, glued on, tied to a protruding bar, magnetically attached, conical extrusions). This includes any installation method described in any section of this document. Attachment Methods

[0271] Any of the devices described herein may employ one or more of the attachment methods described below. The methods and / or systems herein may be applicable to any other part of the present disclosure including but not limited to construction assets and construction objects.

[0272] Attachments to construction resources (CR) may include Magnetic Attachment: In some embodiments, magnets are employed to attach devices (including gateways, beacons or sensor devices) to a crane or gantry’s hook block, a floor lift’s tire well, or any other location on assets made of ferromagnetic (or magnetic) material. The device may be attached to the CR using one or more high-strength magnets. This method allows for easy repositioning and installation while maintaining a strong hold. In one embodiment, devices include magnets that are coated to maximize friction with the construction resource and also protect the magnet from environmental conditions. Such magnets may be made up of one or more of neodymium, ferrite, samarium cobalt, alnico, or composite magnets (or may also be formed of electrically controlled electromagnets). The coatings may be made up of one or more of high-friction rubber, epoxy resin, high-friction polymer, high-friction Teflon, or a dual-layer coating with a corrosion-resistant metal such as nickel or zinc, and an outer layer of high-friction material such as rubber or polyurethane, or other similar materials. Devices may make use of any combination of the aforementioned magnet and coating types. Attachments to construction resources (CR) may include Strapped Attachment. In some embodiments, one or more straps (including heavy-duty straps, rubber or overmolded straps) can be employed to attach devices to CRs. Attachments to construction resources (CR) may include Adhesive Attachment. In some embodiments, high-strength adhesives may be used to affix devices to the CR. Attachments to construction resources (CR) may include Hook and Loop Attachment. In some embodiments, devices use a hook and loop system (such as Velcro) for attachment to the CR. Attachments to construction resources (CR) may include Pocket Attachment. In some embodiments, a special pocket or holder is designed within or on the CR where the device maybe securely placed. It provides a snug fit for the device and reduces the risk of it falling off. Attachments to construction resources (CR) may include Bolted Attachment. In some embodiments, the device is affixed to the CR using bolts (e.g. steel bolts). Attachments to construction resources (CR) may include Welded Attachment. In some embodiments, the device is welded directly onto the CR. Attachments to construction resources (CR) may include Clamp Attachment. This method uses a robust clamp mechanism to attach the sensor to the CR. The faces of the clamp directly touching the CR may be coated with a special material to increase the coefficient of friction between the CR and the clamp.

[0273] With reference to FIG. 17, and example implementation 1700 is illustrated. As shown, a sensor device may be enclosed in a protective, non-metallic casing (may be referred to as the “enclosure”). In some embodiments, this enclosure may be attached to a CR substrate such as the surface of a crane or gantry block, or wheel well of a forklift truck using a dual- method attachment system. The primary attachment method involves the use of strong magnets coated in a rubber material. The magnets are designed to adhere securely to the metallic surface of the crane block, ensuring a firm grip. This magnetic attachment allows for easy repositioning of the sensor if necessary, without compromising the attachment's strength. However, considering the structural failure mechanism of such a connection would be abrupt in nature, such a connection on its own would not meet the health and safety criteria of most construction applications. As such, in this embodiment, a dual connection methodology is adopted, whereby a safety lanyard is used as a secondary attachment method, acting as a failsafe. The lanyard is made from a durable material able to withstand harsh conditions of a construction site and would have a plastic failure mechanism which would allow for advanced notice of any impending structural failure of the attachment. The combination of these methods provides a robust yet flexible attachment system for securing the sensor to most any ferromagnetic construction resource. Hardware System Embodiment 1 Device Description

[0274] In one embodiment, the system may include two types of devices: beacons and gateways. Beacons transmit advertisement packets over a Bluetooth antenna (BLE protocol) in an isotropic, undirected manner at regular intervals. Gateways have BT receivers that at specified intervals scan and process received BT packets, extracting the device identifier (the header in the BT packet) and storing as an attribute the RSSI (received signal strength indicator) of the BT packet received from the beacon. The gateway has a real-time clock so the beacon’sdata is imprinted with a timestamp. The gateway has a GNSS (global navigation satellite system) antenna to obtain GPS coordinates (longitude, latitude), and an orthogonal data-stream records the GPS location of the gateways duly timestamped. Both data-streams are stored in a repository that serve as inputs to the algorithms to be analyzed. In this form, gateways store absolute location information vis-a-vis. GPS; the beacons’ signal strength provides relative location information, relative to a gateway at a given time. In summary, beacons are physically attached on or within construction resources. Beacons emit signals to be received by gateways or other beacons. Gateways then pick up on neighboring beacon signals and beacon sensor measurements. Association

[0275] In one embodiment, construction elements prefabricated in a factory are the construction resource of interest. These may weigh several tons and are hence immobile until lifted by an asset (for example, forklift truck). Beacons may be mounted / installed on, or embedded in an element, such as illustrated in FIG. 17, and hence are associated with that element. Gateways are installed on an asset. If the beacons are within range of the gateways, then the gateway will receive the beacons data BT packets and will store the data in this packet along with the time-stamped GPS coordinates. This association may be enabled by linkage. Dynamic and Static Logistics Devices

[0276] Construction projects are complex dynamic environments, including many continuously moving and evolving resources and processes. This means that logistics devices (e.g., beacons and gateways in this embodiments) associated with construction resources may in general be dynamic (e.g. cranes, forklifts, trucks and shunters move in space) and may need to track other logistics devices / construction resources which may also be dynamic. The inventors have therefore developed novel dynamic localization and interaction tracking techniques to overcome this challenge. The case of a static logistics device / construction resource (e.g., fixed in place), reduces from the dynamic case. Core Toolkit Algorithms

[0277] The core toolkit algorithms are the location tracking algorithm and the interaction tracking algorithms. The problem definition outlines the following three key aspects: (a) statement with context and information around tracking and interactions, (b) based on received inputs, and (c) subject to the required outputs. The primary inputs to the algorithms may be anymeasurement (including RSSI signals) generated by any logistics device (including a beacon), which may include wave-based and non-wave-based devices described herein, as well as any logistics device embodiment described herein. The desired output may be (1) the determination of an interaction alongside relocation information (2) a precise location and timestamp coordinate for a construction resource. Core Toolkit Algorithms Embodiment Algorithms Background

[0278] Based on the signals received by gateways from nearby beacons attached to construction objects, there are three ways to estimate the location of the object, listed here in order of decreasing confidence of the prediction provided: (1) from interactions with a construction asset, (2) from close proximity to a construction asset, and (3) from trilateration.

[0279] With reference to FIG. 18, each of these methods will determine an interaction fingerprint using two independent sources of input: Γ = signal strength fingerprint indicating proximity between the asset and element, and Δ the correlated movement profile of the gateway relative to the beacon. Fundamental to all of these methods is inferring from the raw RSSI signals the following: Ζ = Proximity of Beacons and Gateways, and Θ = Movement of Gateways. Both Ζ and Θ of these operate on a discrete spectrum, which if shown on a 2-axis plot 1800 in FIG.18, summarizes the domains in which each of the proposed methods are valid. Interaction Algorithm

[0280] The problem statement for interaction algorithms addresses the detection / determination and tracking (in space and time) of an interaction between construction resources. Tracking An Interaction Involved An Element In The Yard

[0281] For example the models identify when (in time interval [ ^^1 , ^^2]) an asset ( ^^) has relocated an element ( ^^), from a location (L1 ) to a new location (L2). The input may be raw streaming data from the devices described herein. These may be the (1) received signal strength indicator (RSSI) signals transmitted at prescribed intervals by a beacon and received by a gateway, and (2) the GPS coordinates referencing the location of a gateway at prescribed intervals. The output may be Construction Resources involved in the interaction, Timing of the interaction, and relocation coordinates of the element by the asset caused by the interaction.Algorithm Logic

[0282] Query 1 requires the system to identify when an asset A has relocated an element B. With reference to an example interaction state machine 1900 in FIG.19, the interaction logic seeks an interaction fingerprint using two independent checks: Check 1 - signal strength fingerprint indicating proximity between the asset and element. If Check 1 proves to be true, then Check 2 will determine if these fingerprints are correlated to a movement profile of the asset to the element and together to the destination. On a high level, Check 1 the fingerprint will have the characteristics shown in the illustrations 2000 in FIG. 20. Check 2 will then consider the gateway’s GPS sensor data during the time range of the fingerprints above. If the change in position over this time range fits within a prescribed velocity range, the algorithm then can infer with high confidence that the beacon and gateway are together in this time period and it is highly likely that an interaction in which the construction object is an object of an interaction is being executed by the construction asset. An additional verification step that provides confirmation is that an estimated lift combines with the location estimation logic via another means to verify that the locations prior and post a detected lift are measurably different.

[0283] In some embodiments, the interaction algorithm methods may include proximity estimation methods, which may include a set of methods for determining proximity between two or more entities instrumented with devices, as well as the type of proximity interaction (e.g. is an asset approaching an object, is an asset lifting an object). Additionally or alternatively, the proximity interaction types may be associated with the gateway-beacon relative movement configurations data shown in FIG. 20. In some embodiments, proximity between two or more instrumented entities may be determined using RSSI data over time based on signals between devices instrumented on or in the two or more entities.

[0284] An increase in RSSI as shown in FIG. 20 may be used in the methods herein to determine any of the following interactions or data associated with the following interactions: (i) an entity approaches another entity, or both are approaching each other e.g. in the case where a beacon instrumented on an asset is known to be stationary, this may be used to determine that an asset is moving towards an element; (ii) and asset / gateway is lifting an element. Additionally or alternatively, the models herein may process the signal by computing the derivative of the RSSI signal over time to make this interaction determination e.g. d(RSSI) / dt. If the derivative is positive, d(RSSI) / dt > 0 within a given timeframe, the models herein may determine that entities are approaching each other. Using the methods described in the location algorithms, the models may determine which entity is moving towards which.

[0285] A decrease in RSSI as shown in FIG. 20 may be used in the methods herein to determine any of the following interactions or data associated with the following interactions: (i) an asset / gateway is moving away from a stationary unit / beacon; (ii) An asset is dropping an element. Additionally or alternatively, if d(RSSI) / dt < 0 within a given timeframe, the models herein may determine that entities are moving away from each other. Using the methods described in the location algorithms, the models may determine which entity is moving away from which.

[0286] An increase and subsequent decrease in RSSI as shown in FIG.20 may be used in the methods herein to determine that an asset / gateway may have approached and subsequently moved away from a stationary beacon / element (e.g. gantry crane flying by, above units). This may also be determined by computing d(RSSI) / dt and may be characterized by a sub-timeframe wherein d(RSSI) / dt > 0, followed by another sub-timeframe wherein d(RSSI) / dt < 0 (with one moment in time where d(RSSI) / dt = 0).

[0287] A constant RSSI value over a given timeframe may be used by the models herein to determine that an asset / gateway and / or unit / beacon may be staying at constant distance from each other. Additionally or alternatively, this may be determined on the basis that d(RSSI) / dt = 0 within the timeframe of interest. This may be indicative of a carrying or moving interaction wherein an asset is actively carrying or moving a unit and they are moving together. Any combination of any of the RSSI time-evolving features described herein may be used by the models herein to infer any interaction and / or state data or determine an interaction and / or assign a state to an entity. In some embodiments, features such as concavity and / or convexity of RSSI curves may be used for interaction determination and / or other such inferences. This may be represented as the second derivative of the RSSI with respect to time, or a measure of RSSI equivalent acceleration, which may be indicative of the acceleration of entities. Additionally or alternatively, the first derivative of RSSI with respect to time may be indicative of the velocity of entities.

[0288] Additionally or alternatively, the methods herein may use another measure of signal strength or other metrics associated with transmitted and / or received signals, which may not be RSSI. Example of other metrics may include but are not limited to: SNR (signal to noise ratio); SINR (signal to interference to noise ratio); RSRP (reference signal received power); RSRQ (Reference signal received quality); Error Vector Magnitude; CQI (channel quality indicator). Additionally or alternatively, the RSSI value may be determined in relation to any transmitted and received wave or other signal transferred between two or more devices. Additionally or alternatively, such waves may include mechanical and / or electromagneticwaves. Additionally or alternatively, mechanical waves may include ultrasonic waves, electromechanical waves, acoustic waves (e.g. sound), vibrational waves and / or any other such waves. Additionally or alternatively, electromagnetic waves may include microwaves, radio waves (RF), infrared waves, visible waves (visible light), ultraviolet waves, x-ray waves, gamma waves, and / or any wave type associated with any frequency in between. Additionally or alternatively, this may include communications protocols which including but not limited to: LoRA (long range); BLE (Bluetooth low energy); BT (Bluetooth); Wi-Fi; cellular protocols such as 4G, LTE, 5G; RFID; satellite communications e.g. for positioning; NFC (near field communication). Additionally or alternatively, the devices described herein or elsewhere herein in any section of the present disclosure may be configured to communicate using any of the protocols listed herein as well as any other communication protocols. Additionally or alternatively, the waves may be transmitted isotropically from a device source (e.g., antenna in a device). Additionally or alternatively, the devices herein may include directionality in their transmitted waves. All embodiments and configurations described herein may be applicable to any distributed device system or method which uses such distributed devices described herein, including for state determination (e.g. state may be determined using signals received from visible light for example using LIDAR based methods).

[0289] In some embodiments, interaction algorithm methods may include entity movement determination methods, which may include a set of methods for determining whether an entity for example an asset or construction asset, may be in motion, and if so, determining more details or data associated with the motion (e.g. speed, acceleration etc.). Additionally or alternatively, this may include the use of satellite based positioning data gathered from a gateway. Additionally or alternatively, wherein the satellite based positioning data is associated with a gateway instrumented on an asset. Additionally or alternatively this interaction algorithm methods may include determining the velocity of a entity from its associated location data, by taking the derivative of location with respect to time. A device may generate data indicative of its position moving along a path P, determining location coordinates c(t) at discrete time intervals t. From these time varying coordinates, the relative distance travelled between successively recorded time intervals, the gateway / asset speed of movement may be determined as v(t) = (Δc / Δt). Additionally or alternatively the speed or velocity may be used to identify the asset’s movement state. Additionally or alternatively, states associated with movers (i.e. entities capable of moving themselves and / or other objects e.g. forklift, truck, crane) may include ‘idle’ and / or ‘in-transit’. Additionally or alternatively, a threshold speed Vmay be assigned such that the system determines an entity (through an associated device such as a gateway) to be ‘idle’ if v(t) < V, and ‘in transit’ if v(t) > V.

[0290] In some embodiments, interaction determination include interaction inference methods based on combining data and / or information and / or insights generated by both RSSI signals and / or satellite based positioning data together. In one embodiment, such a combined interaction inference logic and / or method may include any one or plurality of the following steps (for the instantiated embodiment of a crane lift):

[0291] (A) From move rate, ^^ (e.g. velocity) determine entity or asset state, ^^ (e.g. using methods described above). This may comprise any of the following sub-steps:

[0292] (A.i) determine ^^(t) = [c(t ) - c(t)] / [t - t] for all data times;

[0293] (A.ii) determine distance between locations (i,j) pair (start location and end location) as c - c;

[0294] (A.iii) if ^^(t) > 0, then the entity associated with the device / gateway is mapped to the ‘in transit’ or ‘moving’ state. Otherwise, it is mapped to the ‘idle’ state.

[0295] (B) Determine ^^, the time interval of paired move events that bracket a lift (e.g. the discrete time interval which defines an event or interaction between entities or devices, in this case two entities, a unit-crane pair or associated beacon-gateway pair). This may include any of the following sub-steps:

[0296] (B.i) ^^ may be determined using the PAIRED_EVENTS( ^^) procedure, which determines a pair undergoing the same interaction and / or event (e.g. a beacon attached on a unit that is being lifted by a crane which has a gateway installed on it may be considered pairs such as beacon-gateway pairs, or unit-crane pairs);

[0297] (B.ii) if a given time t sits within the time interval ^^ then the interaction is under way for the pair. If a given time sits outside the time interval, then the interaction is determined to not be happening for the pair.

[0298] (C) Determine R, the proximity state of the entities. Proximity states may include ‘Near’ or ‘Far’, depending on whether RSSI data exceeds a threshold ^^. This may include any of the following sub-steps:

[0299] (C.i) R(t) may be determined as the beacon RSSI as measured by the gateway;

[0300] (C.ii) if R(t) > R, then the proximity state is ‘near’. Else, it is ‘far’.

[0301] (D) Determine interaction state combining move state and proximal state I( ^^). Output I( ^^).

[0302] In some embodiment, the interaction state determination step may include a convolution of the gateway and beacon movement & interaction signals.

[0303] Additionally or alternatively, the interaction state determination method may include the following steps: (i) The method takes as input signal profiles from positioning and signal strength based measurements associated with beacons and / or gateways and / or any other device or communication device or sensor device, wherein positioning data may include satellite positioning based data and signal strength data may include RSSI data; (ii) the method may convert position data into speed or velocity data; (iii) the method may translate the signals’ respective data-streams to movement and proximity state data, wherein a movement state may be ‘moving’ or static’ where speed data values may be mapped to a ‘moving’ state represented by a ‘1’ or a ‘static’ state represented by a ‘0’ based on whether the speed is above or below a predetermined speed threshold, and a proximity state may be ‘near’ or ‘far’ where RSSI data values may be mapped to a ‘near’ state represented by a ‘1’ or a ‘far’ state represented by a ‘0’ based on whether the RSSI value is above or below a predetermined threshold. Additionally or alternatively, the determination may be done using machine learning methods; (iv) the method may determine that a time frame wherein states may change, may be associated with a single aggregated interaction of lower granularity. For example, a crane lift interaction may comprise the lifting, moving and dropping sub-interactions, which may be determined to be part of the same interaction. This may be mapped to ‘possible interaction’ states and ‘no interactions’ states, wherein the possible interaction state is mapped to ‘1’ and ‘no interaction’ to ‘0’, such that the ‘possible interaction’ state covers the entire aggregated interaction (e.g. crane lift). This may be done both based on proximity state signatures and / or on move state signatures; (v) both aggregate proximity and move state signatures are combined for a final interaction state determination which may include ‘no interaction’ or ‘interaction’, mapped to ‘0’ or ‘1’ respectively. In some embodiments, the combination of data signatures may include signal convolution based methods.

[0304] The interaction methods herein may be used for any other embodiment of interaction determination based methods. For example proximity mappings and movement mappings may be executed based on any instrumented entities that may or may not interact. Additionally or alternatively, the state determination methods herein may also be used for any other embodiment of interaction determination as well as state and state change determination methods (e.g. applying a threshold to device data values and converting that into state and / or convolving signals or data from multiple devices for determining a state). Additionally oralternatively, the methods herein may be applicable to any other method herein involving inference based on device data such as based on beacon and / or gateway data. Supervised learning with Contextual Information Problem Statement, Inputs and Outputs

[0305] This example embodiment is configured to identify when (in time interval [ ^^1 , ^^2]) an asset ( ^^) has relocated an element ( ^^), from a location (L1) where several elements are collocated (B1, B2.. Bn) to a new location (L2) traversing over space with several other elements pre-installed (b1, b2, b3.. bm).

[0306] In some embodiments, interaction sequences for entities may not exactly match those outlined or expected by a given state machine or may otherwise be challenging to determine due to the presence of many entities. The methods herein allow for resolution of such scenarios. An example to highlight the scenario is installations on site wherein tower cranes have different movement profiles as compared to gantry cranes, which may, for example, be in violation of an interaction state machine identified in FIG.19. The confounding scenarios 2100 and 2102 of FIGS.21A-21 demonstrates one embodiment wherein a crane lifts an element where the beacon is wedged between slab layers or mounted at the base of the column. Other interaction confounding situations may include a crane hovering over other installed precast elements, whilst prior ground operations ensue, waiting to deliver the lifted element. Due to spatio-temporal compression, site operations involve dependencies that may not be incurred in factories.

[0307] The inputs may include the raw streaming data from the devices described in the core toolkit. These may include, for example, (1) received signal strength indicator (RSSI) signals transmitted at prescribed intervals by a beacon and received by a gateway, and (2) the GPS coordinates referencing the location of a gateway at prescribed intervals. In addition, situational data, which in this embodiment is defined to include identifying data or spatio- temporal data of any entity, including CO, CA, CC and sensor devices, may also be included, as well as any data of any type described herein including demand data, association data and other. This may include, site load demands (as a set of elements), prior site installations (as a set of elements), CA asset type (tower crane versus forklift truck) and site type (factory or site). This data can be used to build a set of beacons to be tracked for interactions by a set of gateways that can affect a lift interaction. Construction asset and objects involved in an interaction, Timing of the interaction, and relocation coordinates of the element by the asset caused by the interaction may be outputs.Algorithm Logic

[0308] The algorithm may be used for determination of when asset A has relocated an element B. However, state detection may be confounded by movement profiles and signal strength profiles that deviate from ideals due to real-world installation considerations, including movement patterns and lift patterns. In this scenario the models may be augmented through: (a) situational data that allows the models to build a series of hierarchical filters to reduce the noise that the signal analyzer contends with, and (b) the use of supervised learning to develop a model that predicts lift-interactions.

[0309] A Key precursor may include access to labelled data: Labelled data enables supervised learning models, which is further split into training and tests set, that are in order used to train the model and verify its accuracy. This may also include access to further data used to contextualize the labelled data, which may include: Information about (a) onsite lifting gateways (b) load deliveries to site provide a priori data that allows the model to specify filters, (c) newly arrived units, which may a database query or a real-time component of data analysis.

[0310] Data processing may include application of situational data using filters (on gateways, focused on elements in arriving loads), temporal analysis to analyze signals in intervals once loads have arrived on site. Interval-wise data smoothing to reduce the impact of noise in the signal for processing. Feature engineering may include methods to facilitate pattern identification. An analysis of the labelled data indicates unique patterns that may be used to characterize these signals. This includes ensemble estimates, which include statistical measures (e.g., mean, skew, kurtosis of sample) and determinative estimates (e.g., distance travelled over the interval) to enable characterization of the unique intervals that distinguish a lift event from other intervals where no lift event was detected.

[0311] The problem described herein may be represented as a pattern identification problem in a nested sequential framework (several signals analyzed as a collection in a given interval of time). The methods herein to solve this may comprise machine learning techniques. These methods may include generative models (e.g., naive Bayes), discriminative models (e.g., support vector machines), regression methods (e.g., logistic), graphical methods (e.g., decision trees), ensemble learning methods (e.g., bagging on weak learners like shallow decision trees). ML methods can handle small amounts of labelled data and yet achieve a decent amount of success. Methods herein may also comprise deep learning techniques such as RNN, LSTM, transformers and autoencoders, as well as ensemble methods that combine multiple deep learning models.Unsupervised learning with Minimal Contextual Information

[0312] This embodiment may be configured to identify when (in time interval [ ^^1 , ^^2]) an asset ( ^^) has relocated an element ( ^^), from a location (L1 ) to a new location (L2) traversing over space with signal noise and obstructions.

[0313] As outlined above, FIGS. 21A-21B depicts a crane lift wherein an element where the beacon is wedged between slab layers or mounted at the base of the column. Other interactions confounding situations include obstructions such as the crane hook block base acting as the barrier between the gateway and the beacon, or a gateway mounted on the bonnet of a shunter, moving a trailer of several units that act as obstructions for the mounted beacons.

[0314] The raw streaming data from the devices disclosed in the core toolkit herein may be the inputs. These are the (1) received signal strength indicator (RSSI) signals transmitted at prescribed intervals by a beacon and received by a gateway, and (2) the GPS coordinates referencing the location of a gateway at prescribed intervals. Some situational information regarding site operations, storage plans, CA asset types (tower crane, forklift truck, crawler crane) and Site type (factory or site). Prior awareness of scenarios will allow the enable integration of deterministic modelling into the systems herein. Construction asset and objects involved in an interaction, Timing of the interaction, and relocation coordinates of the element by the asset caused by the interaction may be outputs. Algorithm Logic

[0315] The algorithm may be used for determination of when asset A has relocated an element B. However state detection is confounded by movement profiles and signal strength profiles that deviate from ideal due to real-world installation considerations including movement patterns, lift patterns and obstructions. The methods herein solve for that by integrating the following into the model: (a) site geo-spatial knowledge (e.g., factory location, storage areas, open-source maps which include prior information), (b) site operational knowledge: gateway mounting on assets, potential sources of obstructions (such as A-frames on trailers), trailer transport methods etc.

[0316] This information may be collected from any data source herein including from site / factory operational documentation and / or site visits, video streaming of site status (that may be used to identify cause of deviations from the prior expected layout).

[0317] The key precursor includes prior information gathering such as geo-spatial layouts on the basis of which GPS coordinates can be used to identify areas of operation. This mayalso include operational information such as shunter-trailer interactions. This also includes deterministic-model development, which may comprise modelling of a spatial representation of signal strength, which extends beyond the calibration model that maps distance to signal strength. Mapping tools may be used to estimate signal strength whilst accounting for obstructions and computing signal attenuation due to blocking materials. By incorporating GPS signals with the system the model may accurately simulate signal strength between gateways and beacons and / or other devices. Data pre-processing may include interpretation of scenarios into the deterministic model as well as identification of intervals of time that are of interest and deemed worthy of simulations.

[0318] This may include prior modelling. By ingesting time intervals and GPS data the focus area may be identified. Prior information may be used to define the scenario and obtain simulations of signals for beacons of interest. Additionally or alternatively this may also include anomaly identification: The simulations in the prior step may be compared against acquired signals, and deviations form the basis for anomaly identification. Additionally or alternatively, this may also include Scenario modelling: Based on prior knowledge, scenario modelling may include modelling obstructions due to geometry of handling. For example, intermittent signals for some but not all beacons on a trailer may occur due to beacons being tethered to elements that may be intermittently obstructed whilst being moved by the shunter. The model may then incorporate geometric information about obstructions, may also include geometric variability to actually simulate or use statistical methods to interpret the variability. Additionally or alternatively, this may include Probabilistic Predictions. Multi-scenario modelling can be combined to generate simulated signals for each scenario. Comparisons with measured signals for various scenarios now require some level of reasoning to eliminate unlikely / select most probable scenarios or for insufficient confidence, propose variations on modelled scenarios. This may be executed using Bayesian inferencing based methods wherein priors may be updated in the light of simulated scenarios. Other Embodiments

[0319] In some embodiments, gateways and beacons can communicate as long as they are within range, the beacons transmit information and gateways act as receivers. The gateways may be mounted on construction assets or at static locations in strategic areas. Four key scenarios include: Static Gateway / Static Beacon; Static Gateway / Dynamic Beacon; Dynamic Gateway / Static Beacon; and Dynamic Gateway / Dynamic Beacon.

[0320] The beacons or gateways may collect timestamps alongside each signal or sensor measurement point, in this way this becomes 4D Location Tracking. The system may synchronize and manage time drift through various network topologies.

[0321] Algorithmic specifics may vary depending on the particular configuration of beacons and gateway, as well as the type of interaction being captured. For example, one instantiation may involve the use of two gateways one dynamic on an asset, and another fiducial (e.g., placed at a known, static location, not involved with the interaction) and a dynamic beacon (e.g., beacon made dynamic by being placed on a dynamic object). In this instantiation, it may be possible to compare the signatures gathered by each gateway and determine an interaction. Another instantiation may involve a single gateway and beacon. In this case, comparison is impossible so the signature gathered by the singular gateway may be used in absolute terms to infer an interaction. Any conceivable combination of beacon and gateway configurations may be used here. Interactions may allude to different types of activities involving beacon-gateway / entity-asset pairs and need not be limited to movement (or location alone). Therefore, certain signatures in gateway and beacon tracking data (including those based on the signal and sensor data, and a multivariate combination of both) may indicate these different types of interactions between the entities each sensor is linked to. The system / models may therefore use these signatures to infer whether interactions have happened. Once this has been confirmed within a certain likelihood threshold, the system may classify these interactions by activity type and infer the nature of the interactions having occurred.

[0322] Interactions that evolve properties other than location (e.g., which change the physical or geometrical composition of an entity for example) may be determined by using the 4D-spatio-temporal determination data. In this way, the full scope of construction logistics related interactions may be mapped. The system may also employ Machine Learning techniques described herein to automatically infer the interaction type with no use of prior knowledge. 4D-Location Tracking Algorithm

[0323] The systems may operate to identify the location of any construction resource alongside associated time stamps (e.g. in a yard or on site). Tracking The Location An Element In The Yard Using Gateways And Beacons

[0324] With reference to an example construction element prefabricated in a factory, the systems may consider an abstraction of the sensors described herein a beacon synonymous withan element and a gateway with an asset. The raw streaming data from the devices described herein may be inputs. These are the (1) received signal strength indicator (RSSI) signals transmitted at prescribed intervals by a beacon and received by a gateway, and (2) the GPS coordinates referencing the location of a gateway at prescribed intervals. The outputs may be the precise location and timestamp coordinate for an element. By inspection, the location specific problem statement is answered with the answer to the interaction specific problem statement, as the location of the beacon will be known at the end of an interaction by assigning the GPS coordinate of the gateway involved in the interaction the time of the end of the interaction. Location Tracking / Determination by Proximity and Trilateration:

[0325] Noting that the yards have elements instrumented with beacons and are associated with specific lifting assets (gantry cranes, forklift trucks) that are all installed with operational gateways the system may determine that virtually all beacons will be within range of at least one gateway several times a day. The fingerprint of the signals of these interactions, assuming no move was completed, may be translated into a location in one of two ways. Both of these methods rely on a predetermined relationship between distance of a gateway and the signals received by that gateway in the yard.

[0326] The first method of determining location directly, proximity, may be employed when the signal strength exceeds a predetermined threshold such that it is accurate to assume that the asset and beacon passed so close to one another at time (t), that the beacon’s location at time (t) what the gateways GPS coordinate at time (t). The second method of determining location directly, Trilateration, when the received signal strength of the beacon exceeds a certain minimum threshold but is also below the minimum threshold for employing proximity. The system may use the GPS coordinates associated with (3) values which fell into this range and associating those signals with the predetermined signal-distance ratio, intersect three (3) circles to arrive at an estimated location of the beacon as shown in the trilateration schematic 2200 in FIG.22. Other Embodiments

[0327] In other embodiments, the location system may be formed of devices (e.g., gateways and beacons) that may, through novel proprietary algorithms that leverage machine learning, signal strength correlation logic and sensor inference, track location of assets. For example, gateways and beacons may communicate as long as they are within range, the beaconstransmit information and gateways act as receivers. This relationship may be wrapped into a single device, where every device listens to all other devices on a public channel and prior private data exchanges through alternate means allows the system to decrypt the information and add context, thus ensuring secure data even over standard channels. The specific subtleties of the algorithms for location determination may be different for each scenario, but the general logic of using signal strength correlation remains the same. The beacons or gateways may collect timestamps alongside each signal or sensor measurement point, in this way this becomes 4D Location Tracking. The system may synchronize and manage time drift through various network topologies.

[0328] This foundational location determination technique may be enhanced in a number of ways. One embodiment may enable the beacons the ability to communicate with each other. In such a paradigm, it would be possible to create a daisy chain / mesh network of distributed, strategically placed beacons surrounding a gateway. In such a paradigm, signals from beacons theoretically out of range of the gateway may be relayed to the gateway by beacons closer to it, such that the location of those may be tracked. Another example where this may be particularly valuable is in refining the position / location of several precast units relative to each other in a stack of units in a yard. By relying on a mesh network of beacons, the system may precisely determine the stacking order, further refining the positioning algorithm.

[0329] In some embodiments, location determination may be executed based on mapping RSSI data to distance. Additionally or alternatively, the RSSI signal associated with an RF signal. Additionally or alternatively, this mapping may be based on the median attenuation of a radio signal being dependent on distance (between antennae) through free space, and the variability of the signal. Additionally or alternatively, the relationship between RSSI and distance may be defined as:

[0330] ^^( ^^) = 10^^− ^^⁄ ^^

[0331] Wherein ^^, ^^ are respectively the signal strength at unit distance between antennae and the path attenuation factor which accounts for environmental conditions. Additionally or alternatively, these parameters may be determined using a calibration procedure that measures signal strength at known distance. Relay Node Firmware

[0332] In another embodiment, the location and interaction determination methods and other methods in the core toolkit include the use of BLE mesh protocols and manipulation ofthe PDU (protocol data unit) to include specific details (e.g., first relay node that receives a BLE packet from a beacon, the signal strength at this first relay, timestamp of message received) in addition to the BLE packet generated by the beacon.

[0333] Further aspects of the algorithms include the use of BLE mesh hop counters to ensure decay of the messages (avoiding an infinite life of messages that is energy inefficient), as well as making use of publish-subscribe messaging protocols. This may be leveraged to boost message life to allow for messages to be routed to a remote gateway. Additionally or alternatively, use of different relay node types may occur. For example, this may include static relay nodes, which are associated to a fixed location (enabled at system installation) and may retain a short buffer of received messages. The node firmware may temporarily block repeated messages from the same source over a predefined period of time, leveraging a time based white- list logic. Another example includes dynamic relay nodes which are associated to a movable asset. An in-built accelerometer is used herein to detect motion of the asset, and a suspension of the white-list rejection logic may be invoked in order to receive a continuous signal stream from a beacon / unit that is being moved by the construction asset. Position

[0334] At provisioning, the static relay nodes may be geo-located, and in addition the discrete position error will be known. This may be stored in a look-up table, which may be used by the algorithm. In an interval of time, the database will receive various message packets for a beacon from potentially different relay nodes. The algorithm will select the message with the strongest signal. It will apply the geo-location of the relay node to the beacon with the associated relay-node position error. Interaction

[0335] At provisioning, the dynamic relay nodes may be associated with an asset that houses a hardwired generic gateway inside the asset’s cabin. This provides dynamic geo- location information that may be associated to the relay node. When an element (with a BLE beacon) is lifted, the relay-node receives a constant stream of signals, over a duration when there is movement. The interaction algorithm will tie in the dynamic relay-nodes’ associated gateway’s GPS coordinates with the beacon RSSI of the lifted beacon. The algorithm extracts the start and end times of lifting and the new location where the element was placed, which is the definitive information associated to a unit.Embodiment for Construction Factory Application

[0336] Another embodiment includes system and / or methods herein comprising strategic placement of devices for optimal communication and tracking. Specifically, the methods herein comprise use of relay nodes, which act as beacons with a priori known precise locations, that may receive and / or transmit signals from other beacons. In the factory, for example, these would be strategically placed at the grid markers of the facility. In this configuration, beacons are affixed to precast units. The beacons emit radio signals which are detected by the relays within range. Upon receiving these signals, the relay node packages up data and transmits it on to other relays, within the coverage area. This creates an effective communication network based on the Bluetooth Low Energy (BLE) mesh protocol. This BLE mesh network ensures a robust and reliable mode of communication across the entirety of the prefabrication facility, reaching even its most remote corners. The messages emanating from the beacons, which carry critical data about the precast units, continue to traverse from one relay to another within this network.

[0337] The transmission of messages concludes when the data packets reach a gateway that may receive signals from nearby beacons and relays. The gateway packs up the information and transmits the data to a cloud database for further analysis. This cloud-based processing enables real-time tracking and efficient coordination of resources, thereby providing valuable insights for managing transportation and installation of prefabricated units. This embodiment may be used in industrial environments and logistics instances comprising obstruction of dense materials. The network topology allows for flexible data routing minimizing impact data loss from obstructions. Embodiment for Construction Site Application:

[0338] In one embodiment, the methods herein may be applied in the context of a construction site. Herein, the system may include three types of devices: beacons, relays, and gateways. Beacons are attached to mobile construction resources such as equipment, tools, and workers. Static relays may be strategically placed at predetermined known locations throughout the site to pick up signals from the beacons and pass them on to other relays or gateways. Examples of these known locations may include column grid intersections, ingress / egress points, slab openings, and other such locations which offer widest coverage. Dynamic relays may be placed at the end of a crane hook block. For asset tracking, gateways may be positioned inside the cabin receiving data from the relay nodes. Gateways may also be located at specific points around the site. The gateways will receive these signals and transmit them to the cloudfor further processing. Gateways may also be attached to the side of a job site trailer in a static implementation.

[0339] The beacon-relay-gateway association creates a robust communication network across the entire construction site. Beacons attached to construction resources emit signals that are picked up by nearby relays. These signals, carrying crucial data about the resource's location and status, pass through the network of relays until they reach a gateway which transmits the data to the cloud. This results in real-time tracking and efficient coordination of resources within the construction site, in particular, the relationship between space, time, and construction resources. The methods and / or systems herein may be used for real-time resource tracking and monitoring, equipment and asset management, site safety compliance monitoring and augmented project management. Core Toolkit Algorithms Embodiment

[0340] A third embodiment includes instrumenting resources and / or entities with beacons that include GPS and / or accelerometers, such that direct location determination may be executed, as well as separate devices used exclusively for data relay. Interactions may be determined based on proximity, velocity, acceleration and other signal features from these signal types (e.g., sharp increases in velocity).

[0341] The methods herein include enhancements to the BLE based methods described previously. These novel embodiments may comprise the use of an accelerometer to monitor element movement, in some embodiments, wherein the beacon or device may be embedded, at which point BLE messages will be constructed (including GPS coordinates over and above the standard message packet). In addition a timer may also be included to ensure proof of life messages can be sent. This may be used for extending the life of the BLE device, which may be in sleep mode until activated. The algorithms herein may leverage BLE mesh protocols, wherein the PDU will be routed by the relay network without requiring message updates, noting that the beacon that serves as the source of the original BLE message packet will serve up the GPS coordinates. In this embodiment, position may be directly determined by GPS data. For a given interval of time, the database may receive several message packets for a beacon from potentially different relay nodes. The sifting logic for the interval retains the most recent coordinate in the examining time interval. Interactions may be determined. Interactions are determined on the basis of direct location data, and accelerometer data. Other features may include emission of location and / or movement data from the GPS and / or accelerometer, which may then be detected by the strategically placed relays within the facility. Additionally oralternatively, another feature may include the use of sink nodes in the mesh system to transform and transmits signals to the cloud for further analysis. Embodiment for Transportation of Construction Objects

[0342] In one embodiment, the system is configured to monitor and generate insights associated with the transportation of construction objects from the factory to the site. The placement of devices embedded with GPS and accelerometers on these objects creates an optimal tracking and communication mechanism during transportation. Specifically, beacons may be affixed to the construction objects before they are loaded onto trailers for delivery, and these beacons emit signals inclusive of location and movement data from the GPS and accelerometer. Upon receiving these signals, gateways strategically placed along the transportation or on the lorry moving the trailer transmit the received RSSI signal strength, GPS coordinates, and accelerometer data to gateways positioned at significant points along the route. These gateways then forward these signals to the cloud for further analysis. This cloud- based processing enables real-time tracking and efficient coordination of resources, thereby providing valuable insights for managing the transportation and installation of the construction objects.

[0343] Features of this system may include estimated time of arrival prediction based on movement data associated with lorries on their way to site; additionally or alternatively, determination of damage during transportation. The accelerometer in each beacon may be used for determination of impacts and / or abnormal movements that may be indicative of possible damage to the construction objects during transportation; additionally or alternatively, the methods herein may be used for determination and calculation of Time of Demurrage on Site, for comparison against specified or stipulated time. Other Embodiments

[0344] Further embodiments include the use of a unified devices which may include GPS, accelerometers, as well as data relaying capabilities. One specific embodiment includes use of this system to monitor and track objects associated with the construction of a tall tower. The placement of devices embedded with GPS and accelerometers on construction elements results in an optimal tracking and communication mechanism during the building process. Specifically, beacons may be affixed to different construction objects before they are hoisted onto the respective floors of the building. These beacons emit signals, inclusive of location and movement data from the GPS and accelerometer. Upon receiving these signals, relaysstrategically placed on each floor transmit the BLE messages (that include GPS coordinates, and accelerometer data) to relays on the floors above them, creating an effective communication network based on the Bluetooth Low Energy (BLE) mesh protocol. The transmission of messages concludes when they reach a beacon that has cloud connection, located at the top of the building, which then forwards these signals to the cloud for further analysis. This cloud-based processing enables real-time tracking and efficient coordination of resources, thereby providing valuable insights for managing the construction of the tall tower. This system enables reliable vertical communication in environments with high verticality. The system herein may also be used for structural health monitoring. Accelerometer data from devices attached at various levels on the structure may be used to detect unusual vibrations or movements that could indicate potential structural issues. Another specific embodiment includes comprehensive tracking of various types of entities including operatives, machinery or construction assets, and construction objects. By cross referencing real-time data from various entities with data from 4D spatio-temporal representations, site bottlenecks may be predicted and mitigated. Embeddability

[0345] As described herein, logistics devices may be embedded inside of construction resources, which constitutes a particularly novel embodiment of the techniques herein. In one specific embodiment, this may include a beacon device embedded inside of a construction element (e.g., precast concrete element, where the device uses any of the attachment methods for embedded devices described in this document). The methods allow for localization and interaction tracking using a system of embedded beacon devices. In such embodiments, the core algorithm toolkits are able to compensate for the effect of the host material on the signal generated by the device. For example, for a beacon embedded in a concrete element, the concrete (and any reinforcement) will attenuate the signal generated by the beacon by a characteristic factor based on the properties of the host material / concrete. This attenuation factor may be characteristic of the material properties of the host-material / concrete and may be adjusted, normalized, or otherwise accounted for. Daisy Chaining

[0346] In another embodiment, logistics devices may be daisy chained, or installed in a distributed configuration within range of each other. This may increase the tracking range of the entire logistics system. In one embodiment, this includes daisy chaining beacon devicesaround gateway devices. Using a single gateway and a distributed network array of beacons may allow for distributed, parallelized tracking of a multitude of construction resources. In this embodiment, each daisy chained beacon may achieve the same functionality as a gateway, wherein other beacons may be tracked and / or localized relative to this first beacon. Down the chain, all beacons may be localized / tracked relative to the gateway device. This embodiment may be particularly advantageous for embedded beacons, and for tracking stacking order of a plurality of prefabricated units, which impacts load tracking. Further Beacon and Gateway Sensor and / or Device Embodiments

[0347] Further embodiments of Gateways and Beacons may also include embodiments formed of any device type, sensor and actuator type, and / or device configuration listed herein such as mechanical wave-based devices, E&M wave-based devices, point devices or others, configured to track construction resources and / or processes. For example, an advanced embodiment may include the device described above, with the above system configuration, and which may additionally onboard other sensors and / or actuators such as accelerometers, gyroscopes, other inertial sensing systems, temperature sensors etc.

[0348] Beacons emit signals to be received by gateways. These signals may be E&M signals (e.g., frequency bands of UV, visible spectrum, IR, RF for example Wi-Fi, Bluetooth, AM, FM, shortwave and / or others). Signals may also be mechanical waves for example ultrasonic waves, acoustic waves and / or others. Signals may be generated by any sensor and / or actuator type including but not limited to those listed herein, for example this may apply to signals generated by wave-based sensing device and / or point sensing devices Embodiments may also take the form of arrays, including for spatial tomography processes. Time-domain reflectometry (e.g., through GPR techniques within construction elements, or more generally through E&M waves on the jobsite) may be employed to spatially map and position construction resources.

[0349] Beacons and gateways may become unified, miniaturized into a single device capable of detection and / or communication with all other devices with registration information providing the system full context. Further embodiments may also use techniques for positioning, interaction determination and any other technique listed herein, in any capacity (in particular, the use of structural and temporal data, such as BIM and construction schedules, may be used to refine positioning, by utilizing such resources as a priori knowledge, with an associated confidence bound).Further Algorithmic Embodiment

[0350] Advanced embodiments include the augmentation of the beacon and gateway system (and the RSSI method) to include Time of Arrival (ToA) based localization. Time of Arrival based localization leverages time domain analysis. Assuming a synchronized clock (or by establishing one), the relative time difference between a signal being sent and received can be established. In light of sight scenarios, this may be used to detect the distance between construction objects. In practicality, reflections and multi-path interference may need to be cleaned out. The amplitude of any reflected signal should be lower, and there may be a phase shift, so it should be possible to identify the line of sight signal amongst a plurality of signals.

[0351] Another advanced embodiment employs angle-of-arrival based sensing, through antenna arrays. This may augment or replace RSSI-based and / or ToA methods. In AoA sensing, instead of estimating the distance of a signal (e.g., based on its RSSI) or the ToA, the angle of arrival of the signal is computed, using an array of receiving antennas. This may be done by comparing the differences in the time of arrival of a signal at a plurality of spatially separated antennas (separated with a known distance). This is known as the phase difference. By analyzing the phase differences, the system is able to determine the angle of the incident signal relative to a reference (which is known as the angle of arrival). Advanced signal processing techniques may be employed where significant multi-path interference is present, to clean the signal (optionally this is done using a machine learning model, trained on construction site data, or on synthetic simulated data for construction environments - for both embedded and non-embedded cases). Knowledge by the device, through other sensors such as wave based sensors, of its host material characteristics (e.g. in concrete, and geometry) may be used to augment the AoA method.

[0352] Another advanced embodiment employs accelerometer, altimeters, pressure sensors and / or other inertial sensor data to augment positioning and interaction accuracy of all the above methods. These sensors may be mounted on the beacon of interest, or on one or more gateways in proximity to the beacon, or on one or more nearby beacons, and provide information on the acceleration, rotations and altitude of each device. This may be used to increase the accuracy of positioning. For example, in dynamic systems, accelerometer data may be integrated (over short periods of time) to estimate a velocity vector for the beacon or gateway. Over long periods of time, this will suffer from integration errors, but over short periods of time, it can be used to refine positioning estimations. Altimeter and pressure data may be used to locate the device in 3D space (including the floor it is on). These sensor data may be fed into a model (optionally a machine learning model), which may be executed on thedevice, a nearby device, or a server (or a combination of those), to provide higher accuracy positioning estimates.

[0353] In a further embodiment, the system is treated as a distributed system. RSSI, AoA and ToA data, sensor data of all of the types is analyzed across a plurality of beacons, gateways, mobile phones etc. (where beacons are in both transmission, but optionally also receiving mode - e.g. through daisy chaining). This network of datasets may be combined to build an improved positioning map. The multiplicity of data sources can be used to generate a higher resolution positioning determination and remove the influence of noise and / or multipath.

[0354] In another embodiment, a different global positioning or satellite system is used (e.g., Galileo or the like). In a further embodiment, the RF module is used to analyze opportunistic reference signals may be used (e.g., from satellites, FM radio stations, LTE or 5G mobile towers, Wi-Fi access points, mobile phones or other sources). Optionally, the positioning of these signal sources is known. These signals will include synchronization sequences (which in some cases, may be encrypted). For example, these other third-party devices may employ OFDM (orthogonal frequency division multiplexing). Synchronization sequences (such as the CRS emitted by an LTE cell-tower) may be extracted, and the period and changing frequencies of these signals can be characterized and used for opportunistic positioning. This may be done with or without any prior knowledge of the expected signal structure. The applicable ground-based or satellite-base stations are detected. Their signals are analyzed for periodicity and synchronization sequences extracted. These are then used to obtain characteristics related to the position of the beacon and / or gateway. In opportunistic positioning systems, positioning may be carried out without any uplink communication back to the signal source, which carries significant advantages.

[0355] Further embodiments may employ the use of RFID or NFC-based positioning (with RFID or NFC-based beacons). These may be suited to low cost units. QR codes disposed on the units, alongside high resolution cameras (e.g. embedded in the gateways) may also be employed for positioning. Ultrawideband-based positioning may also be employed, which leverages high frequency radio (3 to 10GHz), pulsed signals. Short (picosecond long) pulses are sequentially sent by the transmitter. ToA analysis is carried out (which can be carried out with very high precision given how short the pulses are). This allows for distance determination with accuracy of the order of 10cm. Trilateration techniques as described herein are then applied to determine the position. UWB carries particular advantages in non-light of sight scenarios.

[0356] In a further embodiments, one or more of the following is employed. Quadrilateration is carried out for 3D positioning (that includes height), RTK GPS techniques are employed where Real-time Kinematic GPS augments GPS with fixed base stations of known locations, and / or Positioning information is fused with laser scanning data (from total stations on the construction site). This allows the positioning of fixed (static) gateways and beacons (e.g. those that may have been mounted on the crane base can be considered static, and beacons embedded in units that have been installed can be considered static).

[0357] Smartphones and other personal devices may also act as gateways (either through a mobile application, or in the background, or otherwise). As the construction of the structure completes, with embedded beacons, those units are installed in known locations (as defined by, for example, the BIM model, or laser scanning data operated by an operative). This provides further information to the models herein, for further refinement of positioning accuracy. The advanced embodiments may also be combined (so trilateration / quadrilateration, angle of arrival, time domain analysis positioning, inertial and other sensor data, and nearby device data, a priori knowledge from BIM models and schedules would be combined into a model to output a highly accurate positioning determination). Cumulative Element Lifts

[0358] A construction object might be the object of an interaction multiple times in the course of its existence. There are numerous examples in the supply chain where tracking the history of these interactions would lead to reduced friction and / or improve QA. One example of this would be in certain jurisdictions for certain element types, there is a finite number of lifts that are acceptable for quality assurance purposes. If recorded using sensors, these interactions could be tracked and stored in the object’s Data Passport and exposed to various stakeholders. Load Analytics Tracking Insights

[0359] The use of machine learning techniques (and other data analysis techniques as described herein) to analyze load information collected from beacons and gateways and provide tracking insights (e.g., % of loads loaded on time) provide significant benefit to improve factory and site performance, coordination, and overall orchestration activities. This will enable the production of key performance indicators that inform decision making. Asset Utilization

[0360] At all levels of the supply chain, measuring the efficiency of asset use is rarely performed. By instrumenting assets, energy expenditure and efficiency may be measured. By understanding the nature of how these assets expend energy, over what time period, and to what result, allows for reduction of friction. For example, a tower crane on site interacts with dozens of construction objects every hour. If by instrumenting this asset, a project manager determines that the time length of these interactions with precast concrete elements for precast concrete elements follows a normal distribution whose average is 6.5 minutes, whereas their assumptions for the project planning called for 3, they will know that there is an average of 3.5 minutes worth of delays per lift which cumulatively, will result in a project delay. They may then use this information to determine how to improve site operations. The Logistics Enabling Toolkit

[0361] A register is used to create a non-public (encrypted) link between construction resources (asset or object) and its associated device. The algorithm separates input data streams to connect the device to its associated resource. As illustrated in the example logic blocks 2300 of FIG. 23, any construction resource object or asset may be instrumented. Therefore an identification system such as a raw image, or image of a barcode or QR-code for both the element and the device will be fed into system. The method reads the inputs from element and device, where the reading method is dependent on input type (e.g., OCR for alpha-numeric codes, barcode / QR code reader for 1D or 2D matrix of data, or any similar ID encoding information processor) that may extract the unique identifier from the image. Algorithm Embodiments

[0362] As shown in FIG.23, an algorithm R1 is illustrated where the first datastream in an input that includes an image reader (with OCR / QRcode / barcode reading) that converts images to textual data (or direct textual input of the element identifier), the second datastream is a similar textual / QRcode / barcode. The internal logic creates a 1:1 mapping between the two, in order that they may be accessed. Internal logic includes error-checking to prevent non-unique mapping.

[0363] As shown in FIG.23, an algorithm R2 is shown. Algorithm R1 inherently involves humans to use the application to registers the units. Double tagging can introduce inefficiencies and errors, hence in the second generation packet sniffing logic is included to eliminate one less input stream / one less source of error.

[0364] As shown in FIG.23, an algorithm R3 is shown. Integrating this embodiments with other tools, the system may identify the Element Id and with the packet sniffer from R2 and completely eliminate sources of human error. Entity Creation (A)

[0365] Entity creation may operate to determine at any time during a given project timeline if any construction object exists. Identifying that a construction object has been created and exists is important in the construction logistics supply chain. This action naturally...

Claims

CLAIMS:

1. A computer-implemented method for construction resource operations, the method comprising: receiving a first dataset comprising one or more first data entries, wherein the first data entries are associated with at least a first construction resource; generating a spatio-temporal sequence for the first construction resource, wherein the spatio-temporal sequence defines one or more operations configured to minimize the construction friction with a project associated with the first construction resource; and outputting at least a portion of the data associated with the spatio-temporal sequence.

2. The computer-implemented method according to Claim 1, wherein the first construction resource comprises one or more of: a construction object, wherein the construction object is a construction resource that is passive during a time period of an interaction associated with the construction resource; or a construction asset, wherein the construction asset is a construction resource that is active during the time period of the interaction associated with the construction resource.

3. The computer-implemented method according to Claim 1, wherein the construction friction comprises one or more of: a time cost; a financial cost; an energy cost; a utilization metric; a safety metric; an emitted CO2cost; or a waste metric.

4. The computer-implemented method according to Claim 1, wherein the spatio- temporal sequence defines a set of one or more of: a physical location of the first construction resource; a configuration of the first construction resource; or an operation of the first construction resource.

5. The computer-implemented method according to Claim 1, further comprising determining an interaction associated with the first construction resource.

6. The computer-implemented method according to Claim 5, further comprising modifying the spatio-temporal sequence in response to the determined interaction.

7. The computer-implemented method according to Claim 6, wherein modifying the spatio-temporal sequence comprises modifying one or more of: a physical location of the first construction resource; a configuration of the first construction resource; or an operation of the first construction resource.

8. The computer-implemented method according to Claim 1, wherein generating the spatio-temporal sequence further comprises deploying a machine learning (ML) model on the first dataset.

9. The computer-implemented method according to Claim 1, wherein, in generating the spatio-temporal sequence, the method further comprises determining a location of the first construction resource.

10. The computer-implemented method according to Claim 1, wherein, in generating the spatio-temporal sequence, the method further comprises determining a state of the first construction resource.

11. The computer-implemented method according to Claim 1, wherein the one or more first data entries are associated with a second construction resource of the project.

12. The computer-implemented method according to Claim 11, further comprising: determining an interaction between with the first construction resource and the second construction resource; and modifying the spatio-temporal sequence in response to the determined interaction.

13. The computer-implemented method according to Claim 1, wherein the construction resource is a prefabricated building element.

14. The computer-implemented method according to Claim 1, wherein the one or more first data entries are generated by one or more sensor devices associated with the construction resource.

15. A computing device comprising: a non-transitory storage device; and a processor coupled to the non-transitory storage device, wherein the processor is configured to: receive a first dataset comprising one or more first data entries, wherein the first data entries are associated with at least a first construction resource; generate a spatio-temporal sequence for the first construction resource, wherein the spatio-temporal sequence defines one or more operations configured to minimize the construction friction with a project associated with the first construction resource; and output at least a portion of the data associated with the spatio-temporal sequence.

16. The computing device according to Claim 15, wherein the first construction resource comprises one or more of: a construction object, wherein the construction object is a construction resource that is passive during a time period of an interaction associated with the construction resource; or a construction asset, wherein the construction asset is a construction resource that is active during the time period of the interaction associated with the construction resource.

17. The computing device according to Claim 15, wherein the processor is further configured to: determine an interaction associated with the first construction resource; and modify the spatio-temporal sequence in response to the determined interaction.

18. A computer program product comprising at least one non-transitory computer- readable storage medium having computer program code thereon that, in execution with at least one processor, configures the computer program product for: receiving a first dataset comprising one or more first data entries, wherein the first data entries are associated with at least a first construction resource; generating a spatio-temporal sequence for the first construction resource, wherein the spatio-temporal sequence defines one or more operations configured to minimize the construction friction with a project associated with the first construction resource; and outputting at least a portion of the data associated with the spatio-temporal sequence.

19. The computer program product according to Claim 18, wherein the first construction resource comprises one or more of: a construction object, wherein the construction object is a construction resource that is passive during a time period of an interaction associated with the construction resource; or a construction asset, wherein the construction asset is a construction resource that is active during the time period of the interaction associated with the construction resource.

20. The computer program product according to Claim 18, further configured for: determining an interaction associated with the first construction resource; and modifying the spatio-temporal sequence in response to the determined interaction.

Images