A computer system and a computer-implemented method that utilize a sensor-driven dynamically adjustable feedback loop to manage device-based risks at the asset-specific level of energy data usage

Abstract

To provide a computer implementation method and system which determine and reconsider a failure insurance fee for energy consuming physical asset.SOLUTION: A method according to the present invention includes the steps of: receiving asset-unique history data and asset-unique current energy consumption data; determining, for each corresponding physical asset category, each corresponding average severity of each failure based on corresponding failure frequency and the asset-unique history data; determining current energy consumption data for each of the corresponding physical asset categories based on the asset-unique current energy consumption data; associating, with a specific physical asset category, each of the corresponding energy consumption places representing an energy consumption physical asset of an aggregate of energy consumption physical assets; and determining, for each of the corresponding energy consumption places, a specific use based failure insurance fee value based on the number of the energy consumption physical assets of the aggregate of the energy consumption physical assets in the corresponding physical asset category associated with the energy consumption place and the corresponding current energy consumption value per each physical asset with respect to each of the corresponding physical asset categories.SELECTED DRAWING: Figure 3A

Description

Technical Field

[0001] Cross - Reference to Related Applications This application claims the benefit of U.S. Provisional Application No. 62 / 537,684, filed Jul. 27, 2017, which is hereby incorporated herein by reference for all purposes.

[0002] In some embodiments, the present invention relates to a computer system and a computer - implemented method that utilize a sensor - driven dynamically adjustable feedback loop to manage device operation based on an asset - specific level of energy usage.

Background Art

[0003] The current computing era has introduced an array of small devices that perform various specific functions. For example, sensors or sensor devices have seen significant advancements in structure and low - power technology. In some applications, sensors can utilize micro - electro - mechanical systems, i.e., MEMS technology. A sensor can include more than one component, such as an embedded processor, digital storage, power source, transceiver, and an array of sensors, environmental detectors, and / or actuators. In some cases, sensors rely on small batteries, solar cells, or ambient power energy and can operate for long periods without maintenance. In some applications, sensors are present within or attached to one or more device units and are tasked with collecting data regarding one or more operations of the associated device and / or environmental conditions.

Prior Art Documents

Patent Documents

[0004] [Patent Document 1] U.S. Patent Application Publication No. 2017 / 0076263 (A1) [Summary of the Invention]

[0005] In some embodiments, and optionally, in any combination of the embodiments described above or below, the present invention provides a typical innovative computer implementation method. This method at least includes a step in which at least one processor receives, for a set of energy-consuming physical assets during a predetermined time, i) asset-specific historical data and ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor, or both, where the asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operation characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data, and a step in which the at least one processor determines, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and a step in which the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and a step in which the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and a step in which the at least one processor determines, for the set of energy-consuming physical assets, For each corresponding energy consumption location representative of at least one energy-consuming physical asset of the assembly , associating with a specific physical asset category, and the at least one processor For each corresponding energy consumption location, i) at least one of the aggregate of the energy-consuming physical assets in the corresponding physical asset category associated with the corresponding energy consumption location The number of energy-consuming physical assets, and ii) based at least in part on the number of each physical asset per corresponding physical asset category and the corresponding average current energy consumption value per physical asset, determining a specific usage-based Failure insurance premium value, and the at least one processor, based at least in part on the specific usage-based failure insurance premium value of the corresponding energy consumption location, i) at least one service Provider that provides services to the at least one energy-consuming physical asset, ii) at least one electronic device of at least one entity associated with the at least one energy-consuming physical asset, iii) the at least one Sensor, or iv) generating at least one warning for at least one of the at least one energy-consuming physical assets, and the at least one electronic warning Is, for the location-specific level of energy usage of the at least one energy-consuming physical asset, i) requesting a new usage-based failure insurance premium value or a change in the usage-based failure insurance premium value , ii) causing at least one user associated with the at least one energy-consuming physical asset to change the level of energy usage of the at least one energy-consuming physical asset, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset Including, and the at least one electronic warning At least one electronic device of at least one entity associated with the at least one energy-consuming physical asset, iii) the at least one Sensor, or iv) generating at least one warning for at least one of the at least one energy-consuming physical assets, and the at least one electronic warning Including generating at least one warning for at least one of the at least one energy-consuming physical assets, and the at least one electronic warning Is, for the location-specific level of energy usage of the at least one energy-consuming physical asset, i) requesting a new usage-based failure insurance premium value or a change in the usage-based failure insurance premium value , ii) causing at least one user associated with the at least one energy-consuming physical asset to change the level of energy usage of the at least one energy-consuming physical asset, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset Requesting, ii) causing at least one user associated with the at least one energy-consuming physical asset to change the level of energy usage of the at least one energy-consuming physical asset, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset At least one user associated with the at least one energy-consuming physical asset to change the level of energy usage of the at least one energy-consuming physical asset, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset Usage level, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset Instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset , iv) instructing the at least one user to adjust at least one environmental characteristic of the at least one energy-consuming physical asset, and v) affecting at least one of: instructing the at least one user to adjust at least the sensor operation of the at least one sensor. It is configured to be affected by at least one of: In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one energy-consuming physical asset is a physical configuration including one or more unit of equipment (UOE). In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one historical environmental characteristic is at least one of at least one light parameter, at least one acoustic parameter, at least one pressure parameter, at least one temperature parameter, at least one temperature parameter, at least one acceleration parameter, at least one magnetic parameter, at least one biological parameter, at least one chemical parameter, or at least one motion parameter. In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one light parameter is selected from the group consisting of infrared light parameters, visible light parameters, and ultraviolet light parameters. In some embodiments, each corresponding energy consumption location is defined based on global positioning system (GPS) data identifying the physical location of the at least one energy-consuming physical asset. In some embodiments,

[0006] In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one energy-consuming physical asset is a physical configuration including one or more unit of equipment (UOE). In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one historical environmental characteristic is at least one of at least one light parameter, at least one acoustic parameter, at least one pressure parameter, at least one temperature parameter, at least one temperature parameter, at least one acceleration parameter, at least one magnetic parameter, at least one biological parameter, at least one chemical parameter, or at least one motion parameter. In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one light parameter is selected from the group consisting of infrared light parameters, visible light parameters, and ultraviolet light parameters. In some embodiments, each corresponding energy consumption location is defined based on global positioning system (GPS) data identifying the physical location of the at least one energy-consuming physical asset. In some embodiments, In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one historical environmental characteristic is at least one of at least one light parameter, at least one acoustic parameter, at least one pressure parameter, at least one temperature parameter, at least one temperature parameter, at least one acceleration parameter, at least one magnetic parameter, at least one biological parameter, at least one chemical parameter, or at least one motion parameter. In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one light parameter is selected from the group consisting of infrared light parameters, visible light parameters, and ultraviolet light parameters. In some embodiments, each corresponding energy consumption location is defined based on global positioning system (GPS) data identifying the physical location of the at least one energy-consuming physical asset. In some embodiments, the at least one historical environmental characteristic is at least one of at least one light parameter, at least one acoustic parameter, at least one pressure parameter, at least one temperature parameter, at least one temperature parameter, at least one acceleration parameter, at least one magnetic parameter, at least one biological parameter, at least one chemical parameter, or at least one motion parameter. In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one light parameter is selected from the group consisting of infrared light parameters, visible light parameters, and ultraviolet light parameters. In some embodiments, each corresponding energy consumption location is defined based on global positioning system (GPS) data identifying the physical location of the at least one energy-consuming physical asset. In some embodiments, the at least one historical environmental characteristic is at least one of at least one light parameter, at least one acoustic parameter, at least one pressure parameter, at least one temperature parameter, at least one temperature parameter, at least one acceleration parameter, at least one magnetic parameter, at least one biological parameter, at least one chemical parameter, or at least one motion parameter. In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one light parameter is selected from the group consisting of infrared light parameters, visible light parameters, and ultraviolet light parameters. In some embodiments, each corresponding energy consumption location is defined based on global positioning system (GPS) data identifying the physical location of the at least one energy-consuming physical asset. In some embodiments, the at least one light parameter is selected from the group consisting of infrared light parameters, visible light parameters, and ultraviolet light parameters. In some embodiments, each corresponding energy consumption location is defined based on global positioning system (GPS) data identifying the physical location of the at least one energy-consuming physical asset. In some embodiments, each corresponding energy consumption location is defined based on global positioning system (GPS) data identifying the physical location of the at least one energy-consuming physical asset. In some embodiments, ​​​​​​​wherein the at least one sensor is one of i) a liquid pressure sensor, ii) a liquid flow sensor, i ii) a temperature sensor, iv) a gas flow sensor, v) a gas pressure sensor, or vi) an electrical system sensor.

[0007] In some embodiments, and optionally, in any combination of the embodiments described above or below, the step of the at least one processor associating each corresponding energy consumption location with the specific physical asset category further includes the at least one pr ocessor classifying one or more UOEs of the corresponding energy consumption location into the specific physical asset category. In some embodiments, and optionally, in any combination of the embodiments described above or below, classifying one or more UOEs of the corresponding energy consumption location into the specific physical asset category includes the at least one pro cessor applying at least one machine learning technique that has been trained to classify physical assets based at least in part on Standard Industrial Classification (SIC) codes. In some embodiments, and optionally, in any combination of the embodiments described above or below, the asset-specific historical energy consumption data and the asset-specific current energy consumption data are in units of kilowatt-hours (kwh). In some embodiments, and optionally, in any combination of the embodiments described above or below, the aforesaid at least one processor converts the asset-specific historical energy consumption data and the asset-specific current energy consumption data into corresponding kwh amounts.

[0008] In some embodiments, and optionally, in any combination of the embodiments described above or below,

[0009] ​​​In some embodiments, and optionally, in any combination of the embodiments described above or below, the present invention provides a typical innovative system. This system includes at least the following components, namely, at least one dedicated computer. This dedicated computer includes a non-transitory computer memory storing specific computer-executable program code, and at least one computer processor. When the specific program code is executed, this computer processor performs at least the following operations, that is, for an aggregate of energy-consuming physical assets during a predetermined time period, i) receiving asset-specific historical data and, ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor or both of them. The asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operation characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data. The operations include, for each corresponding physical asset category, determining a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, determining an adjusted failure loss value per physical asset for each corresponding physical asset category based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, determining a corresponding average current energy consumption value per physical asset for each corresponding physical asset category based at least in part on the asset-specific current energy consumption data, and associating each corresponding energy consumption location representing at least one energy-consuming physical asset of the aggregate of energy-consuming physical assets with a specific physical asset category 、i) receiving asset-specific historical data and, ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor or both of them. The asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operation characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data. The operations include, for each corresponding physical asset category, determining a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, determining an adjusted failure loss value per physical asset for each corresponding physical asset category based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, determining a corresponding average current energy consumption value per physical asset for each corresponding physical asset category based at least in part on the asset-specific current energy consumption data, and associating each corresponding energy consumption location representing at least one energy-consuming physical asset of the aggregate of energy-consuming physical assets with a specific physical asset category including 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operation characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data. The operations include, for each corresponding physical asset category, determining a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, determining an adjusted failure loss value per physical asset for each corresponding physical asset category based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, determining a corresponding average current energy consumption value per physical asset for each corresponding physical asset category based at least in part on the asset-specific current energy consumption data, and associating each corresponding energy consumption location representing at least one energy-consuming physical asset of the aggregate of energy-consuming physical assets with a specific physical asset category 、i) receiving asset-specific historical data and, ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor or both of them. The asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operation characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data. The operations include, for each corresponding physical asset category, determining a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, determining an adjusted failure loss value per physical asset for each corresponding physical asset category based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, determining a corresponding average current energy consumption value per physical asset for each corresponding physical asset category based at least in part on the asset-specific current energy consumption data, and associating each corresponding energy consumption location representing at least one energy-consuming physical asset of the aggregate of energy-consuming physical assets with a specific physical asset category or both of them. The asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operation characteristic, 3) at least one first asset-specific historical environmental characteristic, and the operation in question, and for each corresponding energy consumption location, i) the number of at least one energy-consuming physical asset in the set of energy-consuming physical assets in each corresponding physical asset category associated with the corresponding energy consumption location and ii) at least partially based on the corresponding average current energy consumption value per physical asset for each corresponding physical asset category, an operation of determining a specific usage-based failure insurance premium value, and based at least partially on the specific usage-based failure insurance premium value of the corresponding energy consumption location, i) at least one service provider that provides services to the at least one energy-consuming physical asset, ii) at least one electronic device of at least one entity associated with the at least one energy-consuming physical asset, iii) at least one sensor, or iv) at least one warning to at least one of the at least one energy-consuming physical assets configured to perform an operation of causing the at least one electronic warning to i) request a new usage-based failure insurance premium value or a change in the usage-based failure insurance premium value with respect to the location-specific level of energy usage of the at least one energy-consuming physical asset, ii) cause at least one user associated with the at least one energy-consuming physical asset to change the level of energy usage of the at least one energy-consuming physical asset, iii) instruct the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset, or iv) adjust at least one environmental characteristic of the at least one energy-consuming physical asset ​​​​​​​​​​​​​​​commanding at least one user, and v) commanding the at least one user to adjust at least one of the sensor operations, at least one of which is configured to affect at least one of these. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] These features and further features will become apparent with reference to the following description and drawings. Here wherein, throughout several of the figures, the same structure is referenced by the same numerals. The drawings shown are not necessarily to scale, instead, emphasis is generally placed when illustrating the principles of the present invention. Further, some functions may be exaggerated to show the details of a particular component . Therefore, the specific structural and functional details disclosed herein should not be construed as limiting, but rather as a representative basis for teaching those skilled in the art to variously utilize the present invention should be construed. to be.

[0011]

Figure 1

Figure 2

Figure 3A

Figure 3B

Figure 4

Figure 5

Figure 6

Figure 7

Best Mode for Carrying Out the Invention

[0012] Although detailed embodiments of the present invention are disclosed herein, it should be understood that these disclosed embodiments are merely examples of the present invention that can be embodied in various forms. In addition, each of the plurality of examples provided in connection with the various embodiments of the present invention is intended to be illustrative and not limiting. Any modifications and further improvements of the inventive features exemplified herein, as well as additional applications of the principles of the present invention exemplified herein, are also considered to be within the scope of the present invention. It should be understood that each of the plurality of examples provided in connection with the various embodiments of the present invention is intended to be illustrative and not limiting. Any modifications and further improvements of the inventive features exemplified herein, as well as additional applications of the principles of the present invention exemplified herein, are also considered to be within the scope of the present invention. It should be understood that each of the plurality of examples provided in connection with the various embodiments of the present invention is intended to be illustrative and not limiting. Any modifications and further improvements of the inventive features exemplified herein, as well as additional applications of the principles of the present invention exemplified herein, are also considered to be within the scope of the present invention. Any modifications and further improvements of the inventive features exemplified herein, as well as additional applications of the principles of the present invention exemplified herein, are also considered to be within the scope of the present invention. Any modifications and further improvements of the inventive features exemplified herein, as well as additional applications of the principles of the present invention exemplified herein, are also considered to be within the scope of the present invention. Any modifications and further improvements of the inventive features exemplified herein, as well as additional applications of the principles of the present invention exemplified herein, are also considered to be within the scope of the present invention.

[0013] Throughout this specification and the claims, the following terms have the meanings explicitly associated herewith unless the context clearly indicates otherwise. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same embodiment, although they may. Further, the phrases "in other embodiments" and "in some other embodiments" as used herein do not necessarily refer to different embodiments, although they may. That is, as described below, the various embodiments of the present invention may be readily combined without departing from the scope or gist of the present invention. Throughout this specification and the claims, the following terms have the meanings explicitly associated herewith unless the context clearly indicates otherwise. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same embodiment, although they may. Further, the phrases "in other embodiments" and "in some other embodiments" as used herein do not necessarily refer to different embodiments, although they may. That is, as described below, the various embodiments of the present invention may be readily combined without departing from the scope or gist of the present invention. Throughout this specification and the claims, the following terms have the meanings explicitly associated herewith unless the context clearly indicates otherwise. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same embodiment, although they may. Further, the phrases "in other embodiments" and "in some other embodiments" as used herein do not necessarily refer to different embodiments, although they may. That is, as described below, the various embodiments of the present invention may be readily combined without departing from the scope or gist of the present invention. Throughout this specification and the claims, the following terms have the meanings explicitly associated herewith unless the context clearly indicates otherwise. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same embodiment, although they may. Further, the phrases "in other embodiments" and "in some other embodiments" as used herein do not necessarily refer to different embodiments, although they may. That is, as described below, the various embodiments of the present invention may be readily combined without departing from the scope or gist of the present invention. Throughout this specification and the claims, the following terms have the meanings explicitly associated herewith unless the context clearly indicates otherwise. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same embodiment, although they may. Further, the phrases "in other embodiments" and "in some other embodiments" as used herein do not necessarily refer to different embodiments, although they may. That is, as described below, the various embodiments of the present invention may be readily combined without departing from the scope or gist of the present invention. Throughout this specification and the claims, the following terms have the meanings explicitly associated herewith unless the context clearly indicates otherwise. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same embodiment, although they may. Further, the phrases "in other embodiments" and "in some other embodiments" as used herein do not necessarily refer to different embodiments, although they may. That is, as described below, the various embodiments of the present invention may be readily combined without departing from the scope or gist of the present invention. Throughout this specification and the claims, the following terms have the meanings explicitly associated herewith unless the context clearly indicates otherwise. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same embodiment, although they may. Further, the phrases "in other embodiments" and "in some other embodiments" as used herein do not necessarily refer to different embodiments, although they may. That is, as described below, the various embodiments of the present invention may be readily combined without departing from the scope or gist of the present invention. Throughout this specification and the claims, the following terms have the meanings explicitly associated herewith unless the context clearly indicates otherwise. As used herein, the phrases "in one embodiment" and "in some embodiments" do not necessarily refer to the same embodiment, although they may. Further, the phrases "in other embodiments" and "in some other embodiments" as used herein do not necessarily refer to different embodiments, although they may. That is, as described below, the various embodiments of the present invention may be readily combined without departing from the scope or gist of the present invention.

[0014] The term "based on" is not exclusive and allows for being based on additional factors not recited unless the context clearly indicates otherwise. In addition, throughout this specification, The term "based on" is not exclusive and allows for being based on additional factors not recited unless the context clearly indicates otherwise. In addition, throughout this specification, or, "one", "a", "one of", "that", "this", "said", and "the foregoing" include plural references. The meaning of "in" includes "in" and "on". It should be understood that at least one aspect / function of the various embodiments described herein can be performed in real time and / or dynamically. As used herein, the term

[0015] "real time" refers to the ability of one event / action to occur instantaneously or almost instantaneously when another event / action occurs. For example, "real-time processing", "real-time calculation", and "real-time execution" all relate to the performance of calculations during the actual time when the relevant physical process (e.g., a user interacting with an application on a mobile device) occurs, and the results of such calculations can be used to guide the physical process. As used herein, the term "runtime" corresponds to any behavior that is dynamically determined during the execution of a software application or at least a part of a software application. As used herein, the term "dynamically" means that an event and / or action can be triggered and / or occur without any human intervention. In some embodiments, the events and / or actions according to the present invention can be based on at least one predetermined periodicity, such as in real time and / or at one nanosecond, several nanoseconds, one millisecond, several milliseconds, one minute, several minutes, per hour, several hours, per day, several days, per week, per month, etc. In some embodiments, the innovative electronic system is in a distributed network environment

[0016]

[0017]

[0018]

[0018] An electronic mobile device (such as a smartphone, sensor, etc.) and a server communicate via a suitable data communication network (such as the Internet, etc.), and are associated with at least one suitable data communication protocol (such as IPX / SPX, X.25, AX.25, AppleTalk (registered trademark), TCP / IP (such as HTTP), etc.). In some embodiments, a plurality of simultaneous network participants (such as sensors, servers, device units etc.) can be at least 100 (such as 100 - 999 but not limited to these), at least 1,000 (such as 1,000 - 9,999 but not limited to these), at least 10,000 (such as 10,000 - 99,999 but not limited to these), at least 100,000 (such as 100,000 - 999,999 but not limited to these) , at least 1,000,000 (such as 1,000,000 - 9,999,999 but not limited to these), at least 10,000,000 (such as 10,000,000 - 99,999,999 but not limited to these), at least 100,000,000 (such as 100,000,000 - 999,999,999 but not limited to these), at least 1,000,000,000 (such as 1,000,000,000 - 10,0 00,000,000 but not limited to these), although not limited to these.

[0019] In some embodiments, an inventive specially programmed computing system having associated devices is in a distributed network environment, communicating via a suitable data communication network (such as the Internet, etc.), and at least one suitable data communication protocol (such as IPX / SPX, X.25, AX.25, AppleTalk (registered trademark), TCP / IP (such as HTTP), etc.). (For example, it is configured to operate in the use of IPX / SPX, X.25, AX.25, AppleTalk (registered trademark), T CP / IP (such as HTTP), etc.). Naturally enough, the embodiments described herein can, of course, be implemented using any suitable hardware and / or computer software language. In this regard, those skilled in the art are familiar with the type of computer hardware that can be used, the type of computer programming techniques that can be used (such as object-oriented programming), and the type of computer programming languages (such as C++, Objective-C, Swift, Java (registered trademark), Javascript, Python, Perl). The above examples are, of course, exemplary and not restrictive.

[0020] The material disclosed herein may be implemented in software or firmware or a combination of these, or as instructions stored on a machine-readable medium that can be read and executed by one or more processors. A machine-readable medium can include any medium and / or mechanism that stores or transmits information in a form readable by a machine (such as a computing device). For example, a machine-readable medium can include read-only memory (ROM), random access memory (RAM), magnetic disk storage media, optical storage media, flash memory devices, electrical, optical, acoustic or other forms of propagated signals (such as carrier waves, infrared signals, digital signals, etc.).

[0021] In other forms, a non-transitory article such as a non-transitory computer-readable medium can be used in conjunction with any of the above-described or other examples, except when it itself contains a It can be done. This includes the element other than the signal itself that can temporarily hold data in a "transient" manner such as in RAM or the like.

[0022] As used herein, the terms "computer engine" and "engine" identify at least one software component that is designed / programmed / configured to manage / control other software (such as libraries, software development kits (SDKs), objects, etc.) and / or hardware, and / or a combination of at least one software component and at least one hardware component. Examples of hardware elements can include processors, microprocessors, circuits, circuit elements (such as transistors, resistors, capacitors, inductors, etc.), integrated circuits, application specific integrated circuits (ASICs), programmable logic devices (PLDs), digital signal processors (DSPs), field programmable gate arrays (FPGAs), logic gates, registers, semiconductor devices, chips, microchips, chip sets, etc. In some embodiments, one or more processors can be implemented as complex instruction set computer (CISC) or reduced instruction set computer (RISC) processors, x86 instruction set compatible processors, multi-core, or any other microprocessor or central processing unit (CPU). In various implementation examples, one or more processors can be, for example, dual-core processors, dual-core mobile processors, etc.

[0023]

[0024] Examples of software can include software components, programs, applications, Computer programs, application programs, system programs, machine programs Operating system software, middleware, firmware, software Modules, routines, subroutines, functions, methods, procedures Software interfaces, application program interfaces (APIs ), instruction sets, calculation codes, computer codes, code segments, computer code Segments, words, values, symbols, or any combination thereof. Whether an embodiment is implemented using hardware elements and / or software elements can depend on any number of factors such as desired calculation speed, power level, heat tolerance, processing cycle budget, input data speed, output data speed, memory resources, data bus speed, and other design or

[0025] In one example implementation, a multiprocessor system includes a plurality of processor chips, each processor chip including at least one I / O component designed to be directly connected to a photonic component connected to at least one I / O device. In some embodiments, the I / O device can be a standard interface such as a Peripheral Component Interconnect Express (PCIe), Universal Serial Bus (USB), Ethernet (registered trademark), Infiniband (registered trademark). In some embodiments,

[0026] the I / O device can include a storage device. It may include on - chip and off - chip memory. The off - chip memory can be shared by more than one of the processor chips. The off - chip memory can be directly connected to one processor chip and shared with other processor chips using a processor - to - processor approach implemented with a global memory architecture. The multi - processor system may also include caches and multiple processor chips. Each processor chip includes at least one I / O component. The I / O component is designed to be directly connected to a photonic component that communicates with one or more other processor chips. At least one I / O component of at least one processor chip can be configured to use a directory - based cache coherence protocol. In some embodiments, at least one of the caches of the processor chips can be configured to store directory information. In some embodiments, the off - chip memory may include DRAM. In some embodiments, the directory information can be stored in the off - chip memory and in at least one on - chip cache of the processor chips. In some embodiments, the multi - processor system further includes a directory subsystem configured to separate off - chip memory data and directory information on two different off - chip memories. In some embodiments, the multi - processor system further has a part of a subsystem implemented on a high - performance chip that is part of a 3D DRAM memory stack. The off - chip memory can be shared by more than one of the processor chips. The off - chip memory can be directly connected to one processor chip and shared with other processor chips using a processor - to - processor approach implemented with a global memory architecture. The multi - processor system may also include caches and multiple processor chips. Each processor chip includes at least one I / O component. The I / O component is designed to be directly connected to a photonic component that communicates with one or more other processor chips. At least one I / O component of at least one processor chip can be configured to use a directory - based cache coherence protocol. In some embodiments, at least one of the caches of the processor chips can be configured to store directory information. In some embodiments, the off - chip memory may include DRAM. In some embodiments, the directory information can be stored in the off - chip memory and in at least one on - chip cache of the processor chips. In some embodiments, the multi - processor system further includes a directory subsystem configured to separate off - chip memory data and directory information on two different off - chip memories. In some embodiments, the multi - processor system further has a part of a subsystem implemented on a high - performance chip that is part of a 3D DRAM memory stack. The off - chip memory can be shared by more than one of the processor chips. The off - chip memory can be directly connected to one processor chip and shared with other processor chips using a processor - to - processor approach implemented with a global memory architecture. The multi - processor system may also include caches and multiple processor chips. Each processor chip includes at least one I / O component. The I / O component is designed to be directly connected to a photonic component that communicates with one or more other processor chips. At least one I / O component of at least one processor chip can be configured to use a directory - based cache coherence protocol. In some embodiments, at least one of the caches of the processor chips can be configured to store directory information. In some embodiments, the off - chip memory may include DRAM. In some embodiments, the directory information can be stored in the off - chip memory and in at least one on - chip cache of the processor chips. In some embodiments, the multi - processor

[0027] system further includes a directory subsystem configured to separate off - chip memory data and directory information on two different off - chip memories. In some embodiments, the multi - processor system further has a part of a subsystem implemented on a high - performance chip that is part of a 3D DRAM memory stack. may include a configured directory subsystem. In some embodiments, the multi- processor system may further include a directory subsystem configured to support a varying number of sharers per memory block. may include a configured directory subsystem. In some embodiments, the multi- processor system may further include a directory subsystem configured to support a varying number of sharers per memory block using caching. may include a configured directory subsystem. In some embodiments, the multiprocessor system may further include a directory subsystem configured to support a varying number of sharers per memory block using hashing to entries having storage for different numbers of pointers to the sharers. In some embodiments, the multiprocessor system may further include a directory subsystem configured to use hashing to reduce storage allocated to memory blocks having zero sharers. In some embodiments, the multiprocessor system may further include a directory subsystem configured to use hashing to reduce storage allocated to memory blocks having zero sharers. In some embodiments, the multiprocessor system may further include a directory subsystem configured to use hashing to reduce storage allocated to memory blocks having zero sharers. subsystem.

[0028] One or more aspects of at least one embodiment can be implemented by representative instructions stored on a machine-readable medium. The instructions, when read by a machine, cause the machine to create logic in various logic within a processor that performs the techniques described herein. The representation, known as an “IP core,” is stored on a tangible machine-readable medium and is provided to various customers or manufacturing facilities that actually load the logic or processor into a manufacturing machine that makes the logic or processor. When read by a machine, the instructions cause the machine to create logic in various logic within a processor that performs the techniques described herein. The representation, known as an “IP core,” is stored on a tangible machine-readable medium and is provided to various customers or manufacturing facilities that actually load the logic or processor into a manufacturing machine that makes the logic or processor. When read by a machine, the instructions cause the machine to create logic in various logic within a processor that performs the techniques described herein. The representation, known as an “IP core,” is stored on a tangible machine-readable medium and is provided to various customers or manufacturing facilities that actually load the logic or processor into a manufacturing machine that makes the logic or processor. The representation, known as an “IP core,” is stored on a tangible machine-readable medium and is provided to various customers or manufacturing facilities that actually load the logic or processor into a manufacturing machine that makes the logic or processor. The representation, known as an “IP core,” is stored on a tangible machine-readable medium and is provided to various customers or manufacturing facilities that actually load the logic or processor into a manufacturing machine that makes the logic or processor. and supplied.

[0029] FIG. 1 shows a typical sensor 20. Many of them can be configured to form a typical sensor network. In some embodiments, the typical sensor 20 has various sensors. It may be sized about that of a quarter, or even smaller. This is because sensor sizes are now in the millimeter range. In some embodiments, sensor 20 may include power supply 22, logic circuit / microprocessor 24, storage device 2 5, transmitter (or transceiver) 26, communication coupler 28 coupled to transmitter 26, and sensor element 30. In some embodiments, the sensor may be unpowered or powered, and the power may be drawn from a reader or other power source.

[0030] In some embodiments, power supply 22 provides power to sensor 20. For example, power supply 22 may include a continuous power supply provided by an external power source, such as by a battery, a solar cell, and / or a connection to a power line. By way of example, storage device 25 may include any computer-readable medium, such as volatile and / or non-volatile media, removable and / or non-removable media, for storing computer data in a permanent or semi-permanent form, and may be implemented by any data storage technique. In some embodiments, storage device 25 can store data in a form that can be sampled or converted into a form storable on a computer-readable medium.

[0031] In some embodiments, a typical transmitter 26 may be configured to only transmit data signals. In some embodiments, transmitter 26 is configured to both receive and transmit data signals (transceiver). In some embodiments, as referred to herein, a "data signal" may be, for example, for storage, transfer, combination, comparison, and / or other operations. It may include current signals, voltage signals, magnetic signals, and / or optical signals in any possible form without limitation. In some embodiments, the transmitter 26 uses a communication coupler 28 for central computing devices Or central stations, one or more device units, and / or optionally other sensors Wireless, wired, infrared, optical, and / or other communication techniques for the purpose of communicating with. In some embodiments, the communication coupler 28 may include an antenna for wireless communication, a connection for wired communication Part, and / or an optical port for optical communication.

[0032] In some embodiments, a typical sensor 20 is, for example, an application-specific integrated circuit ( ASIC) and a hardware logic circuit such as programmable logic, or A microcomputer or microcontroller including, for example, a programmable microprocessor, such as Any type of data processing capacity, such as a computing device. In some embodiments, the embodiment of the sensor 20 shown in FIG. 1 may include the data processing capacity provided by the microprocessor 24. In some embodiments, The microprocessor 24 may include memory, processing, interface resources, a controller And a counter. In some embodiments, the microprocessor 24 may also Include one or more programs stored in memory to operate the sensor 20. When an embodiment uses a hardware logic circuit, the logic circuit generally includes a logic structure for operating the sensor 20.

[0033] In some embodiments, the sensor 20 may include one or more sensor elements 30. This sensor element 30 can be configured to detect at least one of the parameters of the environment in which sensors associated with one or more device units are disposed, and at least one operating characteristic of at least one of the one or more associated device units. In some embodiments, for example, without any limitation, a typical sensor element 30 can detect at least one parameter from the group of parameters of light, sound, pressure, temperature, heat, acceleration, magnetism, biology, chemistry, and motion. In some embodiments, the light parameters can include at least one from the group consisting of infrared light, visible light, and ultraviolet light parameters. For example, the sensor element 30 can include, without limitation, a light sensor that detects a certain level of light or a change in light level, a temperature sensor that detects temperature, an acoustic sensor that detects sound, and / or a motion sensor that detects motion. In some embodiments, the sensor element 30 can include, without limitation, a digital image capture device such as a CCD or CMOS imager that captures data related to infrared light, visible light, and / or ultraviolet light. In some embodiments, a typical sensor element 30 can be configured to output a data signal representative of at least one detection state. In some embodiments, the sensor 20 can automatically acquire data related to the parameters of the sensor environment and transmit the data to a central computing device. For example, a sensor element 30 in the form of an acoustic sensor can acquire the level and frequency of sound and transmit the data related to the level and frequency together with a time track using a transmitter 26 and a communication coupler 28. In some embodiments, for example, without any limitation, a typical sensor element 30 can detect at least one parameter from the group of parameters of light, sound, pressure, temperature, heat, acceleration, magnetism, biology, chemistry, and motion. In some embodiments, for example, without any limitation, a typical sensor element 30 can detect at least one parameter from the group of parameters of light, sound, pressure, temperature, heat, acceleration, magnetism, biology, chemistry, and motion. In some embodiments, for example, without any limitation, a typical sensor element 30 can detect at least one parameter from the group of parameters of light, sound, pressure, temperature, heat, acceleration, magnetism, biology, chemistry, and motion. In some embodiments, for example, without any limitation, a typical sensor element 30 can detect at least one parameter from the group of parameters of light, sound, pressure, temperature, heat, acceleration, magnetism, biology, chemistry, and motion. In some embodiments, the light parameters can include at least one from the group consisting of infrared light, visible light, and ultraviolet light parameters. For example, the sensor element 30 can include, without limitation, a light sensor that detects a certain level of light or a change in light level, a temperature sensor that detects temperature, an acoustic sensor that detects sound, and / or a motion sensor that detects motion. In some embodiments, the light parameters can include at least one from the group consisting of infrared light, visible light, and ultraviolet light parameters. For example, the sensor element 30 can include, without limitation, a light sensor that detects a certain level of light or a change in light level, a temperature sensor that detects temperature, an acoustic sensor that detects sound, and / or a motion sensor that detects motion. In some embodiments, the light parameters can include at least one from the group consisting of infrared light, visible light, and ultraviolet light parameters. For example, the sensor element 30 can include, without limitation, a light sensor that detects a certain level of light or a change in light level, a temperature sensor that detects temperature, an acoustic sensor that detects sound, and / or a motion sensor that detects motion. In some embodiments, the light parameters can include at least one from the group consisting of infrared light, visible light, and ultraviolet light parameters. For example, the sensor element 30 can include, without limitation, a light sensor that detects a certain level of light or a change in light level, a temperature sensor that detects temperature, an acoustic sensor that detects sound, and / or a motion sensor that detects motion. In some embodiments, the light parameters can include at least one from the group consisting of infrared light, visible light, and ultraviolet light parameters. For example, the sensor element 30 can include, without limitation, a light sensor that detects a certain level of light or a change in light level, a temperature sensor that detects temperature, an acoustic sensor that detects sound, and / or a motion sensor that detects motion. In some embodiments, the light parameters can include at least one from the group consisting of infrared light, visible light, and ultraviolet light parameters. For example, the sensor element 30 can include, without limitation, a light sensor that detects a certain level of light or a change in light level, a temperature sensor that detects temperature, an acoustic sensor that detects sound, and / or a motion sensor that detects motion.

[0034] In some embodiments, a typical sensor element 30 can be configured to output a data signal representative of at least one detection state. In some embodiments, a typical sensor element 30 can be configured to output a data signal representative of at least one detection state. In some embodiments, the sensor 20 can automatically acquire data related to the parameters of the sensor environment and transmit the data to a central computing device. In some embodiments, the sensor 20 can automatically acquire data related to the parameters of the sensor environment and transmit the data to a central computing device. For example, a sensor element 30 in the form of an acoustic sensor can acquire the level and frequency of sound and transmit the data related to the level and frequency together with a time track using a transmitter 26 and a communication coupler 28. For example, a sensor element 30 in the form of an acoustic sensor can acquire the level and frequency of sound and transmit the data related to the level and frequency together with a time track using a transmitter 26 and a communication coupler 28. In embodiments, acquisition may be real-time, continuous, intermittent, sporadic, occasional, and on-demand. In some embodiments, the time track can be any time-based. The check can be provided elsewhere, such as on the device receiving the sensor data.

[0035] By way of further example and without limitation, the sensor element 30 may be periodically, such as once per second. An optical device that captures a visual image and transmits data related to the visual image along with a time track. In some embodiments, the sensor element 30 may be in the form of a digital camera. The temperature change over a set temperature interval (e.g. 2 seconds, 5 seconds, 10 seconds, etc.) A temperature sensor that can detect and transmit every two degrees of temperature change along with the time it occurred. The above examples may take the form of a series of acoustic detections, from continuous to two-degree Illustrate the temperature change to the base each time it occurs.

[0036] In some embodiments, the sensor element 30 may also include, for example and without limitation, Also senses the operating parameters of the sensor 20 itself, such as its power level or its radio signal strength. In some embodiments, data related to the sensed parameters may be The sensor data including the sensor data is transmitted in any signal form via a transmitter 26 and a communication coupler 28. The sensor 20 transmits the signal to a receiver, which can receive the signal from other sensors 20, a central computing device, or other The sensor data may be a device, a sensor array, or any other data receiver. This may include the time and / or date the data was obtained.

[0037] In some embodiments, the sensor 20 is associated with a unique identifier. The separator can be made operable to communicate in association with the detected parameters In some embodiments, the sensor 20 can include a configuration for determining its location by a global positioning system (GPS), by triangulation based on known points, or by communication with other sensors In some embodiments, the location of the sensor 20 can be a pre-established known parameter. Similarly, the identification of the location can be associated with data derived from and / or transferred to the sensor In some embodiments, a typical sensor 20 can be configured, alone and / or in a group of suitable sensors, to accomplish a range of tasks including high-level tasks In some embodiments, typical tasks can include operations such as general information collection, security monitoring, industrial monitoring, biomedical monitoring, and other similar tasks As used herein, the terms "monitoring" and "control" and their synonyms and equivalents include, without limitation, tasks such as sending commands to adjust the operating behavior of one or more associated equipment units

[0038] In some embodiments, a typical sensor 20 and similarly suitable sensors can be placed inside a building (e.g., a house, an office, an industrial factory, etc.) For example, location-specific sensor data generated by a typical sensor 20 and similarly suitable sensors can indicate specific operating conditions and / or environmental conditions related to the operation of one or more UOEs located inside and / or outside the associated building and / or a set of buildings For example, location-specific sensor data can include the time when various lights are on, the light intensity setting, general electricity consumption, electricity consumption per UOE In some embodiments, typical sensor 20 and similarly suitable sensors can be placed inside a building (e.g., a house, an office, an industrial factory, etc.) As used herein, the terms "monitoring" and "control" and their synonyms and equivalents include, without limitation, tasks such as sending commands to adjust the operating behavior of one or more associated equipment units In some embodiments, typical sensor 20 and similarly suitable sensors can be placed inside a building (e.g., a house, an office, an industrial factory, etc.) For example, location-specific sensor data generated by a typical sensor 20 and similarly suitable sensors can indicate specific operating conditions and / or environmental conditions related to the operation of one or more UOEs located inside and / or outside the associated building and / or a set of buildings

[0039] In some embodiments, a typical sensor 20 and similarly suitable sensors can be placed inside a building (e.g., a house, an office, an industrial factory, etc.) For example, location-specific sensor data generated by a typical sensor 20 and similarly suitable sensors can indicate specific operating conditions and / or environmental conditions related to the operation of one or more UOEs located inside and / or outside the associated building and / or a set of buildings For example, location-specific sensor data generated by a typical sensor 20 and similarly suitable sensors can indicate specific operating conditions and / or environmental conditions related to the operation of one or more UOEs located inside and / or outside the associated building and / or a set of buildings For example, location-specific sensor data generated by a typical sensor 20 and similarly suitable sensors can indicate specific operating conditions and / or environmental conditions related to the operation of one or more UOEs located inside and / or outside the associated building and / or a set of buildings For example, location-specific sensor data generated by a typical sensor 20 and similarly suitable sensors can indicate specific operating conditions and / or environmental conditions related to the operation of one or more UOEs located inside and / or outside the associated building and / or a set of buildings the time when various lights are on, the light intensity setting, general electricity consumption, electricity consumption per UOE Data related to general water consumption, water consumption per UOE, general natural gas consumption, and natural gas consumption per UOE can be included without limitation. For example, typical sensors 20 and similar suitable sensors may be one or more of the following types (but are not limited thereto). i) Liquid (e.g., water) pressure sensor: Detect the liquid pressure (e.g., water pressure) at various locations within the structure. For example, the water pressure sensor may be placed at any location inside or outside the structure, and thus can provide information related to the stress caused in the piping system of the structure (including sewer, water supply, HVAC system, household appliances, and automatic fire fighting system). ii) Liquid (e.g., water) flow sensor: Detect the amount and / or velocity of the fluid (e.g., water) flowing through a selected point in the piping system (including sewer, water supply, HVAC system, household appliances, and automatic fire fighting system). For example, the water flow sensor may be placed at any location inside or outside the structure, and thus can provide information related to the amount of water routed to the structure, specifically, how much water that part of the structure is receiving accurately (or approximately). iii) Electrical system sensor: The electrical system sensor detects the operating parameters of the electrical system of the structure. Readings from the electrical system sensor can be used to determine at least one of 1) whether the voltage is (continuously) too high or too low, 2) whether the voltage frequently drops and / or spikes, 3) the current flowing through the electrical system, 4) the energy usage level and the time of day, etc., without limitation. iv) Temperature sensor, v) Gas flow sensor, or vi) Gas pressure sensor.

[0040] ​​​​​​​​​ FIG. 2 is a block diagram of a typical computing architecture 200 suitable for implementing at least some embodiments of the present invention. For example, a typical network server 201 may include at least one central processing unit (CPU) 202 and one or more databases or data storage devices 203. The network server 201 can be configured in many different ways. In some embodiments, a typical network server 201 may be well as a stand-alone computer, or alternatively, the functions of a typical network server 201 may be distributed across a number of computing systems and architectures. For example, a typical network server 201 may be configured in a distributed architecture where the database and processors are housed in separate units and / or locations. The network server 201 may include at least one central processing unit (CPU) 202 and one or more databases or data storage devices 203. The network server 201 can be configured in many different ways. In some embodiments, a typical network server 201 may be well as a stand-alone computer, or alternatively, the functions of a typical network server 201 may be distributed across a number of computing systems and architectures. The network server 201 can be configured in many different ways. In some embodiments, a typical network server 201 may be well as a stand-alone computer, or alternatively, the functions of a typical network server 201 may be distributed across a number of computing systems and architectures. For example, a typical network server 201 may be configured in a distributed architecture where the database and processors are housed in separate units and / or locations. The network server 201 can be configured in many different ways. In some embodiments, a typical network server 201 may be well as a stand-alone computer, or alternatively, the functions of a typical network server 201 may be distributed across a number of computing systems and architectures. For example, a typical network server 201 may be configured in a distributed architecture where the database and processors are housed in separate units and / or locations. The network server 201 may include at least one central processing unit (CPU) 202 and one or more databases or data storage devices 203. The network server 201 can be configured in many different ways. The network server 201 can be configured in many different ways. In some embodiments, a typical network server 201 may be well as a stand-alone computer, or alternatively, the functions of a typical network server 201 may be distributed across a number of computing systems and architectures. For example, a typical network server 201 may be configured in a distributed architecture where the database and processors are housed in separate units and / or locations.

[0041] In some embodiments, a typical computing architecture 200 may be configured to utilize any wired and wireless types integrated into the network environment to exchange data between various sensors (1-n) 204, device units ("UOE") (1-n) 205, other servers / computer systems 209, and / or user devices 208 (e.g., computers, laptops, smartphones, etc.). In some embodiments, a typical network server 201 may be configured to exchange data between various sensors (1-n) 204, device units ("UOE") (1-n) 205, other servers / computer systems 209, and / or user devices 208 (e.g., computers, laptops, smartphones, etc.) using one or more communication protocols. The network server 201 may include at least one central processing unit (CPU) 202 and one or more databases or data storage devices 203. The network server 201 can be configured in many different ways. In some embodiments, a typical network server 201 may be well as a stand-alone computer, or alternatively, the functions of a typical network server 201 may be distributed across a number of computing systems and architectures. For example, a typical network server 201 may be configured in a distributed architecture where the database and processors are housed in separate units and / or locations. The network server 201 can be configured in many different ways. In some embodiments, a typical network server 201 may be well as a stand-alone computer, or alternatively, the functions of a typical network server 201 may be distributed across a number of computing systems and architectures. For example, a typical network server 201 may be configured in a distributed architecture where the database and processors are housed in separate units and / or locations. The network server 201 may include at least one central processing unit (CPU) 202 and one or more databases or data storage devices 203. The network server 201 can be configured in many different ways. In some embodiments, a typical network server 201 may be well as a stand-alone computer, or alternatively, the functions of a typical network server 201 may be distributed across a number of computing systems and architectures. For example, a typical network server 201 may be configured in a distributed architecture where the database and processors are housed in separate units and / or locations. The cores 206 and 207 can be configured / programmed for utilization. In some embodiments, typical communication protocols may include, but are not limited to, Ethernet, SAP®, SAS®, ATP, BLUETOOTH®, GSM®, TCP / IP, LAN, WAN, Wi-Fi, 802.11x, 3G, LTE, Near Field Communication (NFC), and any other similarly suitable communication protocols. In some embodiments, each member device of the typical computing architecture 200 may also have an associated IP address.

[0042] In some embodiments, at least one data storage device 203 may include a suitable combination of magnetic, optical, and / or semiconductor memory, such as RAM, ROM, flash drives, optical disks such as compact disks, and / or hard disks or drives. In some embodiments, the CPU 202 and the data storage device 203 may each be fully disposed within, for example, one computer or other computing device, or may be connected to each other by a communication medium such as a USB port, serial port cable, coaxial cable, Ethernet type cable, telephone line, wireless transceiver, or other similar wireless or wired medium, or a combination of the foregoing.

[0043] In some embodiments, the data storage device 203 is (i) programmed (e.g., computer program code and / or computer program) to be adapted to direct the CPU 202 to follow the processes described in detail below, particularly with a computer program product), and (ii) a database adapted to store information that can be used to store the information required by the program may be stored. In some embodiments the program may be stored, for example, in a compressed format, a non-compiled format, and / or an encrypted format, and may include computer program code. Execution of a series of instructions in the program causes the processor 202 to execute the process steps described herein, while hardwired circuitry can be used instead of or in combination with the software instructions for the purpose of implementing the processes of the present invention. That is, the embodiments of the present invention are not limited to any particular combination of hardware and software. In some embodiments, appropriate computer program code that can be executed by the network server 201 can be programmed to cause the network server 201 to perform a number of functions, such as, but not limited to, secure data processing functions and / or insurance contract management functions In some embodiments, as shown in FIG. 2, when executing a typical insurance contract management application a typical network server 201 can be part of one or more sensor-driven dynamic adjustable feedback loops that manage devices (e.g., UOE(1-n)205) based on location-specific energy usage levels. For example, as shown in FIG. 2, typical sensors (1-n)204 at least collect various environmental parameters and / or operating parameters related to typical UOE(1-n)205 and collect the sensor data and / or insurance contract management functions and / or insurance contract management functions can be programmed to perform.

[0044] In some embodiments, as shown in FIG. 2, when executing a typical insurance contract management application a typical network server 201 can be part of one or more sensor-driven dynamic adjustable feedback loops that manage devices (e.g., UOE(1-n)205) based on location-specific energy usage levels. For example, as shown in FIG. 2, a typical network server 201 can be part of one or more sensor-driven dynamic adjustable feedback loops that manage devices (e.g., UOE(1-n)205) based on location-specific energy usage levels. For example, as shown in FIG. 2, a typical network server 201 can be part of one or more sensor-driven dynamic adjustable feedback loops that manage devices (e.g., UOE(1-n)205) based on location-specific energy usage levels. For example, as shown in FIG. 2, a typical network server 201 can be part of one or more sensor-driven dynamic adjustable feedback loops that manage devices (e.g., UOE(1-n)205) based on location-specific energy usage levels. For example, as shown in FIG. 2, a typical network server 201 can be part of one or more sensor-driven dynamic adjustable feedback loops that manage devices (e.g., UOE(1-n)205) based on location-specific energy usage levels. For example, as shown in FIG. 2, , to a typical network server 201 via one or more communication media / protocols 206 and can be transmitted. In some embodiments, typical environmental pa rameters and / or operating parameters of the sensor data are related to the location-specific level of energy usage by a typical UOE(1~n) 205. In some embodiments, when executing a typical insurance contract management application, a typical network server 201 can utilize typical sensor data including the location-specific level of energy usage by a typical UOE(1~n) 205 to determine one or more data values related to asset failure estimation (asset failure estimation value).

[0045] In some embodiments, when executing a typical insurance contract management application based on at least one equipment failure estimation value for at least one specific UOE, a typical network server 201 can be programmed to determine insurance data for guaranteeing at least one specific UOE and / or one or more UOEs, whether or not controlled by the same entity. In some embodiments, the insurance data can include location-specific insurance premium data such as the current location-specific insurance premium and / or the change in the location-specific insurance premium relative to an existing insurance premium, but not limited to these. In some embodiments, a typical network server 201 can issue at least one electronic warning to i) one or more other server / computer systems 209 (e.g., the server / computer system of a service provider that provides services to one or more UOE(1 ~n) 205), ) ii) one or more various user electronic devices 208 (e.g., the electronic devices of the insured entity​ ) iii) One or more sensors (1~n) 204, iv) One or more typical UOEs (1~n) 205, or v) Any combination thereof may be programmed to cause generation for at least one of them.

[0046] In some embodiments, at least one electronic warning may be configured to provide information about at least a new premium and / or a change in premium. In some embodiments at least one electronic warning may be configured to cause at least one insurance company associated with at least one UOE related to the at least one electronic warning to affect the location-specific level of energy usage of the one or more UOEs. In some embodiments at least one electronic warning may include at least one instruction to adjust at least one of the operating parameters of at least one of the one or more sensors (1~n) 204 and at least one of the operating parameters of at least one of the one or more typical UOEs (1~n) and may be configured to collect sensor data regarding the location-specific level of energy usage of the one or more UOEs and affect at least one of the operating modes of at least one of the one or more UOEs.

[0047] In some embodiments, then, when executing a typical proprietary insurance contract management application a typical network server 201 may be configured to generate in real time an electronic operation warning that determines that the typical network server 2 01 has stopped receiving data from one or more sensors (1~n) 204.

[0048] In some embodiments, when executing a typical innovative insurance contract management application, a typical network server 201 applies one or more machine learning techniques detailed herein to received data (e.g., asset-specific history data, current energy consumption data, failure frequency, etc.) in real time, for example, to predictively generate warnings in real time, reduce the likelihood of equipment failure, reduce usage-based insurance premiums, etc., and is configured to achieve one or more of these without limitation. When executing a typical innovative insurance contract management application, a typical network server 201 applies one or more machine learning techniques detailed herein to received data (e.g., asset-specific history data, current energy consumption data, failure frequency, etc.) in real time, for example, to predictively generate warnings in real time, reduce the likelihood of equipment failure, reduce usage-based insurance premiums, etc., and is configured to achieve one or more of these without limitation. When executing a typical innovative insurance contract management application, a typical network server 201 applies one or more machine learning techniques detailed herein to received data (e.g., asset-specific history data, current energy consumption data, failure frequency, etc.) in real time, for example, to predictively generate warnings in real time, reduce the likelihood of equipment failure, reduce usage-based insurance premiums, etc., and is configured to achieve one or more of these without limitation. When executing a typical innovative insurance contract management application, a typical network server 201 applies one or more machine learning techniques detailed herein to received data (e.g., asset-specific history data, current energy consumption data, failure frequency, etc.) in real time, for example, to predictively generate warnings in real time, reduce the likelihood of equipment failure, reduce usage-based insurance premiums, etc., and is configured to achieve one or more of these without limitation. When executing a typical innovative insurance contract management application, a typical network server 201 applies one or more machine learning techniques detailed herein to received data (e.g., asset-specific history data, current energy consumption data, failure frequency, etc.) in real time, for example, to predictively generate warnings in real time, reduce the likelihood of equipment failure, reduce usage-based insurance premiums, etc., and is configured to achieve one or more of these without limitation. When executing a typical innovative insurance contract management application, a typical network server 201 applies one or more machine learning techniques detailed herein to received data (e.g., asset-specific history data, current energy consumption data, failure frequency, etc.) in real time, for example, to predictively generate warnings in real time, reduce the likelihood of equipment failure, reduce usage-based insurance premiums, etc., and is configured to achieve one or more of these without limitation.

[0049] FIGS. 3A and 3B are typical flowcharts of a typical innovative process for a typical insurance contract management application executed in a typical network server 201 shown in FIG. 2 according to at least some embodiments of the present invention. In some embodiments, a typical innovative process is related to determining, for example, without limitation, whether a given device or system will fail or be damaged and at least one of when such failure and / or damage is likely to occur, and determining energy usage-based insurance premium data that can be utilized in a typical sensor-driven dynamic adjustable feedback loop for managing a device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process can be applied at one or more physical locations or at any level having energy consumption metering or sensor records. In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). FIGS. 3A and 3B are typical flowcharts of a typical innovative process for a typical insurance contract management application executed in a typical network server 201 shown in FIG. 2 according to at least some embodiments of the present invention. In some embodiments, a typical innovative process is related to determining, for example, without limitation, whether a given device or system will fail or be damaged and at least one of when such failure and / or damage is likely to occur, and determining energy usage-based insurance premium data that can be utilized in a typical sensor-driven dynamic adjustable feedback loop for managing a device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process can be applied at one or more physical locations or at any level having energy consumption metering or sensor records. In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). FIGS. 3A and 3B are typical flowcharts of a typical innovative process for a typical insurance contract management application executed in a typical network server 201 shown in FIG. 2 according to at least some embodiments of the present invention. In some embodiments, a typical innovative process is related to determining, for example, without limitation, whether a given device or system will fail or be damaged and at least one of when such failure and / or damage is likely to occur, and determining energy usage-based insurance premium data that can be utilized in a typical sensor-driven dynamic adjustable feedback loop for managing a device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process can be applied at one or more physical locations or at any level having energy consumption metering or sensor records. In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process is related to determining, for example, without limitation, whether a given device or system will fail or be damaged and at least one of when such failure and / or damage is likely to occur, and determining energy usage-based insurance premium data that can be utilized in a typical sensor-driven dynamic adjustable feedback loop for managing a device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process can be applied at one or more physical locations or at any level having energy consumption metering or sensor records. In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process is related to determining, for example, without limitation, whether a given device or system will fail or be damaged and at least one of when such failure and / or damage is likely to occur, and determining energy usage-based insurance premium data that can be utilized in a typical sensor-driven dynamic adjustable feedback loop for managing a device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process can be applied at one or more physical locations or at any level having energy consumption metering or sensor records. In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process is related to determining, for example, without limitation, whether a given device or system will fail or be damaged and at least one of when such failure and / or damage is likely to occur, and determining energy usage-based insurance premium data that can be utilized in a typical sensor-driven dynamic adjustable feedback loop for managing a device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process can be applied at one or more physical locations or at any level having energy consumption metering or sensor records. In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process is related to determining, for example, without limitation, whether a given device or system will fail or be damaged and at least one of when such failure and / or damage is likely to occur, and determining energy usage-based insurance premium data that can be utilized in a typical sensor-driven dynamic adjustable feedback loop for managing a device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process can be applied at one or more physical locations or at any level having energy consumption metering or sensor records. In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process is related to determining, for example, without limitation, whether a given device or system will fail or be damaged and at least one of when such failure and / or damage is likely to occur, and determining energy usage-based insurance premium data that can be utilized in a typical sensor-driven dynamic adjustable feedback loop for managing a device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process can be applied at one or more physical locations or at any level having energy consumption metering or sensor records. In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process is related to determining, for example, without limitation, whether a given device or system will fail or be damaged and at least one of when such failure and / or damage is likely to occur, and determining energy usage-based insurance premium data that can be utilized in a typical sensor-driven dynamic adjustable feedback loop for managing a device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process can be applied at one or more physical locations or at any level having energy consumption metering or sensor records. In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process is related to determining, for example, without limitation, whether a given device or system will fail or be damaged and at least one of when such failure and / or damage is likely to occur, and determining energy usage-based insurance premium data that can be utilized in a typical sensor-driven dynamic adjustable feedback loop for managing a device (e.g., UOE(1-n)205). In some embodiments, a typical innovative process can be applied at one or more physical locations or at any level having energy consumption metering or sensor records. In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205). In some embodiments, a typical insurance contract management application can be configured / programmed to utilize energy usage-based insurance premium data to determine usage-based insurance premiums for a location, system, and / or device (e.g., UOE(1-n)205).

[0050] In FIGS. 3A and 3B, step 301 relates to energy consumption physical assets that can be the energy consumption physical composition (e.g., one or more UOEs). In some embodiments, typical physical compositions can be one or more geographical locations (e.g., an apartment), physical systems within the location (e.g., HVAC), and / or individual devices, such as an MRI machine, having a common function. For example, without limitation, the energy usage of each asset can be obtained from one or more demand meters and / or sensors mounted on the asset to measure energy usage data. In some embodiments, asset-level energy usage data is compiled over a specific historical period that is appropriate to collect a meaningful aggregate and short enough to represent future possible damages (exposures). For example, without limitation, for the purposes of this description, a period of 5 years is used without one limitation. In addition to energy consumption, step 301 collects standard asset characteristics for each asset environment. For example, its size, type of business, address, and / or other data are relevant to the asset size and / or operating characteristics. In step 302, claim data is collected that includes the same data as in step 301, but additionally includes asset-specific loss data about the failed location, device and / or system, cause of loss, and amount of loss. In step 303, the data sources developed in steps 301 and 302 are combined to calculate claim frequency (e.g., frequency of failure / defect) and claim severity (e.g., severity of failure / defect). For example, this can be, for example, as follows to collect a meaningful aggregate and short enough to represent future possible damages (exposures). For example, without limitation, for the purposes of this description, a period of 5 years is used without one limitation. In addition to energy consumption, step 301 collects standard asset characteristics for each asset environment. For example, its size, type of business, address, and / or other data are relevant to the asset size and / or operating characteristics. In step 302, claim data is collected that includes the same data as in step 301, but additionally includes asset-specific loss data about the failed location, device and / or system, cause of loss, and amount of loss. In step 303, the data sources developed in steps 301 and 302 are combined to calculate claim frequency (e.g., frequency of failure / defect) and claim severity (e.g., severity of failure / defect). For example, this can be, for example, as follows location, device and / or system, cause of loss, and amount of loss. In step 303, the data sources developed in steps 301 and 302 are combined to calculate claim frequency (e.g., frequency of failure / defect) and claim severity (e.g., severity of failure / defect). For example, this can be, for example, as follows location, device and / or system, cause of loss, and amount of loss. In step 303, the data sources developed in steps 301 and 302 are combined to calculate claim frequency (e.g., frequency of failure / defect) and claim severity (e.g., severity of failure / defect). For example, this can be, for example, as follows example, as follows example, this can be, for example, as follows It can be achieved by applying the following formulas (1) and (2).

Number

[0051] These calculations are performed on a previously identified data subset of the exposure and loss databases, and the claim frequency and severity for each subset are calculated. In some embodiments, these data categorizations are at least partially based on the nature of the business operations in the data collected. Other embodiments are based on physical systems such as, for example, HVAC, refrigeration, lighting, heating, cooling, etc. And still other embodiments can be based on specific equipment such as, for example, chillers, boilers, motors, engines, etc. The subsets can be defined for geographical regions, business types, sizes, and number of operating days. In some embodiments, as shown in the following formula (3), the claim frequency f and severity S are multiplied together, and the base loss cost R for each subset is calculated for property insurance. In some embodiments, these data categorizations are at least partially based on the nature of the business operations in the data collected. Other embodiments are based on physical systems such as, for example, HVAC, refrigeration, lighting, heating, cooling, etc. And still other embodiments can be based on specific equipment such as, for example, chillers, boilers, motors, engines, etc. The subsets can be defined for geographical regions, business types, sizes, and number of operating days. In some embodiments, as shown in the following formula (3), the claim frequency f and severity S are multiplied together, and the base loss cost R for each subset is calculated for property insurance. ー, boilers, motors, engines, etc. The subsets can be defined for geographical regions, business types, sizes, and number of operating days. In some embodiments, as shown in the following formula (3), the claim frequency f and severity S are multiplied together, and the base loss cost R for each subset is calculated for property insurance. In some embodiments, as shown in the following formula (3), the claim frequency f and severity S are multiplied together, and the base loss cost R for each subset is calculated for property insurance. In some embodiments, as shown in the following formula (3), the claim frequency f and severity S are multiplied together, and the base loss cost R for each subset is calculated for property insurance. In some embodiments, as shown in the following formula (3), the claim frequency f and severity S are multiplied together, and the base loss cost R for each subset is calculated for property insurance.

Number

[0052] In FIGS. 3A and 3B, step 304 shows that a typical insurance contract management application can be configured / programmed to adjust the base loss cost to include standard insurance-related business costs that include overhead, claim management, fees, and / or reinsurance resources. In some embodiments, a typical insurance contract management application calculates these costs via standard accounting procedures and ensures that the costs are sufficient to support executable business activities. In some embodiments, a typical insurance contract management application calculates these costs via standard accounting procedures and ensures that the costs are sufficient to support executable business activities. In some embodiments, a typical insurance contract management application calculates these costs via standard accounting procedures and ensures that the costs are sufficient to support executable business activities. In some embodiments, a typical insurance contract management application calculates these costs via standard accounting procedures and ensures that the costs are sufficient to support executable business activities. In addition to the base insurance premium loss cost. In some embodiments, the applicable fees and charges may vary depending on the subset group defined in step 303.

[0053] In some embodiments, a typical insurance contract management application executes a parallel process path starting from step 305 where energy usage data is generated for each asset. It can be configured / programmed to do so. In FIG. 3A, the energy usage data 305 is generated on any time basis such as real-time, continuous, intermittent, sporadic, occasional, and on-demand. In FIG. 3B, the energy usage data 305 is generated in real-time. For example, the actual / current energy usage of an asset can be obtained from one or more demand meters or from sensors installed on the asset to measure energy and / or usage. In some embodiments, this energy usage can relate to diesel fuel gallons, cubic feet of natural gas, kilowatt-hours, kilowatts, and / or other energy usage units without limitation. In step 306, a typical insurance contract management application can be configured / programmed to store energy usage data regarding the energy used over a specific period. This energy usage data can be received, for example, from typical sensors ( 1 - n) 204 (such as customer-installed energy meters), typical UOEs (1 - n) 205 ( such as the demand itself), and one or more electronic sources associated with one or more third parties. In some embodiments, a typical insurance contract management application represents the overall usage for a location, system, or separate device, so that energy usage data is generated for each asset. usage data is generated for each asset. - It can be configured / programmed to divide usage data into groups. In step 307, For each site in an aggregation, a typical insurance contract management application - can be configured / programmed to obtain energy usage data and store the energy usage data as an aggregation-level database. A typical insurance contract management application - can be configured / programmed to obtain site attributes along with the energy usage data. This attribute includes, without limitation, data related to the location, size, and / or business activities of the site. In step 308, a typical insurance contract management application - can be configured / programmed to convert or map the collected site and customer-level data into typical asset-level codes used to describe the property insurance risks used in steps 301 to 304. - This enables the energy usage data to be mapped / categorized based on the same subset criteria as those performed in steps 301 to 304. This mapping is used to convert both - the aggregation-level energy data from step 307 and the customer energy data for pricing in step 309. For example, the site address and postal code can be mapped to a predefined geographic area to model the asset risk. Also, the business activities routinely described in terms of the Standard Industrial Classification (SIC) code may require mapping to an asset risk occupancy code. This step ensures that the energy data can be mapped / categorized based on the same subset criteria as those performed in steps 3 01 to 304. - can be mapped / categorized based on the same subset criteria as those performed in steps 301 to 304. - This mapping is used to convert both the aggregation-level energy data from step 307 and the customer energy data for pricing in step 309. - This mapping is used to convert both the aggregation-level energy data from step 307 and the customer energy data for pricing in step 309. - For example, the site address and postal code can be mapped to a predefined geographic area to model the asset risk. Also, the business activities routinely described in terms of the Standard Industrial Classification (SIC) code may require mapping to an asset risk occupancy code. - This step ensures that the energy data can be mapped / categorized based on the same subset criteria as those performed in steps 301 to 304. - This step ensures that the energy data can be mapped / categorized based on the same subset criteria as those performed in steps 301 to 304. - This step ensures that the energy data can be mapped / categorized based on the same subset criteria as those performed in steps 301 to 304. - This step ensures that the energy data can be mapped / categorized based on the same subset criteria as those performed in steps 301 to 304.

[0054] In step 309, a typical insurance contract management application may compile a unique set of customer data mapped to class variables at the asset level (using the results of step 30 8) and energy consumption data, and be configured / programmed to determine an energy usage-based insurance premium for asset failure insurance. If multiple energy sources are being consumed at a site, a typical insurance contract management application may be configured / programmed to utilize at least one standard energy conversion factor to convert all energy consumption to kilowatt-hours.

[0055] In step 310, the data results from steps 304 and 308 are applied to the customer data input in step 30 9. A typical insurance contract management application may be configured / programmed to calculate a usage-based insurance premium from the following equation (4) for each asset-based customer listed in step 309. In some embodiments, a typical insurance contract management application may be configured / programmed to utilize other appropriate criteria. Thereafter, a typical insurance contract management application may be configured / programmed to determine sums and totals across specified subsets of criteria (e.g., region / size / business).

[0056] In step 310, each asset insurance premium P i is calculated from the product adjustment base cost and the α power of the quotient of the energy consumption E of the specific asset divided by the average energy consumption of the asset class. i

Equation

Number

[0057] The constant K is included to ensure that the total premium for a given business category or asset class remains constant with respect to α. When a given insurance contract results in a given amount of premium, this amount should not be changed by the choice of scaling factor. Further, from the perspective of insurance regulation, when the standard rate is approved by the state regulatory authority, the insurance contract for the premium should remain unchanged, i.e., independent of the scaling factor. The total business category or asset class insurance premium constant K can be calculated as follows. of. When a given insurance contract is signed to result in a given amount of premium, this amount should not be changed by the choice of scaling factor. Further, from the perspective of insurance regulation, when the standard rate is approved by the state regulatory authority, the insurance contract for the premium should remain unchanged, i.e., independent of the scaling factor. The total business category or asset class insurance premium constant K can be calculated as follows. should not. Further, from the perspective of insurance regulation, when the standard rate is approved by the state regulatory authority, the insurance contract for the premium should remain unchanged, i.e., independent of the scaling factor, and be maintained. The total business category or asset class insurance premium constant K can be calculated as follows. can be done.

Number

[0058] The scale factor α is selected by the insurance company. Its value is based on insurance data, engineering ring data, and the experience of a particular asset class being signed. This can vary for various reasons. For example, when α = 1, doubling the asset energy usage doubles the premium. This linearity can describe the possible insurance damage when the change in energy usage is directly related to the change in the number of devices or the operating time. However, for other cases it can vary. For example, when α = 1, doubling the asset energy usage doubles the premium. This linearity can describe the possible insurance damage when the change in energy usage is directly related to the change in the number of devices or the operating time. However, for other cases it can vary. For example, when α = 1, doubling the asset energy usage doubles the premium. This linearity can describe the possible insurance damage when the change in energy usage is directly related to the change in the number of devices or the operating time. However, for other cases it can vary. For example, when α = 1, doubling the asset energy usage doubles the premium. This linearity can describe the possible insurance damage when the change in energy usage is directly related to the change in the number of devices or the operating time. However, for other cases For example, insurance risk is not necessarily linear with respect to energy use. For example, if α=1 / 2, doubling energy use will not reduce insurance rates by approximately 40% ( This approach has several advantages over the previous approach. This could help customers replace their old units with larger, more energy-efficient items. In embodiments, different values can be used, and in fact, values of α>1 may be used. For example, high-value equipment may be appropriate for some asset classes because of its unique technology. The value of α chosen may reflect the high cost of capital expenditures, resulting in a high value of business interruption. Insurance company data on how class risk varies with energy consumption and reflecting on experience.

[0059] As an example of the exemplary inventive method described in Figures 3A and 3B, Figures 4-7 show exemplary How, for example, can an insurance policy management application run three typical Energy usage-based insurance is offered for a given geographic area for clients that fall into an asset class. This indicates whether the device can be configured / programmed to calculate the insurance premium.

[0060] In FIG. 4, at step 410, a typical policy administration application Electronically capture historical exposure data per asset class. Examples include equipment asset classes for retail locations, HVAC systems, and Magnetic Resonance Imaging (MRI) machines. In step 420, a typical policy administration application Electronically capture historical data regarding historical asset claims data for the collection. Step 4 In 30, a typical insurance contract management application calculates the base loss cost to dynamically combine the losses and exposure data from steps 410 and 420. In step 440, a typical insurance contract management application dynamically adjusts the base loss cost by a predetermined multiplier. The multiplier can be determined or calculated based at least in part on historical data describing various additional items such as, but not limited to, asset class characteristics, expenses, reinsurance, profit, etc.

[0061] In FIG. 5, at step 510, a typical insurance contract management application electronically obtains energy data from at least one of, for example, without limitation, (1) one or more demand meters, (2) one or more sensors, or (3) one or more electronic databases to generate energy consumption data for an insured asset aggregate for which a price is to be set. For example, at step 520, a typical insurance contract management application electronically determines the energy consumption data for four insureds for each of three asset classes. This data is compiled over a given period similar to that normally done to determine sufficient exposure and loss data for price setting of standard insurance products. At step 5 30, a typical insurance contract management application generates an average energy consumption statistic ( E bar) for each asset class across all insured asset classes for a particular insured aggregate i. E i bar) is generated.

[0062] In FIG. 6, at step 610, a typical insurance contract management application Map the set customer ID (e.g., retail store #1234) to its asset class. Step In 620, a typical insurance contract management application links each rated customer ID to its energy consumption and the asset class adjusted base loss cost calculated in step 440. In step 630, a typical insurance contract management application uses a table provided by an insurance company that includes a scale factor (α k ) for the asset class used in premium calculation.

[0063] In FIG. 7, in step 710, a typical insurance contract management application calculates the customer premium using tabular data and equations (4) and (5).

[0064] In some embodiments, a typical insurance contract management application can be configured / programmed to determine the total energy usage of a representative customer across all locations and all fuels. For example, a business may use natural gas for heating in addition to electricity consumption. In such a case, a typical insurance contract management application can be configured / programmed to add natural gas usage equivalent to electricity consumption using a specific conversion of, for example, 100 ft 3 of natural gas equivalent to 29.21 kwh.

[0065] In some embodiments, a typical insurance contract management application can be configured / programmed to utilize other kwh equivalent conversion factors for different fuels. In some embodiments, a typical insurance contract management application applies the energy conversion calculation across the customer's complete energy data set and applies the generated energy conversion data​​ configured / programmed to compile the data into a separate or integrated database with one or more other databases detailed herein. In some embodiments, a typical insurance contract management application may be configured / programmed to apply an adjusted equipment insurance pricing model to the energy consumption data of new insurance customers to support a typical innovative sensor-driven dynamic adjustable feedback loop that manages equipment (e.g., UOE(1-n)205) based on the asset-specific level of energy usage. For example, a typical insurance contract management application may be configured / programmed to map the name of a new customer and the total energy consumption (measured in kwh units) to an insurance business category. Subsequently, a typical insurance contract management application may be configured / programmed to determine the asset breakdown insurance premium for a new customer based at least in part on a combination of the corresponding rating information and the customer's energy usage for a separate contract. In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein).

[0066] In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical insurance contract management application may, in real time, use one or more machine learning techniques (e.g., neural networks, support vector machines, decision trees, random forests, boosting, nearest neighbor algorithms, naive Bayes, bagging, etc.) to classify assets based on, for example, at least one of a location, system, device, or one or more other suitable asset classification criteria / categories without limitation, where learning is possible or learning / training is possible (i.e., optionally, without the typical analysis detailed herein). For example, it can be configured / programmed to apply to at least one of the asset-specific history data or the asset-specific current energy consumption data without limitation.

[0067] In some embodiments, and optionally, in any combination of the embodiments described above or below, typical neural network techniques can be, without limitation, feedforward neural networks, radial basis function networks, recurrent neural networks, convolutional networks (e.g., U-net), or any other suitable network. One of In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical implementation of a neural network can be carried out as follows. i) Define a neural network architecture / model. ii) Transmit sensor data to a typical neural network model. iii) Gradually train a typical model. iv) Determine the accuracy for a specific number of time steps.

[0068] In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical trained neural network model can identify the neural network by at least a neural network topology, a series of activation functions, and connection weights. For example, a neural network ​​​​​​​​​​The topology can include the configuration of the nodes of the neural network and the connections between the nodes. In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical trained neural network model may also include other parameters including, but not limited to, bias values / functions, and / or aggregation functions. For example, the activation function of a node may be a step function, a sine function, a continuous or piecewise linear function, a sigmoid function, a hyperbolic tangent function, or other types of mathematical functions representing the threshold at which the node is activated. In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical aggregation function may be a mathematical function (e.g., sum, product, etc.) that combines input signals to a node. In some embodiments, and optionally, in any combination of the embodiments described above or below, the output of a typical aggregation function may be used as an input to a typical activation function. In some embodiments, and optionally, in any combination of the embodiments described above or below, the bias may be a constant value or a function that the aggregation function and / or activation function may use to increase or decrease the likelihood that a node is activated. In some embodiments, and optionally, in any combination of the embodiments described above or below, typical connection data for each connection in a typical neural network may include at least one of a node pair or a connection weight. For example, if a typical neural network includes a connection from node N1 to node N2, the connection

[0069] In some embodiments, and optionally, in any combination of the embodiments described above or below, each connection in a typical neural network may have typical connection data that includes at least one of a node pair or a connection weight. For example, if a typical neural network includes a connection from node N1 to node N2, the connection ​ Typical connection data for may include node pairs <N1, N2>. In some embodiments and optionally, in any combination of any of the embodiments described above or below, the connection weight may be a numerical quantity that affects whether and / or how to modify the output of N1 before it is input to N2. In an example of a current network, a node may have a connection to itself (e.g., the connection data may include the node pair <N1, N1>).

[0070] In some embodiments and optionally, in any combination of any of the embodiments described above or below, a typical trained neural network model may also include a species identifier (ID) and fitness data. For example, each species ID may indicate which of a plurality of species (e.g., asset classification categories) a typical model belongs to. For example, the fitness data may indicate how well a typical trained neural network model models an input asset energy consumption dataset and / or an asset failure loss dataset. For example, the fitness data may include a fitness value determined based on evaluating a fitness function for the model. For example, a typical fitness function may be an objective function based on the frequency and / or magnitude of errors generated by testing a typical trained neural network model on an input asset energy consumption dataset and / or an asset failure loss dataset. As a simple example, each of the input asset energy Each of the consumption dataset and / or the asset failure loss dataset is represented by A and B, 2 columns, and a typical trained neural network model is assumed to output the predicted value B for the input value A. In this example, testing a typical trained neural network model would involve inputting 10 values of A each from the input asset energy consumption dataset and / or the asset failure loss data set, comparing the predicted value B with the corresponding actual value B from each of the input asset energy consumption dataset and / or the asset failure loss dataset, and determining whether and / or by how much the two predicted values B and the actual value B differ. By way of illustration, if a particular neural network accurately predicted the value B for 9 out of 10 rows, a typical fitness function could assign the corresponding model a fitness value of 9 / 10 = 0.9. It should be understood that the examples given so far are for illustrative purposes only and should not be considered limiting. In some aspects, a typical fitness function may be based on factors unrelated to the error frequency or error rate, such as the number of input nodes, node layers, hidden layers, connections, and computational complexity. In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical neural network model receives input asset energy - consumption and / or asset failure loss values at the input layer. In some embodiments and optionally, in any combination of the embodiments described above or below, a typical trained neural network model then passes those values through the connections

[0071] In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical neural network model receives input asset energy - consumption and / or asset failure loss values at the input layer. In some embodiments and optionally, in any combination of the embodiments described above or below, a typical trained neural network model then passes those values through the connections Propagate it to a specific layer through. In some embodiments, and optionally, in any combination of the embodiments described above or in any combination of the embodiments described below, each connection may include a numerical weighting value (e.g., a value between -1 and 1) that should be used to modify the initial value (e.g., propagation value = initial value * weight). In some embodiments, and optionally, in any combination of the embodiments described above or below, a plurality of nodes in a specific layer receive these propagation values as inputs. In some embodiments, and optionally, in any combination of the embodiments described above or below or in any combination of the embodiments described below, each node in a specific layer may include a function that combines the received input values (e.g., taking the sum of all received values). For example , each node may further include one or more activation functions that determine when one value is output to one of the multiple connections to the subsequent layer (e.g., if the combined input value is >0, output +1; if the combined input value is <0, output -1 ; if the combined input value is =0, output 0). Each node in a typical output layer may correspond to a predefined category for the input sensor values. For example, the combined input sensor values for each node in the output layer may determine the category determined for the input (e.g., the category for the output node with the largest combined input value). In some embodiments, and optionally, in any combination of the embodiments described above or below, in this way, a typical neural network structure can be used to determine, for example, one or more asset classification categories for an input asset energy consumption dataset and / or an asset failure loss dataset (e.g., the category for the output node with the largest combined input value). In some embodiments, and optionally, in any combination of the embodiments described above or below, in any combination of the embodiments described below, in this way, a typical neural network structure can be used to determine, for example, one or more asset classification categories for an input asset energy consumption dataset and / or an asset failure loss dataset such as, for example, an input asset energy consumption dataset and / or an asset failure loss dataset for one or more asset classification categories.

[0072] In some embodiments, and optionally, in any combination of the embodiments described above or below, a default value for initiation and / or a random value is given to the weight for the connection. In some embodiments, and optionally, in any combination of the embodiments described above or below, the sensor input is then provided to a typical neural network model through the input layer, and a category determined based on the values of the asset energy consumption and / or asset failure loss input (e.g., based on the highest combined input value at the nodes of the output layer) is observed and compared with the correctly labeled positive categories. In some embodiments, and optionally, in any combination of the embodiments described above or below, the weights for the connections are repeatedly modified until a typical neural network model correctly determines the correct category for all inputs or at least for all allowable portions of the inputs, resulting in a typical trained neural network model. For example, when a new input is received without a pre-determined correct category, a typical inventive computer-based system of the present invention can submit the input to a typical trained neural network model and be configured to determine the most likely category for the input. In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical neural network model further, in real time, for example, reduces the number of nodes, reduces the number of connections, reduces the file size, neural net In some embodiments, and optionally, in any combination of the embodiments described above or below, the weights for the connections are repeatedly modified until a typical neural network model correctly determines the correct category for all inputs or at least for all allowable portions of the inputs, resulting in a typical trained neural network model. For example, when a new input is received without a pre-determined correct category, a typical inventive computer-based system of the present invention can submit the input to a typical trained neural network model and be configured to determine the most likely category for the input. For example, when a new input is received without a pre-determined correct category, a typical inventive computer-based system of the present invention can submit the input to a typical trained neural network model and be configured to determine the most likely category for the input.

[0073] In some embodiments, and optionally, in any combination of the embodiments described above or below, a typical neural network model further, in real time, for example, reduces the number of nodes, reduces the number of connections, reduces the file size, neural net Reducing the file size of a file storing parameters that define a work model, or Optimization can be achieved by any combination of these, but not limited to these.

[0074] In some embodiments, and optionally, in any combination of the embodiments described above or below, the present invention provides a typical inventive computer-implemented method. This method at least includes at least one processor receiving, for a set of energy-consuming physical assets over a predetermined period of time, i) asset-specific historical data and ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor, or both, where the asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operating characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data, and the at least one processor determining, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and the at least one processor determining, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determining, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the method is that at least one processor, during a predetermined time, for a set of energy-consuming physical assets, i) receives asset-specific historical data and ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor, or both, where the asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operating characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data, and the at least one processor determines, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the method is that at least one processor, during a predetermined time, for a set of energy-consuming physical assets, i) receives asset-specific historical data and ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor, or both, where the asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operating characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data, and the at least one processor determines, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the method is that at least one processor, during a predetermined time, for a set of energy-consuming physical assets, i) receives asset-specific historical data and ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor, or both, where the asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operating characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data, and the at least one processor determines, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operating characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data, and the at least one processor determines, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the method is that at least one processor, during a predetermined time, for a set of energy-consuming physical assets, i) receives asset-specific historical data and ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor, or both, where the asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operating characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data, and the at least one processor determines, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the method is that at least one processor, during a predetermined time, for a set of energy-consuming physical assets, i) receives asset-specific historical data and ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor, or both, where the asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operating characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data, and the at least one processor determines, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the at least one processor determines, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the at least one processor determines, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the at least one processor determines, for each corresponding physical asset category, a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the at least one processor determines, for each corresponding physical asset category, an adjusted failure loss value per physical asset based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets where the at least one processor determines, for each corresponding physical asset category, a corresponding average current energy consumption value per physical asset based at least in part on the asset-specific current energy consumption data, and the at least one processor for the set of energy-consuming physical assets Each corresponding energy consumption location representing at least one energy-consuming physical asset of the body, associating with a specific physical asset category, and the at least one processor for each corresponding energy consumption location, i) the corresponding at least one of the aggregates of the energy-consuming physical assets in each of the physical asset categories associated with the corresponding energy consumption location the number of one energy-consuming physical asset, and ii) at least partially based on the corresponding average current energy consumption value per physical asset for each corresponding physical asset category, determining a specific usage-based failure insurance premium value, and the at least one processor, based at least partially on the specific usage-based failure insurance premium value of the corresponding energy consumption location, i) at least one service provider providing services to the at least one energy-consuming physical asset, ii) at least one electronic device of at least one entity associated with the at least one energy-consuming physical asset, iii) the at least one sensor, or iv) generating at least one warning for at least one of the at least one energy-consuming physical assets, and the at least one electronic warning, for the location-specific level of energy use of the at least one energy-consuming physical asset, i) requesting a new usage-based failure insurance premium value or a change in the usage-based failure insurance premium value, ii) causing at least one user associated with the at least one energy-consuming physical asset to change the level of energy use of the at least one energy-consuming physical asset, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset at least one service provider providing services to the at least one energy-consuming physical asset, ii) at least one electronic device of at least one entity associated with the at least one energy-consuming physical asset, iii) the at least one sensor, or iv) generating at least one warning for at least one of the at least one energy-consuming physical assets, and the at least one electronic device, iii) the at least one sensor, or iv) generating at least one warning for at least one of the at least one energy-consuming physical assets, and the at least one electronic device, iii) the at least one sensor, or iv) generating at least one warning for at least one of the at least one energy-consuming physical assets, and the at least one electronic warning, for the location-specific level of energy use of the at least one energy-consuming physical asset, i) requesting a new usage-based failure insurance premium value or a change in the usage-based failure insurance premium value, ii) causing at least one user associated with the at least one energy-consuming physical asset to change the level of energy use of the at least one energy-consuming physical asset, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset warning, for the location-specific level of energy use of the at least one energy-consuming physical asset, i) requesting a new usage-based failure insurance premium value or a change in the usage-based failure insurance premium value, ii) causing at least one user associated with the at least one energy-consuming physical asset to change the level of energy use of the at least one energy-consuming physical asset, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset user associated with the at least one energy-consuming physical asset to change the level of energy use of the at least one energy-consuming physical asset, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset user associated with the at least one energy-consuming physical asset to change the level of energy use of the at least one energy-consuming physical asset, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset user associated with the at least one energy-consuming physical asset to change the level of energy use of the at least one energy-consuming physical asset, iii) instructing the at least one user to adjust at least one operating characteristic of the at least one energy-consuming physical asset iv) adjusting at least one environmental characteristic of the at least one energy-consuming physical asset, v) instructing the at least one user to adjust at least one of the at least one sensor operations, and is configured to be affected by at least one of at least one of: instructing the at least one user to adjust at least one of the at least one energy-consuming physical asset.

[0075] In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one energy-consuming physical asset is a physical configuration including one or more unit of equipment (UOE). In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one historical environmental characteristic is at least one of at least one light parameter, at least one acoustic parameter, at least one pressure parameter, at least one temperature parameter, at least one temperature parameter, at least one acceleration parameter, at least one magnetic parameter, at least one biological parameter, at least one chemical parameter, or at least one motion parameter. In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one light parameter is selected from the group consisting of infrared light parameters, visible light parameters, and ultraviolet light parameters. In some embodiments, and optionally, in any combination of the embodiments described above or below, each corresponding energy consumption location has a global position that identifies the physical location of at least one energy-consuming physical asset. In some embodiments, and optionally, in any combination of the embodiments described above or below, the at least one light parameter is selected from the group consisting of infrared light parameters, visible light parameters, and ultraviolet light parameters. In some embodiments, and optionally, in any combination of the embodiments described above or below, each corresponding energy consumption location has a global position that identifies the physical location of at least one energy-consuming physical asset. In some embodiments, and optionally, in any combination of the embodiments described above or below, each corresponding energy consumption location has a global position that identifies the physical location of at least one energy-consuming physical asset. global position identifying the physical location of at least one energy-consuming physical asset, It is defined based on Global Navigation Satellite System (GPS) data. In some embodiments, the at least one sensor is one of: i) a liquid pressure sensor, ii) a liquid flow sensor, iii) a temperature sensor, iv) a gas flow sensor, v) a gas pressure sensor, or vi) an electrical system sensor.

[0076] In some embodiments, and optionally, in any combination of the embodiments described above or below, the step of the at least one processor associating each corresponding energy consumption location with the specific physical asset category further includes the at least one processor classifying one or more UOEs of the corresponding energy consumption location into the specific physical asset category. In some embodiments, and optionally, in any combination of the embodiments described above or below, classifying one or more UOEs of the corresponding energy consumption location into the specific physical asset category includes the at least one processor applying at least one machine learning technique that has been

[0077] trained to classify physical assets based at least in part on Standard Industrial Classification (SIC) codes. In some embodiments, and optionally, in any combination of the embodiments described above or below, the asset-specific historical energy consumption data and the asset-specific current energy consumption data are in units of kilowatt-hours (kWh). In some embodiments, and optionally, in any combination

[0078] In some embodiments, and optionally, in any combination of the embodiments described above or below, the present invention provides a typical innovative system. This system includes at least the following components, namely at least one dedicated computer. This dedicated computer includes a non-transitory computer memory storing specific computer-executable program code, and at least one computer processor. When the specific program code is executed, this computer processor performs at least the following operations, namely, for an aggregate of energy-consuming physical assets, during a predetermined time period, i) receiving asset-specific historical data and ii) asset-specific current energy consumption data from at least one demand meter, at least one sensor or both of these, wherein the asset-specific historical data includes 1) asset-specific historical energy consumption data, 2) at least one first asset-specific historical operation characteristic, 3) at least one first asset-specific historical environmental characteristic, and 4) first asset-specific historical failure loss data, and for each corresponding physical asset category, determining a corresponding failure frequency and a corresponding average severity of each failure based at least in part on the asset-specific historical data, and determining an adjusted failure loss value per physical asset for each corresponding physical asset category based at least in part on the corresponding failure frequency and the corresponding average severity of each failure, and determining a corresponding average current energy consumption value per physical asset for each corresponding physical asset category based at least in part on the asset-specific current energy consumption data, and for at least one energy of the aggregate of the energy-consuming physical assets - associating each corresponding energy consumption location representing a consumer physical asset with a specific physical asset category an operation related to, and for each corresponding energy consumption location, i) at least one of the aggregate of the energy consumption physical assets in each corresponding physical asset category associated with the corresponding energy consumption location and ii) based at least in part on the number of at least one energy consumption physical asset and the corresponding average current energy consumption value per physical asset for each corresponding physical asset category, an operation of determining a specific usage-based failure insurance premium value, and based at least in part on the specific usage-based failure insurance premium value of the corresponding energy consumption location, i) at least one service provider providing services to the at least one energy consumption physical asset, ii) at least one electronic device of at least one entity associated with the at least one energy consumption physical asset, iii) at least one sensor, or iv) an operation of generating at least one warning for at least one of the at least one energy consumption physical assets, the at least one electronic warning being such that, with respect to the location-specific level of energy usage of the at least one energy consumption physical asset, i) a new usage-based failure insurance premium value or a change in the usage-based failure insurance premium value is requested, ii) at least one user associated with the at least one energy consumption physical asset is caused to change the level of energy usage of the at least one energy consumption physical asset, iii) the at least one user is instructed to adjust at least one operating characteristic of the at least one energy consumption physical asset, and iv) the at least one user is instructed to adjust at least one environmental characteristic of the at least one energy consumption physical asset ​​​​​​​​​​​​​​​​ commanding at least one user, and v) commanding the at least one user to adjust sensor operation by at least one of at least one of the at least one sensor, configured to affect. In some embodiments, the present invention provides a computer-implemented method. The method

[0079] at least includes a server executing an insurance contract management application, during a predetermined period of (1) identifying at least one of the following parameters of the unique data associated with at least one unit of equipment (UOE), namely occupancy, activity, area aggregation, space aggregation, facility size, system type, equipment model, and any combination thereof, at a location, system or equipment, (2) receiving energy usage data from at least one sensor, and (3) receiving asset loss data, and the server executing the insurance contract management application calculating an insurance premium based at least in part on the energy usage data and loss data at a certain number of locations and / or assets identified in the energy usage data and loss data, and the server executing the insurance contract management application determining an energy usage-based asset failure insurance premium for at least one facility based on the aggregate average energy usage and the energy usage data, and the server executing the insurance contract management application, based at least in part on the energy usage-based asset failure insurance premium, (i) at least one service provider providing services to the at least one UOE, (ii) the at least one UOE and (iii) at least one user, commanding at least one of the following, namely (i) commanding at least one user, and (v) commanding the at least one user to adjust sensor operation by at least one of the at least one sensor, configured to affect. and (iii) at least one user, commanding at least one of the following, namely (i) commanding at least one user, and (v) commanding the at least one user to adjust sensor operation by at least one of the at least one sensor, configured to affect. and (iii) at least one user, commanding at least one of the following, namely (i) commanding at least one user, and (v) commanding the at least one user to adjust sensor operation by at least one of the at least one sensor, configured to affect. and (iii) at least one user, commanding at least one of the following, namely (i) commanding at least one user, and (v) commanding the at least one user to adjust sensor operation by at least one of the at least one sensor, configured to affect. and (iii) at least one user, commanding at least one of the following, namely (i) commanding at least one user, and (v) commanding the at least one user to adjust sensor operation by at least one of the at least one sensor, configured to affect. and (iii) at least one user, commanding at least one of the following, namely (i) commanding at least one user, and (v) commanding the at least one user to adjust sensor operation by at least one of the at least one sensor, configured to affect. and (iii) at least one user, commanding at least one of the following, namely (i) commanding at least one user, and (v) commanding the at least one user to adjust sensor operation by at least one of the at least one sensor, configured to affect. and (iii) at least one user, commanding at least one of the following, namely (i) commanding at least one user, and (v) commanding the at least one user to adjust sensor operation by at least one of the at least one sensor, configured to affect. and (iii) at least one user, commanding at least one of the following, namely (i) commanding at least one user, and (v) commanding the at least one user to adjust sensor operation by at least one of the at least one sensor, configured to affect. At least one electronic device of at least one insured entity associated with i) the at least one sensor; iv) the at least one UOE; and v) these. Any combination of at least one of the following will generate at least one warning: and a step of updating said at least one electronic alert, said step including: i) a new premium and / or a premium update; and ii) providing information about the change associated with the at least one UOE. and at least one insurance company to provide a location-specific insurance contract for the energy use of the at least one UOE. and iii) affecting the presence level of at least one of the UOEs. including at least one instruction for adjusting at least one of the operating parameters; iv) at least one of the at least one operating parameters of the at least one sensor. and including at least one instruction to adjust the

[0080] In some embodiments, the present invention provides a computer system. The computer system will have at least the following components: Policy Administration Application a non-transitory memory for electronically storing computer executable program code for the application; When the program code of the insurance policy management application is executed, at least the following is executed: During operation, i.e., a predetermined period of time, (1) at least one unit of equipment (UOE) ) The following parameters for the specific data related to the equipment model, system , occupancy, activity, area intensity, spatial intensity, facility size, and any of these (2) a location parameter that identifies at least one of the combinations; and Receiving energy usage data from, and (3) the operation of receiving asset loss data, and the energy At least a certain number of locations and / or facilities identified in the usage data and loss data Based on at least partially calculating a base loss cost, and based on the energy usage data Determining the energy usage-based asset failure insurance premium for at least one facility The server executing the insurance contract management application, based at least partially on the energy usage Based on the base asset failure insurance premium, i) at least one service provider providing services to the at least one UOE , ii) at least one electronic device of at least one insured entity associated with the at least one UOE , iii) the at least one sensor, iv) the at least one UOE, and v ) At least one warning is generated for at least one of any combination of these , and is configured to be a specifically programmed computer processor that performs the operation of Including at least one computer processor, and the at least one electronic warning is i ) Providing information about new insurance premiums and / or changes in insurance premiums, ii) causing at least one insurance company associated with the at least one UOE to affect the location-specific level of energy usage of the at least one UOE , iii) including at least one instruction to adjust at least one of at least one operation parameter of the at least one UOE , iv) including at least one instruction to adjust at least one of at least one operation parameter of the at least one sensor , and is configured to perform .

[0081] Although a number of embodiments of the invention have been described, these embodiments are illustrative only and are not limiting, and it should be understood that many modifications will be apparent to those skilled in the art There is. Also included is that the various embodiments of the methodology of the invention, the system of the invention, and the device of the invention can be utilized in any combination with each other. Further, of course, the various steps may be performed in any desired order (and any desired steps for a particular embodiment may be added and / or any undesirable steps May be deleted). May be). May be added and / or any undesirable steps May be deleted).

Claims

Claim 1 A computer-implemented method, comprising: at least one processor receiving energy usage data for a collection of energy-consuming physical assets, the energy usage data including asset-specific history data and asset-specific current energy consumption data from at least one sensor; and the at least one processor obtaining failure data, the failure data including a corresponding failure frequency and a corresponding average severity for each failure of the energy-consuming physical assets in the collection of energy-consuming physical assets; the at least one processor determining a corresponding current energy consumption value per physical asset for each corresponding physical asset category, at least partially based on the asset-specific current energy consumption data; the at least one processor associating each corresponding energy consumption location representing at least one energy-consuming physical asset in the collection of energy-consuming physical assets with a specific physical asset category; the at least one processor i) determining a specific usage-based failure estimate, at least partially based on ii) the energy usage data for the collection of energy-consuming physical assets and the failure data for the collection of energy-consuming physical assets, wherein the specific usage-based failure estimate indicates a) whether a failure or damage of at least one energy-consuming physical asset in the collection of energy-consuming physical assets will occur, b) when a failure or damage of the at least one energy-consuming physical asset in the collection of energy-consuming physical assets is likely to occur, or c) at least one of a combination of a) and b); when the specific usage-based failure estimate indicates a), b) or c), the at least one processor determining a specific usage-based failure premium for each corresponding energy consumption location, at least partially based on i) the number of at least one energy-consuming physical asset in the collection of energy-consuming physical assets in each corresponding physical asset category associated with the corresponding energy consumption location, and ii) the corresponding current energy consumption value per physical asset for each corresponding physical asset category. The at least one processor includes generating at least one electronic warning based at least in part on the identified usage-based failure insurance value for the corresponding energy consumption location, wherein the at least one electronic warning is configured to affect either i) a new usage-based failure insurance value or a change in the usage-based failure insurance value, or ii) causing at least one user associated with the at least one energy-consuming physical asset to change the level of energy usage of the at least one energy-consuming physical asset, a computer-implemented method. **Claim 2** The computer-implemented method of claim 1, wherein the at least one energy-consuming physical asset is a physical configuration including one or more device units (UOE). **Claim 3** The computer-implemented method of claim 2, wherein the energy usage data includes at least one of at least one optical parameter, at least one acoustic parameter, at least one pressure parameter, at least one temperature parameter, at least one acceleration parameter, at least one magnetic parameter, at least one biological parameter, at least one chemical parameter, or at least one motion parameter. **Claim 4** The computer-implemented method of claim 3, wherein the at least one optical parameter is selected from the group consisting of infrared light parameters, visible light parameters, and ultraviolet light parameters. **Claim 5** The at least one processor further includes determining the identified usage-based failure estimation based at least in part on each corresponding energy consumption location of the aggregate of energy-consuming physical assets, wherein each corresponding energy consumption location is defined based on global positioning system (GPS) data identifying the physical location of the at least one energy-consuming physical asset, the computer-implemented method of claim 1. **Claim 6** The at least one sensor is i) a liquid pressure sensor, ii) a liquid flow sensor, iii) a temperature sensor, iv) a gas flow sensor, v) a gas pressure sensor, or vi) an electrical system sensor and is one of these, the computer-implemented method of claim 1.

7. The computer-implemented method of claim 1, wherein classifying each corresponding energy consumption location representing the at least one energy-consuming physical asset into the specific physical asset category includes the at least one processor applying at least one machine learning technique that has been trained to classify physical assets based at least in part on Standard Industrial Classification (SIC) codes.

8. The computer-implemented method of claim 1, wherein the energy usage data is asset-specific historical energy consumption data and asset-specific current energy consumption data in units of kilowatt-hours (kWh).

9. The computer-implemented method of claim 8, further comprising the at least one processor converting the asset-specific historical energy consumption data and the asset-specific current energy consumption data into corresponding kWh amounts.

10. A system comprising: at least one dedicated computer, wherein the at least one dedicated computer comprises: a non-transitory computer memory storing specific computer-executable program code; and at least one computer processor and, when the at least one computer processor executes the specific program code, at least the following operations, namely: receiving energy usage data for a collection of energy-consuming physical assets, the energy usage data including asset-specific historical data and asset-specific current energy consumption data from at least one sensor; obtaining failure data including the corresponding failure frequency and the corresponding average severity of each failure of the energy-consuming physical assets in the collection of energy-consuming physical assets; determining a corresponding current energy consumption value per physical asset for each corresponding physical asset category based at least in part on the asset-specific current energy consumption data; associating each corresponding energy consumption location representing at least one energy-consuming physical asset of the collection of energy-consuming physical assets with a specific physical asset category; i) the energy usage data for the collection of energy-consuming physical assets; and ii) the failure data of the collection of energy-consuming physical assets determining a specific usage-based failure estimate based at least in part on, wherein the specific usage-based failure estimate is a) whether a failure or damage occurs in at least one energy-consuming physical asset among the collection of the energy-consuming physical assets; b) when there is a high possibility that a failure or damage occurs in the at least one energy-consuming physical asset among the collection of the energy-consuming physical assets, or c) a combination of a) and b) indicating at least one of them; when the specific usage-based failure estimation indicates a), b) or c), for each corresponding energy-consuming location, i) the number of at least one energy-consuming physical asset among the collection of the energy-consuming physical assets in each corresponding physical asset category associated with the corresponding energy-consuming location, and ii) determining a specific usage-based failure insurance premium based at least in part on the number of the at least one energy-consuming physical asset and the corresponding current energy consumption value per physical asset for each corresponding physical asset category; configured to generate at least one electronic warning based at least in part on the specific usage-based failure insurance premium value of the corresponding energy-consuming location, wherein the at least one electronic warning is configured to affect i) a new usage-based failure insurance premium value or a request for a change in the usage-based failure insurance premium value, or ii) causing at least one user associated with the at least one energy-consuming physical asset to change the level of energy usage of the at least one energy-consuming physical asset, a system.

11. The system according to claim 10, wherein the at least one energy-consuming physical asset is a physical configuration including one or more device units (UOE).

12. The system according to claim 11, wherein the energy usage data includes at least one of at least one optical parameter, at least one acoustic parameter, at least one pressure parameter, at least one temperature parameter, at least one temperature parameter, at least one acceleration parameter, at least one magnetic parameter, at least one biological parameter, at least one chemical parameter, or at least one motion parameter.

13. The system according to claim 12, wherein the at least one optical parameter is selected from the group consisting of an infrared light parameter, a visible light parameter, and an ultraviolet light parameter.

14. The at least one processor is further configured to perform at least one operation including determining the specific usage-based fault estimation at least partially based on each corresponding energy consumption location among the aggregate of the energy consumption physical assets when executing the specific program code. The system of claim 10, wherein each corresponding energy consumption location is defined based on global positioning system (GPS) data identifying the physical location of the at least one energy consumption physical asset.

15. The at least one sensor is i) a liquid pressure sensor, ii) a liquid flow sensor, iii) a temperature sensor, iv) a gas flow sensor, v) a gas pressure sensor, or vi) an electrical system sensor The system of claim 10, which is one of them.

16. Classifying each corresponding energy consumption location representative of the at least one energy consumption physical asset into the specific physical asset category includes applying at least one machine learning technique trained to classify physical assets at least partially based on standard industrial classification (SIC) codes. The system of claim 10.

17. The energy usage data is asset-specific historical energy consumption data and asset-specific current energy consumption data with the unit of kilowatt-hour (kwh). The system of claim 10.

18. The at least one computer processor is further configured to convert the asset-specific historical energy consumption data and the asset-specific current energy consumption data into corresponding kwh amounts when executing the specific program code. The system of claim 17.

Images