Classification engine for identifying business hours

Abstract

Aspects of the subject technology relate to methods and systems for classifying businesses according to an open-hours classification category, for example, based on resource consumption data. In some implementations, methods of the subject technology include steps for receiving a plurality of operating hours categories, wherein each of the operating hours categories is associated with at least one usage profile, and receiving business information for an unclassified business, wherein the business information comprises resource consumption data for the unclassified business. In some aspects, methods of the subject technology can further include steps for determining if the unclassified business should be associated with one of the operating hours categories based on the resource consumption data for the unclassified business. Systems and machine-readable media are also provided.

Description

BACKGROUND

Technical Field

Aspects of this disclosure relate to methods and systems for predicting hours of operation or “business hours” for various establishment types, and in particular, for determining operating hours information based on various types of business information, such as resource usage information.

Introduction

Many types of service providers and vendors could benefit from knowing operating hours for individual businesses. For example, accurate open hours information could help utility providers make customer-specific recommendations for participation in eco-conscious conservation programs, such as energy efficiency programs.

SUMMARY

The following presents a simplified summary of one or more embodiments in order to provide a basic understanding of such embodiments. This summary is not an extensive overview of all contemplated embodiments, and is therefore not intended to identify key or critical elements of all embodiments nor delineate the scope of any or all aspects of the invention. Its sole purpose is to present some concepts of one or more embodiments in a simplified form as a prelude to a more detailed description, presented later.

Aspects of the technology relate to a computer-implemented method including steps for receiving a plurality of operating hours categories, wherein each of the operating hours categories is associated with at least one usage profile, and receiving business information for an unclassified business, wherein the business information comprises resource consumption data for the unclassified business. In certain aspects, methods of the technology can further include steps for determining if the unclassified business should be associated with one (or more) of the operating hours categories.

In another aspect, the subject technology relates to a classification system (e.g., an operating hours category classification system), including one or more processors, and a computer-readable medium having instructions stored therein, that when executed by the processors, cause the processors to perform various operations including, receiving a plurality of operating hours categories, wherein each of the operating hours categories is associated with at least one usage profile, and receiving business information for an unclassified business. In some aspects, the classification system can further execute operations for determining if the unclassified business should be associated with one of the operating hours categories from among the plurality of operating hours categories.

In yet another aspect, the subject technology can relate to a non-transitory computer-readable storage medium that includes instructions for receiving a plurality of operating hours categories, wherein each of the operating hours categories is associated with at least one usage profile, and receiving business information for an unclassified business, wherein the business information comprises resource consumption data for the unclassified business. In some approaches, the instructions can further include steps for determining if the unclassified business should be associated with one of the operating hours categories by comparing the business information to one or more of the usage profiles.

BRIEF DESCRIPTION OF THE DRAWINGS

In the following description, reference is made to the following figures, and in which are shown by way of illustration specific examples in which the subject technology may be practiced. It is understood that other aspects may be utilized and changes made without departing from the scope of the subject technology. In the figures:

FIG. 1 illustrates an example environment that can be used to implement a business hours classification system, according to some aspects of the technology.

FIG. 2 conceptually illustrates an example of power load curves for various businesses, according to some implementations.

FIG. 3A illustrates an example process that can be used to perform operating hours classifications, according to some aspects of the technology.

FIG. 3B illustrates another example process that can be used to determine an operating hours schedule for an unclassified business, according to some aspects of the technology.

FIG. 4 illustrates an example environment in which business information can be collected and provided to a classification system.

FIG. 5 illustrates a conceptual block diagram of hardware components used to implement a business classification system, according to some aspects of the technology.

DETAILED DESCRIPTION

The detailed description set forth below is intended as a description of various configurations of the subject technology and is not intended to represent the only configurations in which the subject technology can be practiced. The appended drawings are incorporated herein and constitute a part of the detailed description. The detailed description includes specific details for the purpose of providing a more thorough understanding of the subject technology. However, it will be clear and apparent that the subject technology is not limited to the specific details set forth herein and may be practiced without these details. In some instances, structures and components are shown in block diagram form in order to avoid obscuring the concepts of the subject technology.

Aspects of the subject technology address the foregoing need by providing methods and systems for determining operating hours for business establishments of various types. In some aspects, resource consumption data, such as power (e.g., electricity) consumption data, can be used to classify businesses using a classification category identifier, e.g., an “operating-hours category” identifier. In some aspects, power consumption data can be provided in the form of power load curve data, which provides a graphical representation of resource consumption relative to a given time resolution (e.g., on monthly, weekly, daily or minute-by-minute intervals etc.). The power consumption data may be analyzed in order to identify one or more elevated energy usage periods that may correspond to operating hours of a business establishment. Alternatively, or additionally, the power consumption data may be analyzed in order to identify one or more periods of low energy usage that may correspond to non-operating hours of a business establishment.

In many circumstances, information about the hours a business is open (e.g., the operating hours of a business) is nonexistent or unreliable. Aspects of the subject technology address these technical problems by providing a classification engine that is able to interface with various systems to collect consumption data for a business establishment and store the data in a database or other storage device. The classification engine may process the consumption data, which may correspond to a prolonged period of time (e.g., 1 to 6 months of consumption/usage data, the consumption data comprising usage data of various possible resolutions or intervals), in order to generate power load curve data for the business establishment. Based on the consumption data (or power load curve data), the classification engine may accurately determine the operating hours for the business establishment and store the operating hours in a business profile or communicate the information to another system.

Although many of the provided examples relate to open hours classifications based on electric energy consumption, it is understood that other information may be used without departing from the scope of the invention. For example, various forms of demographic data can be used (e.g., in conjunction with resource consumption information) to determine business operating hours for a given business. Examples of such demographic data include, but are not limited to, one or more of: business name, location information, square footage, business type, and/or advertising information (e.g., menu data, products listings), etc.

Categories of operating hours may be used to identify operating hours of a business establishment. For example, in some aspects, different operating hours categories are generated, each of which corresponds to a particular hourly schedule that identifies operating hours for an associated businesses. In turn, each operating hours category is associated with one or more usage profiles, each of which contain information (e.g., data and consumption pattern information) that can be used to identify operating hours for an unclassified business.

By way of example, business information containing resource consumption data can be compared with various usage profiles to determine if any patterns/similarities with existing usage profiles can be identified. If a positive match is found, the corresponding operating hours category is associated with the unclassified business, e.g., to associate operating hours information to the previously unclassified business. As used herein, an “operating hours category” relates to a classification category used to define a business schedule e.g., for the business's operating hours or alternatively, a schedule for the business's closed hours. Operating hours categories can contain various types of time interval data, such as open days (e.g., Monday through Friday), open times of day (e.g., “nighttime” or “daytime”) and/or specific operating-hours intervals (e.g., Open Monday: 10:00 AM to 3:00 PM and 5:00 PM to 10:00 PM; Closed Tuesday).

Depending on implementation, comparisons between business information and usage profiles can be performed in different ways. For example, machine learning implementations (such as clustering) can be used to compare unclassified business information with usage profiles produced using training data (i.e., data sets for which known operating hours are already know). As discussed in further detail below, comparisons between business information and usage profiles can also be based on quantified comparisons, and/or user define patterns and/or qualitative features.

Through use of the classification engine, previously unclassified businesses (for which open/closed hours information was previously unknown), can be associated with open hours information. Such information can be of use in several practical applications. In some aspects, open hours information can be used by a behavioral demand response (BDR) notification system or service, for example, to help segment or group businesses with similar hourly schedules. In some implementations, open hours classifications may be used to help in identifying similar businesses, such as those providing similar goods/services and that have similar operating hours. However, in other implementations, open hours classifications may be used to identify/match different businesses or consuming entities on the basis of consumption patterns, for example, based on similarities in operating hours. In this way, the relevance of targeted notifications, such as BDR notifications, can be enhanced, e.g., by improving comparisons between similar business customers that are delivered as part of the notification content.

In other aspects, open hours information may be provided to a resource provider or other third party, such as a power utility, for example, to help improve the utility service's interactions with its customers. By way of example, a power utility may be interested in better understanding operating schedules of its business customers in order to improve marketing or advertising communications, for example, pertaining to customer enrollment in energy savings programs.

FIG. 1 illustrates an example environment 100 that can be used to implement an operating hours classification system (and method), according to some aspects of the technology. Environment 100 includes classification system 102 that is configured to classify businesses into one or more operating hours categories e.g., to associate operating hours with businesses for which operating hours were previously unknown or unverified.

In the example of environment 100, classification system 102 includes category database 104 that contains multiple operating hours categories (i.e., Category 1 . . . Category N). Operating hours categories can be user created/generated, for example, based on a user's selection of associated scheduling information. Alternatively, operating hours categories may be automatically or machine generated, for example, based on a grouping of one or more corresponding usage profiles, as discussed in further detail below.

As illustrated by category database 104, each operating hours category is associated with one or more usage profiles P₁ . . . P_n (e.g., in usage profile database 106). Usage profiles can contain information used for comparison with business information, for example, to help determine corresponding operating hours scheduling information for an associated business. That is, usage profiles can contain identifying/comparison information used to analyze business information corresponding with an unclassified business, as explained in further detail below. Depending on implementation, usage information can include various types of data, such as energy usage data (e.g., a power load curve), for example, that can correlate with an operating hours schedule for the associated operating hours category. Similar to the operating hours categories, in some aspects, usage profiles may be user generated (e.g., through the selection of certain data features by a user or administrator). Alternatively, usage profiles may be machine generated, e.g., based on clusters of consumption data and/or frequency information for other types of information such as textual information (e.g. business names and/or titles, etc.).

In some aspects, each usage profile is exclusive to a single operating hours category. That is, each operating hours category defines a unique schedule or set of schedules for which associated businesses are open to serve customers, whereas the associated usage profile includes data used to identify businesses (using business information), that have operating hours corresponding with the operating category. In the example of FIG. 1, each of the usage profiles (e.g., P₁ . . . P_n) are stored in usage profile database 106. However, it is understood that associations between a particular category (e.g., Category 1), and one or more usage profiles (e.g., P₁ and P₂) can be accomplished using various other data structures and/or methods, such as pointers, linked lists, arrays and/or function calls, etc.

In example environment 100, classification system 102 is coupled to server 110, e.g., via network 108. Network 108 can represent a variety of communication networks, including a combination of private networks, such as local area networks (LANs), wide-area networks (WANs), WiFi networks, cellular networks or a network of networks, such as the Internet. As discussed in further detail below, network 108 can communicate with other types of data providers, such as utility providers and/or configured for communication with smart devices such as Advanced Metering Infrastructure (AMI) devices, or smart thermostats, etc.

Server 110 includes business information database 112 that is configured to store business information for one or more unclassified businesses (e.g., businesses for which open hours information is unknown or unverified). In the illustrated example, database 112 includes business information for multiple unclassified businesses (e.g., B₁, B₂, B₃ . . . B_n). It is understood that business information for any number of unclassified businesses may be accessible by server 110 and stored either locally or remotely. It is further understood that server 110 represents potentially any source of business information. As such, server 110 can include one or more third-party systems or proprietary data stores capable of providing business information to classification system 102 via a network, such as network 108. By way of example, server 110 can represent a data collection network that retrieves information from various online sources, such as business directories, review websites, map providers, and/or rebate websites, etc.

In practice, business information is provided to classification system 102, for example, by server 110. Business information can be collected or aggregated from one or more sources, such as a resource provider (e.g., a power utility) or from one or more third-party services capable of providing demographic data. Business information can be provided directly to classification system 102, or alternatively, to an intermediary processing system, such as that represented by server 110.

In some aspects, business information for each unclassified business entity is segregated into discreet data packages or files (e.g., B₁, B₂, B₃ . . . B_n) and/or separated using metadata tags. As discussed above, business information can contain any information or data pertaining to a particular business, such as resource consumption information (e.g. load curve data), or other demographic information, such as, business name, location, advertising information, etc.

Once the business information for an unclassified business is provided to classification system 102, classification system 102 can use open hours categories and their corresponding usage profiles (e.g., usage profiles P₁ . . . P_n) to determine if an open hours category assignment should be made for the unclassified business. In some approaches, a similarity between the received business information and one or more usage profiles is determined by comparing the business information to the usage profiles.

Where a high-degree of business information/usage profile similarity is identified, an association is created between the corresponding open hours category and the unclassified business. That is, open hours scheduling information attaches to the previously unclassified business. Such associations can be accomplished by editing and/or appending the business information to include a metadata reference to a particular open hours category.

By way of example, business information B₁ for an unclassified first business may be determined to be highly similar to profile information of usage profile P₁ (associated with Category 1). As discussed above, B₁ can include resource consumption data (e.g., for one or more consumable resources such as power, water and/or gas). Further to the above example, category profile P₁ may be based on a cluster of resource consumption information that correlates with business operating hours (e.g., between the hours of 6:00 AM and 8:00 PM). Thus, based on similarities between B₁ and P₁, the business corresponding with B₁ is associated with Category 1, which identifies B₁ as having operating hours from 6:00 AM to 8:00 PM.

In the foregoing example, any type of information can be used to form, or included in, a usage profile with which the business information is compared. For example, P₁ can contain resource usage data (e.g., power data) collected by a utility provider. Data collection frequency may depend on the collection mechanism, for example, utility providers may ascertain consumption data using on-site meter readers, for example, on a monthly basis, or alternatively on more frequent time intervals (e.g., on a daily, hourly or minute-by-minute basis), using an advanced metering infrastructure (AMI) device. Thus, by comparing the available business information for business B₁ with information stored in the various usage profiles for operating hours categories 1-N, operating hours category assignments can be made for the previously unclassified business associated with B₁.

FIG. 2 conceptually illustrates an example of load curve data 200 for various businesses (e.g., businesses 202, 204 and 206), according to some implementations. Load curve data 200 is illustrated using power load curves for three different business establishments having similar operating schedules. As used herein, “power load curve” refers to graphical or illustrative embodiments of time-varying measures of resource consumption, such as measures of power consumption on specific time intervals, e.g., monthly, weekly, daily or hourly, etc. Although example load curve data 200 relates to electric power usage, the example of FIG. 2 is illustrative and not exclusive of representations of consumption patterns for other resources, such as water or gas.

In practice, resource consumption information (such as load curves for businesses 202, 204, and/or 206) may be aggregated for businesses for which operating hours are already known, or verified. As shown in FIG. 2, “open” and “close” intervals for businesses are identified, for example, based on known operating hours information and/or power consumption features identified in the load curve geometry. In some aspects, this information can be used to create a usage profile against which subsequent unclassified businesses can be compared. That is, business information may be compared to usage profiles containing data such as that represented by load curves for businesses 202, 204, and/or 206.

In some aspects, a given usage profile may only identify an open/closed hours schedule for a particular time (e.g., mornings), days of a week (e.g., Wednesdays), or even a particular date, such as a government or cultural holiday (e.g., July 4^th). Alternatively, usage profile information can be used to match or identify business operating hours across multiple days, times and specific dates. Thus, a schedule corresponding with a particular operating hours category can be a composite of all the usage profiles associated with that category.

By way of example, a given operating hours category can be associated with two usage profiles, P1 and P2. In this example, P1 provides data for identifying business operations on Monday mornings and P2 provides data for identifying business operations on Wednesdays. As such, the operating hours category would be associated with scheduling information for Mondays and Wednesdays. Thus, the association between operating hours categories and usage profiles can be used to determine the operating schedule defined by the operating hours categories.

Further to the above example, newly received business information (e.g., for an unclassified business for which operating hour are unknown or unverified) is compared to usage profile information generated from load curves for businesses 202, 204 and/or 206. As discussed in further detail below, where a high degree of similarity is identified as between business information for a particular business and a given usage profile, associations may be formed between an associated operating hours category (e.g., corresponding with the usage profile) and the business information.

FIG. 3 illustrates an example process 300 that can be implemented to perform operating hours classifications. Process 300 begins with step 302, in which a plurality of operating categories are received and/or created or generated. The generation of operating hours categories can be accomplished with a processor based system, such as a classification system (e.g., classification system 102). In some aspects, operating hours categories are user created, for example, based on a user defined hourly schedule. As discussed above, the association between operating hours categories and usage profiles can be performed according to the schedule defined by the operating hours category. For example, if the operating hours category is used to describe an operating hours schedule for weekdays (e.g., Monday-Friday), then usage profiles containing comparative consumption data for weekdays may be associated with the operating hours category. In some aspects, operating hours categories may be generated and/or initialized on one or more third-party systems and then transmitted to the classification system. When implemented, the various operating hours categories are used to define different operating hours schedules, for example, on a daily, weekly, or monthly basis. Operating hours categories may also be used to identify open hours schedules on special days, such as cultural or governmental holidays.

As discussed above, usage profiles provide data that can be used to analyze business information for unclassified businesses and to make operating hours category classifications. That is, usage profiles provide data “fingerprints” to identify key features or patters in business information, such as resource consumption patterns that are necessary to infer when an associated business is open (generally associated with higher resource consumption), or closed (generally associated with lower resource consumption). Depending on implementation, each usage profile can identify different aspects of an operating hours schedule. For example, some usage profiles may be specific to a particular business type, such as a bakery. Alternatively, certain usage profiles may be specific to particular schedules, or schedules on specific calendar days, etc.

By way of example, a given usage profile (e.g., usage profile “P1”), may define a general open hours schedule for retail establishments on business days (e.g., Monday through Friday). In contrast, a different usage profile (“P2”) may identify usage patterns for a specific business type (e.g., bakeries), on a specific day of the week (e.g., Saturdays). Thus, a multitude of usage profiles may be associated with a given operating hours category in order to yield detailed operating hours information for businesses associated with that category.

In practice, operating hours categories can comprise labels or tags, such as metadata tags, that can be attached to, or associated with a business. As noted above, a given operating hours category can be associated with one or more businesses, for example, to indicate similar hourly operating schedules for different distinct businesses.

In step 304, business information for an unclassified business is received. Although the business information for an unclassified business can contain data of different types (such as a business name, location and/or other demographic information), in some aspects, the business information includes resource consumption data for one or more consumable resources, such as electric power.

In practice, business information may be received from virtually any source, including but not limited to a utility provider, a smart device (such as a smart thermostat or behavioral demand response device), and/or a third-party provider or data collection service. By way of example, business information in the form of power consumption information may be received from a smart meter device, such as advanced metering infrastructure (AMI) device that is capable of communicating directly with a classification system, such as classification system 102, discussed with respect to FIG. 1, above.

In step 306, the business information is compared to one or more usage profiles to determine which, if any, of the usage profiles share a high-degree of similarity with the provided business information. Analysis of the business information (e.g., through comparison with the usage profiles) can be accomplished with machine-learning techniques, such as clustering. In some aspects, a quantitative measure of similarity between a set of business information (for an unclassified business) and a particular usage profile may be generated. By way of example, when comparing business information with a usage profile, a numeric score output, such as on a 1-10 scale, can be used to indicate a relative measure of similarity. In such approaches, a score of 1 may indicate little similarity between the business information and the usage profile, whereas a score of 10 can indicate a high degree of similarity.

By way of further example, business information provided for an unclassified business, such as a restaurant that specializes in breakfast and brunch may correspond with a business with operating hours according to the following schedule: Monday through Friday: 7:00 AM to 6:00 PM; Saturday: 8:00 AM to 4:00 PM; and Sunday: Closed. Thus, when compared to a first usage profile with a highly similar schedule (e.g., Monday through Friday: 7:00 AM to 6:00 PM; Saturday and Sunday: Closed), the comparative numeric score output may be an ‘8.’ In contrast, if the same business information is compared to a second usage profile representing a dissimilar operating hours schedule (e.g., Wednesday through Sunday: 10:00 AM to 4:00 PM; Sunday through Monday 6:00 AM to 3:00 PM; and Sunday: Closed), the comparative numeric score output may be a ‘2.’

In step 308, a determination is made as to whether or not the unclassified business should be associated with a particular operating hours category. In some aspects, a threshold similarity score may be used. For example, similarity scores above a predetermined threshold similarity score may result in the formation of associations (classifications) with respect to business information for a previously unclassified business. Further to the above example, if the predetermined threshold similarity score is a ‘7,’ then an association may be formed between the business and an open hours category corresponding with the first usage profile, whereas no associations would be formed with the second usage profile.

FIG. 3B illustrates steps of another example process 301 that can be used to determine an operating hours schedule for an unclassified business. Process 301 begins with step 303 in which business information for an unclassified business is received e.g., by a classification system, such as classification system 102. As discussed above, the business information for the unclassified business can contain data of different types, such as name or title, location and/or other demographic information. In some aspects, the business information includes resource consumption data for one or more consumable resources, such as electric power. In some instances, the business information, including resource consumption data, may be formulated into a graphical representation of resource consumption, such as a power load curve.

In step 305, a consumption baseline for the unclassified business is calculated. For electric power consumption, the consumption baseline can be derived from power consumption data, such as power load curve data reflecting electric power use by the unclassified business. In such aspects, the consumption baseline can represent a minimum power consumption amount over a given unit of time, such as a time of day (e.g., nighttime or mornings) or a day of the week (e.g., Sundays), etc. The minimum power consumption may be a minimum average power consumption amount or a pattern of minimum power consumption that reflects (sometimes periodic) consumption that occurs during closed hours (e.g., periodic refrigeration cycles).

In step 307, an elevated consumption period is determined based on the consumption baseline. As used herein, the “elevated consumption period” can represent a period of time for which resource consumption is elevated above the consumption baseline calculated in step 305. Elevated consumption periods can be identified in various ways, depending on implementation. In some aspects, elevated periods can be identified by marked increases in a rate of resource consumption for a period of time (e.g., over a threshold 30% increase in power consumption over a two-hour timespan). Similarly, elevated consumption periods may include decreases in a rate of resource consumption (e.g., a 45% decrease in a one-hour timespan). It is understood that the rate change (either increase or decrease) necessary to define an elevated consumption period may vary, depending on the implementation.

In another aspect, elevated consumption periods may be determined/identified by based on a total change (e.g., increases or decreases) in resource consumption usage. By way of example, a threshold net resource consumption increase (e.g., 2 kW h) for the unclassified business may be used to determine that an elevated consumption period has begun. Similarly, a net decrease (e.g., again by 2 kW h) may indicate that the elevated consumption period has ended. Thus, the elevated consumption period can be determined by increases and/or decreases in resource usage.

In yet another aspect, elevated consumption periods may be identified based on an analysis of graphical resource consumption patterns, such as power load curves. By way of example, load curve slopes may be used to identify increases/decreases in consumption that may correlate with an opening/closing of the associated (unclassified) business. In some aspects, slopes exceeding a predetermined threshold can be determined to represent the beginning (or end) of an elevated consumption period.

In step 309, an open hours interval (e.g., the unclassified business's operating schedule) is identified based on the consumption baseline and the elevated consumption period. For some businesses, the consumption baseline corresponds with a minimum (sometimes non-zero) power consumption, for example, that is necessary for required operations performed outside of operating hours. Thus, the baseline periods can represent time intervals in which a business is closed. Examples of resource usage that can occur during closed hours include power consumption necessary to operate cooling appliances, such as refrigerators, or information technology (IT) infrastructure, such as servers and/or datacenters.

Conversely, the elevated consumption periods, marked by higher resource consumption, can correspond with greater resource consumption and expenditure associated with a business's operating hours. By way of further example, during operating hours, businesses such as restaurants may expend more power, for example, to power lights, elevators, and ovens, etc. that are required to provide customer service during hours of operation. Thus, by differentiating between baseline periods and elevated consumption periods, methods of the subject technology can identify open/closed hours intervals for an unclassified business.

In some aspects of the subject technology, transition periods (e.g., a transition period from open hours to closed hours or a transition period from closed hours to open hours) may also be considered. Transition periods may be reflected in the resource consumption data as an increase or decrease in resource consumption that represents the transitions between the consumption baseline and the elevated consumption period(s). In some cases, the transition periods may be smooth, such as when opening or closing a business involves merely increasing or decreasing consumption. In other cases, however, the transition periods may include spikes in consumption or other patterns of consumption not associated with the consumption baseline or elevated consumption periods. For example, some businesses perform various preparation tasks before opening that increase resource consumption even above the level of the elevated consumption period(s). In other cases, businesses may perform various closing tasks before or after closing that increase resource consumption. These transition periods may be included or excluded from the open hours interval or closed hours intervals.

With the ability to classify businesses based on operating hours (e.g., where operating hours information was previously unavailable or unknown or unverified), more accurate communication outreach to business customers may be possible. For example, in the context of behavioral demand response notification delivery wherein customer comparisons are employed, a greater degree of similarity between different businesses (e.g., on the basis of operating hours information) may be used to increase the content relevance of targeted notifications.

FIG. 4 illustrates an example system 400 in which business information can be collected and provided to a classification system (e.g., classification system 414) according to some aspects of the technology. System 400 includes a utility 402 that is communicatively connected to several business entities (e.g., businesses 406, 408, and 410) via power infrastructure 404. System 400 also includes a classification system 414, and a third-party data provider communicatively coupled to one another, as well as utility 402, e.g., via network 412. Furthermore, network 412 is communicatively coupled to Advanced Metering Infrastructure (AMI) device 407. In the example of system 400, power infrastructure 404 includes various types of power delivery infrastructure. Similarly, network 412 can represent various communication networks, such as local area networks (LANs), wide area networks (WANs), or a network of networks, such as the Internet.

In practice, business information for each of businesses 406, 408 and 410 can be collected either directly by classification system 414, or via an intermediary collection step, such as by utility 402 or third party server 416. By way of example, utility 402 may collect/aggregate business information (such as power consumption data) pertaining to any (or all) of businesses 406, 406 and/or 410. Collected information can be based on monthly power readings performed at a site of the respective business. In some aspects, more frequent readings may be taken using an advanced metering infrastructure (AMI) device, such as AMI 407, e.g., to take power consumption readings on a daily, hourly or minute-by-minute basis.

In certain aspects, business information pertaining to any of businesses 406, 408 and/or 410 may also be collected by a third party agency or service, such as third party data provider 416. In this example, third party data provider 416 represents any service or combination of services (including on or more servers, clusters or data collection networks) that can collect, host and/or provide various types of information.

In practice, business information received by classification system 414 can include a mixture of resource usage and/or demographic information that is received either directly, or via one or more intermediary parties, such as utility 402 and/or third party data provider 416. By way of example, business information for business 406 may be received by classification system 414 via both of utility 402 and third party data provider 416 Once received by classification system 414, the business information can be used to determine one or more business operating hours classifications for the associated business, for example, to identify operating hours for the business based on an analysis of resource consumption over time.

It is understood that system 400 is exemplifies one example of an environment in which aspects of the invention can be practiced; however, other configurations can be implemented without departing from the scope of the subject technology. For example, in other implementations, various numbers of consuming entities (e.g., businesses, residences, or industrial facilities) may be represented. Similarly, various numbers or other types of resource providers (such as a water or gas provider may be represented).

FIG. 5 illustrates an example configuration of components of computing device 500, which may be used to implement a classification system, as discussed above with respect to FIGS. 1-3. In this example, computing device 500 includes processor 502 for executing instructions stored in memory device or element 504. The instructions can cause computing device 500 to execute a computer-implemented method, for example, to associate businesses with one or more operating hours categories that identify the businesses' operating hours.

As would be apparent to one of skill in the art, computing device 500 can include various types of memory, data storage, and/or non-transitory computer-readable storage media, such as a first data storage for program instructions for execution by the processor 502, a separate storage for usage history or user information, a removable memory for sharing information with other devices, etc. Computing device 500 can also include one or more communication components 506, such as a Wi-Fi, Bluetooth®, radio frequency, near-field communication, wired, and/or wireless communication systems, etc.

Computing device 500 can communicate with a network (e.g, network 412), such as the Internet, and can be configured to communicate with other such devices, such as one or more smart thermostat device, demand response devices, and/or AMI metering devices. Computing device 500 may include at least one input device 508 configured to receive input from a user. Such inputs may include, for example, one or more push button/s, touch pad/s, touch screen/s, wheel/s, joystick/s, keyboard/s, a mouse, keypad/s, or other such devices or elements enabling a user to input a command to the device. In some aspects, however, such a device may not include any buttons at all, but rather controlled through a combination of visual and audio commands, such that a user can manipulate data input to the device without direct physical contact. Computing device 500 can also include a display element 510, such as a touch-screen or liquid crystal display (LCD).

The various aspects can be implemented in a wide variety of operating environments, which in some cases can include one or more user computers, computing devices, or processing devices which can be used to operate any of a number of applications. User or client devices can include any of a number of general purpose personal computers, such as desktop or laptop computers running a standard operating system, as well as cellular, wireless, and handheld devices running mobile software and capable of supporting a number of networking and messaging protocols. Such a system also can include a number of workstations running any of a variety of commercially-available operating systems and other known applications for purposes such as development and database management. These devices also can include other electronic devices, such as dummy terminals, thin-clients, gaming systems, and other devices capable of communicating via a network.

Various aspects also can be implemented as part of at least one service or Web service, such as may be part of a service-oriented architecture. Services such as Web services can communicate using any appropriate type of messaging, such as by using messages in extensible markup language (XML) format and exchanged using an appropriate protocol such as SOAP (derived from the “Simple Object Access Protocol”). Processes provided or executed by such services can be written in any appropriate language, such as the Web Services Description Language (WSDL). Using a language such as WSDL allows for functionality such as the automated generation of client-side code in various SOAP frameworks.

Most embodiments utilize at least one network that would be familiar to those skilled in the art for supporting communications using any of a variety of commercially-available protocols, such as TCP/IP, OSI, FTP, UPnP, NFS, and CIFS. The network can be, for example, a local area network, a wide-area network, a virtual private network, the Internet, an intranet, an extranet, a public switched telephone network, an infrared network, a wireless network, and any combination thereof.

In embodiments utilizing a Web server, the Web server can run any of a variety of server or mid-tier applications, including HTTP servers, FTP servers, CGI servers, data servers, Java servers, and business map servers. The server(s) also may be capable of executing programs or scripts in response requests from user devices, such as by executing one or more Web applications that may be implemented as one or more scripts or programs written in any programming language, such as Java®, C, C# or C++, or any scripting language, such as Perl, Python, or TCL, as well as combinations thereof. The server(s) may also include database servers, including without limitation those commercially available from Oracle®, Microsoft®, Sybase®, and IBM®.

The environment can include a variety of data stores and other memory and storage media as discussed above. These can reside in a variety of locations, such as on a storage medium local to (and/or resident in) one or more of the computers or remote from any or all of the computers across the network. In a particular set of embodiments, the information may reside in a storage-area network (“SAN”) familiar to those skilled in the art. Similarly, any necessary files for performing the functions attributed to the computers, servers, or other network devices may be stored locally and/or remotely, as appropriate. Where a system includes computerized devices, each such device can include hardware elements that may be electrically coupled via a bus, the elements including, for example, at least one central processing unit (CPU), at least one input device (e.g., a mouse, keyboard, controller, touch screen, or keypad), and at least one output device (e.g., a display device, printer, or speaker). Such a system may also include one or more storage devices, such as disk drives, optical storage devices, and solid-state storage devices such as random access memory (“RAM”) or read-only memory (“ROM”), as well as removable media devices, memory cards, flash cards, etc.

Such devices also can include a computer-readable storage media reader, a communications device (e.g., a modem, a network card (wireless or wired), an infrared communication device, etc.), and working memory as described above. The computer-readable storage media reader can be connected with, or configured to receive, a computer-readable storage medium, representing remote, local, fixed, and/or removable storage devices as well as storage media for temporarily and/or more permanently containing, storing, transmitting, and retrieving computer-readable information. The system and various devices also typically will include a number of software applications, modules, services, or other elements located within at least one working memory device, including an operating system and application programs, such as a client application or Web browser. It should be appreciated that alternate embodiments may have numerous variations from that described above. For example, customized hardware might also be used and/or particular elements might be implemented in hardware, software (including portable software, such as applets), or both. Further, connection to other computing devices such as network input/output devices may be employed.

Storage media and computer readable media for containing code, or portions of code, can include any appropriate media known or used in the art, including storage media and communication media, such as but not limited to volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage and/or transmission of information such as computer readable instructions, data structures, program modules, or other data, including RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by the a system device. Based on the disclosure and teachings provided herein, a person of ordinary skill in the art will appreciate other ways and/or methods to implement the various embodiments.

As discussed above, the various embodiments can be implemented in a wide variety of operating environments, which in some cases can include one or more user computers, computing devices, or processing devices which can be used to operate any of a number of applications. User or client devices can include any of a number of general purpose personal computers, such as desktop or laptop computers running a standard operating system, as well as cellular, wireless, and handheld devices running mobile software and capable of supporting a number of networking and messaging protocols. Such a system also can include a number of workstations running any of a variety of commercially-available operating systems and other applications for purposes such as development and database management. These devices also can include other electronic devices, such as dummy terminals, thin-clients, gaming systems, and other devices capable of communicating via a network.

Various aspects also can be implemented as part of at least one service or Web service, such as may be part of a service-oriented architecture. Services such as Web services can communicate using any appropriate type of messaging, such as by using messages in extensible markup language (XML) format and exchanged using an appropriate protocol such as SOAP (derived from the “Simple Object Access Protocol”). Processes provided or executed by such services can be written in any appropriate language, such as the Web Services Description Language (WSDL). Using a language such as WSDL allows for functionality such as the automated generation of client-side code in various SOAP frameworks.

Most embodiments utilize at least one network for supporting communications using any of a variety of commercially-available protocols, such as TCP/IP, FTP, UPnP, NFS, and CIFS. The network can be, for example, a local area network, a wide-area network, a virtual private network, the Internet, an intranet, an extranet, a public switched telephone network, an infrared network, a wireless network, and any combination thereof.

In embodiments utilizing a Web server, the Web server can run any of a variety of server or mid-tier applications, including HTTP servers, FTP servers, CGI servers, data servers, Java servers, and business application servers. The server(s) also may be capable of executing programs or scripts in response requests from user devices, such as by executing one or more Web applications that may be implemented as one or more scripts or programs written in any programming language, such as Java®, C, C# or C++, or any scripting language, such as Perl, Python, or TCL, as well as combinations thereof. The server(s) may also include database servers, including without limitation those commercially available from Oracle®, Microsoft®, Sybase®, and IBM®.

The environment can include a variety of data stores and other memory and storage media as discussed above. These can reside in a variety of locations, such as on a storage medium local to (and/or resident in) one or more of the computers or remote from any or all of the computers across the network. In a particular set of embodiments, the information may reside in a storage-area network (“SAN”). Similarly, any necessary files for performing the functions attributed to the computers, servers, or other network devices may be stored locally and/or remotely, as appropriate. Where a system includes computerized devices, each such device can include hardware elements that may be electrically coupled via a bus, the elements including, for example, at least one central processing unit (CPU), at least one input device (e.g., a mouse, keyboard, controller, touch screen, or keypad), and at least one output device (e.g., a display device, printer, or speaker). Such a system may also include one or more storage devices, such as disk drives, optical storage devices, and solid-state storage devices such as random access memory (“RAM”) or read-only memory (“ROM”), as well as removable media devices, memory cards, flash cards, etc.

Such devices also can include a computer-readable storage media reader, a communications device (e.g., a modem, a network card (wireless or wired), an infrared communication device, etc.), and working memory as described above. The computer-readable storage media reader can be connected with, or configured to receive, a computer-readable storage medium, representing remote, local, fixed, and/or removable storage devices as well as storage media for temporarily and/or more permanently containing, storing, transmitting, and retrieving computer-readable information. The system and various devices also typically will include a number of software applications, modules, services, or other elements located within at least one working memory device, including an operating system and application programs, such as a client application or Web browser. It should be appreciated that alternate embodiments may have numerous variations from that described above. For example, customized hardware might also be used and/or particular elements might be implemented in hardware, software (including portable software, such as applets), or both. Further, connection to other computing devices such as network input/output devices may be employed.

Storage media and other non-transitory computer readable media for containing code, or portions of code, can include any appropriate storage media used in the art, such as but not limited to volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules, or other data, including RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by the a system device. Based on the disclosure and teachings provided herein, a person of ordinary skill in the art will appreciate other ways and/or methods to implement the various embodiments.

The description of the subject technology is provided to enable any person skilled in the art to practice the various embodiments described herein. While the subject technology has been particularly described with reference to the various figures and embodiments, it should be understood that these are for illustration purposes only and should not be taken as limiting the scope of the subject technology.

There may be many other ways to implement the subject technology. Various functions and elements described herein may be partitioned differently from those shown without departing from the scope of the subject technology. Various modifications to these embodiments will be readily apparent to those skilled in the art, and generic principles defined herein may be applied to other embodiments. Thus, many changes and modifications may be made to the subject technology, by one having ordinary skill in the art, without departing from the scope of the subject technology.

A reference to an element in the singular is not intended to mean “one and only one” unless specifically stated, but rather “one or more.” The term “some” refers to one or more. Underlined and/or italicized headings and subheadings are used for convenience only, do not limit the subject technology, and are not referred to in connection with the interpretation of the description of the subject technology. All structural and functional equivalents to the elements of the various embodiments described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and intended to be encompassed by the subject technology. Moreover, nothing disclosed herein is intended to be dedicated to the public regardless of whether such disclosure is explicitly recited in the above description.

Claims

1. A computer-implemented method comprising: receiving a plurality of operating hours categories, wherein a first operating hours category is associated with a first power usage profile describing a rate of change power characteristic, wherein a set of electronic messages are maintained in a storage device in association with the plurality of operating hours categories;receiving business information for an unclassified business, wherein the business information comprises resource consumption data for the unclassified business, the resource consumption data describing a rate of change for power usage of the unclassified business, wherein the rate of change for power usage is based on at least an amount of time that lapses between a minimum power consumption level and an elevated consumption level that exceeds the minimum power consumption level by a second defined threshold;comparing the rate of change power characteristic of the first operating hours category to the rate of change for power usage of the unclassified business to generate a similarity score describing a degree to which the rate of change for power usage of the unclassified business matches the rate of change power characteristic of the first operating hours category;associating the unclassified business with the first operating hours category when the similarity score exceeds a defined threshold, wherein a first subset of the set of electronic messages are maintained in the storage device in association with the first operating hours category; andcontrolling transmission of the set of electronic messages stored in a storage device, comprising: i) selecting the first subset of the set of electronic messages from the storage device for transmission to remote devices associated with the unclassified business based on the unclassified business being associated with the first operating hours category; andii) sending the first subset of the set of electronic messages to the remote devices associated with the unclassified business.

2. The computer-implemented method of claim 1, wherein associating the unclassified business with the first operating hours category comprises associating the unclassified business with the first operating hours category by pairing metadata for the first operating hours category with information identifying the unclassified business.

3. The computer-implemented method of claim 1, further comprising: receiving new business information for the unclassified business; andupdating an association between the unclassified business and the first operating hours category based upon the new business information.

4. The computer-implemented method of claim 1, wherein the rate of change for power usage is based on a difference between the minimum power consumption level and the elevated consumption level.

5. The computer-implemented method of claim 1, wherein the rate of change for power usage is derived from power load curve data.

6. The computer-implemented method of claim 1, wherein the minimum power consumption level for the unclassified business is determined based on an average power consumption when the unclassified business is closed.

7. A classification system comprising: one or more processors, anda computer-readable medium comprising instructions stored therein, which when executed by the one or more processors, causes the one or more processors to perform operations comprising: receiving a plurality of operating hours categories, wherein a first operating hours category is associated with a first power usage profile describing a rate of change power characteristic, wherein a set of electronic messages are maintained in a storage device in association with the plurality of operating hours categories;receiving business information for an unclassified business, wherein the business information comprises resource consumption data for the unclassified business, the resource consumption data describing a rate of change for power usage of the unclassified business, wherein the rate of change for power usage is based on at least an amount of time that lapses between a minimum power consumption level and an elevated consumption level that exceeds the minimum power consumption level by a second defined threshold;comparing the rate of change power characteristic of the first operating hours category to the rate of change for power usage of the unclassified business to generate a similarity score describing a degree to which the rate of change for power usage of the unclassified business matches the rate of change power characteristic of the first operating hours category;associating the unclassified business with the first operating hours category when the similarity score exceeds a defined threshold, wherein a first subset of the set of electronic messages are maintained in the storage device in association with the first operating hours category; andcontrolling transmission of the set of electronic messages stored in a storage device, comprising: i) selecting the first subset of the set of electronic messages from the storage device for transmission to remote devices associated with the unclassified business based on the unclassified business being associated with the first operating hours category; andii) sending the first subset of the set of electronic messages to the remote devices associated with the unclassified business.

8. The classification system of claim 7, wherein the rate of change for power usage is based on a difference between the minimum power consumption level and the elevated consumption level.

9. The classification system of claim 7, wherein associating the unclassified business with the first operating hours category comprises associating the unclassified business with the first operating hours category by pairing metadata for the first operating hours category with information identifying the unclassified business.

10. The classification system of claim 7, wherein the minimum power consumption level for the unclassified business is determined based on an average power consumption when the unclassified business is closed.

11. The classification system of claim 7, wherein the rate of change for power usage is derived from power load curve data.

12. The classification system of claim 7, wherein the elevated consumption level is set as a function of the minimum power consumption level.

13. A non-transitory computer-readable storage medium comprising instructions stored therein, which when executed by one or more processors, cause the one or more processors to perform operations comprising: receiving a plurality of operating hours categories, wherein a first operating hours category is associated with a first power usage profile describing a rate of change power characteristic, wherein a set of electronic messages are maintained in a storage device in association with the plurality of operating hours categories;receiving business information for an unclassified business, wherein the business information comprises resource consumption data for the unclassified business, the resource consumption data describing a rate of change for power usage of the unclassified business, wherein the rate of change for power usage is based on at least an amount of time that lapses between a minimum power consumption level and an elevated consumption level that exceeds the minimum power consumption level by a second defined threshold;comparing the rate of change power characteristic of the first operating hours category to the rate of change for power usage of the unclassified business to generate a similarity score describing a degree to which the rate of change for power usage of the unclassified business matches the rate of change power characteristic of the first operating hours category;associating the unclassified business with the first operating hours category when the similarity score exceeds a defined threshold, wherein a first subset of the set of electronic messages are maintained in the storage device in association with the first operating hours category; andcontrolling transmission of the set of electronic messages stored in a storage device, comprising: i) selecting the first subset of the set of electronic messages from the storage device for transmission to remote devices associated with the unclassified business based on the unclassified business being associated with the first operating hours category; andii) sending the first subset of the set of electronic messages to the remote devices associated with the unclassified business.

14. The non-transitory computer-readable storage medium of claim 13, wherein the rate of change for power usage is based on a difference between the minimum power consumption level and the elevated consumption level.

15. The non-transitory computer-readable storage medium of claim 13, wherein the elevated consumption level is set as a function of the minimum power consumption level.

16. The non-transitory computer-readable storage medium of claim 13, wherein associating the unclassified business with the first operating hours category comprises associating the unclassified business with the first operating hours category by pairing metadata for the first operating hours category with information identifying the unclassified business.

17. The non-transitory computer-readable storage medium of claim 13, wherein the first operating hours category is associated with a plurality of power usage profiles, the first power usage profile describing a rate of change power characteristic for a first day of a week and a power usage profile describing a rate of change power characteristic for a second day of the week.