System, method, and apparatus for data collection and aggregation

Abstract

To provide a system, and the like for aggregating and linking a diverse or disparate datasets related to pet care, resulting in an improved understanding of the needs and wishes of a pet.SOLUTION: A method includes: collecting data from one or more disparate data sources; and aggregating the data collected from the one or more disparate sources in a data lake. The method also includes clearing personal identification information from the aggregated data, and sorting the cleared data into one or more datasets based on one or more attributes of a pet or an owner of the pet. In addition, the method can include determining a pet product to help fulfill the healthcare need of the pet. Further, the method can include targeting the owner of the pet with an advertisement of the pet product.SELECTED DRAWING: Figure 1

Description

Related Applications

[0001] This application claims the benefit of priority from and relies on the contents of U.S. Provisional Patent Application No. 63 / 038568, filed June 12, 2020, the entire contents of which are incorporated herein by reference. This application is also a divisional application of Japanese Patent Application No. 2022-571801, filed June 14, 2021. [Technical field]

[0002] The present disclosure relates to the aggregation and federation of data from one or more sources, and more particularly, to the federation of pet care related data from one or more sources. [Background technology]

[0003] Currently, the digital data footprint created by pet owners continues to grow around the world. Like other consumer groups, pet owners purchase pet supplies online and in stores in a variety of forms. These pet supplies are extensive and can range from food to toys to clothing. However, pet owners are truly in a position to create digital data related to their pets beyond traditional consumer products. For example, some owners are fitting their pets with health or location tracking devices. Additionally, some owners are using services for DNA or genetic testing of their pets. These devices and services, as well as other available services used by pets, can provide unique insights about a given pet that go far beyond insights gained from traditional consumer data. However, as the sheer volume of data is collected, sculpting that data for pets and their owners is becoming increasingly difficult.

[0004] Thus, there is a continuing need in the pet care industry for devices, systems, and methods for analyzing data related to pet care, and in particular for aggregating and linking diverse sets of digital data related to pet care, which can help owners better understand their pets' needs or preferences, thereby enabling them to better care for their pets' health and wellness. Summary of the Invention

[0005] The present disclosure relates to a system, apparatus, or method for aggregating and integrating diverse data sets related to pet care to improve understanding of the needs and desires of a given pet. Certain non-limiting embodiments may include a method for meeting pet health care needs. Certain non-limiting embodiments of the method may include collecting data from one or more disparate data sources and aggregating the collected data from the one or more disparate sources into a data lake. The method may also include clearing personally identifiable information from the aggregated data in the data lake and sorting the cleared data into one or more data sets based on one or more attributes of the pet or the pet's owner. In addition, the method may include creating a pet profile based on the data included in the one or more data sets and determining pet products that help meet the pet's health care needs. Furthermore, the method may include targeting pet owners with advertisements for pet products.

[0006] In certain non-limiting embodiments, the method may further include displaying the advertisement for the pet product to the pet owner via a graphical user interface of the terminal device. The method may also include reformatting the data from the one or more disparate data sources to a uniform quality level. In addition, the method may include predicting a target audience for the advertisement for the pet product, where the target audience may include the pet owner and one or more other pet owners. In some non-limiting embodiments, the data may include at least one of first party data, second party data, or third party data. The one or more disparate data sources may include health and location tracking devices, DNA or genetic testing services, or veterinary clinic point of sale devices. The collected data may include pet health information. In other non-limiting embodiments, the aggregating, cleaning, sorting, creating, and determining steps may be performed by a consumer data platform or a data management platform. The determining or predicting step may use machine learning algorithms for predicting the target audience or determining pet products that will help meet the pet health care needs. The one or more data sets may include at least one of pet health, pet ownership, and physical or behavioral characteristics of the pet.

[0007] In certain non-limiting embodiments, a system for meeting pet health care needs may include at least one memory including computer program code and at least one processor. The computer program code, when executed by the at least one processor, may be configured to cause the device to collect data from one or more disparate data sources and aggregate the collected data from the one or more disparate sources into a data lake. The computer program code, when executed by the at least one processor, may also be configured to cause the device to clean personally identifiable information from the aggregated data in the data lake and sort the cleaned data into one or more data sets based on one or more attributes of the pet or the pet's owner. In addition, the computer program code, when executed by the at least one processor, may also be configured to cause the device to create a pet profile based on data included in the one or more data sets and determine pet products that are useful in meeting the pet's health care needs. Furthermore, the computer program code, when executed by the at least one processor, may also be configured to cause the device to target pet owners with advertisements for pet products.

[0008] According to a particular embodiment, a non-transitory computer-readable medium has encoded thereon instructions for performing a process for satisfying pet health care needs when executed on hardware. The process may include collecting data from one or more disparate data sources and aggregating the collected data from the one or more disparate sources in a data lake. The process may also include clearing personally identifiable information from the aggregated data in the data lake and sorting the cleared data into one or more data sets based on one or more attributes of the pet or the pet's owner. In addition, the process may include creating a pet profile based on the data included in the one or more data sets and determining pet products that help satisfy the pet's health care needs. Furthermore, the process may include targeting pet owners with advertisements for pet products.

[0009] The apparatus may, in certain embodiments, include a computer program product encoding instructions for processing the inspected pet product data according to a method for satisfying the pet's health care needs. Certain non-limiting embodiments of the method include collecting data from one or more disparate data sources and aggregating the collected data from the one or more disparate sources into a data lake. The method may also include clearing personally identifiable information from the aggregated data in the data lake and sorting the cleared data into one or more data sets based on one or more attributes of the pet or the pet's owner. In addition, the method may include creating a pet profile based on the data included in the one or more data sets and determining pet products that help satisfy the pet's health care needs. In some embodiments, the method may include determining pet products that help satisfy any pet service or pet product needs of the pet. Additionally, the method may include targeting the pet owner with advertisements for the pet products.

[0010] It is to be understood that both the foregoing general description and the following detailed description are exemplary and are intended to provide further explanation of the disclosed subject matter as claimed. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 illustrates a system or device for data collection or aggregation according to certain non-limiting embodiments. [Diagram 2] FIG. 1 illustrates a system for data collection or aggregation in accordance with certain non-limiting embodiments. [Diagram 3] FIG. 1 illustrates a system for data collection or aggregation in accordance with certain non-limiting embodiments. [Figure 4] FIG. 1 illustrates a collaborative system in accordance with certain non-limiting embodiments. [Diagram 5] FIG. 1 illustrates a system or method for aggregation and federation according to certain non-limiting embodiments. [Figure 6A] FIG. 1 illustrates a system or method for aggregation and federation according to certain non-limiting embodiments. [Figure 6B] FIG. 1 illustrates a system or method for aggregation and federation according to certain non-limiting embodiments. [Figure 7] FIG. 1 illustrates a system or method for aggregation and federation according to certain non-limiting embodiments. [Figure 8] FIG. 1 illustrates a graph in accordance with certain non-limiting embodiments. [Figure 9] FIG. 1 illustrates a flow chart according to certain non-limiting embodiments. [Figure 10] FIG. 1 illustrates a system according to certain non-limiting embodiments. [Figure 11] FIG. 1 illustrates an apparatus or system according to certain non-limiting embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] There remains a need to aggregate and link diverse or disparate data sets related to pet care to improve understanding of the needs and desires of a given pet. In particular, there remains a need for technology that allows for the aggregation and linkage of diverse sets of digital data to predict or determine pet supplies related to a pet's health care needs. The subject matter of the present disclosure addresses these and other needs.

[0013] For purposes of clarity, and not by way of limitation, this detailed description is divided into the following subsections.

[0014] A.Definition B. Data Collection or Aggregation C. Data integration and audience or product predictions D. Results of the Systems or Methods Described Herein E. Flowcharts of the methods described herein F. Diagrams of the Systems and Apparatus Described Herein

[0015] A.Definition The terms used herein generally have their ordinary meaning in the art, within the context of this disclosure and in the specific context in which each term is used. Particular terms are explained below or elsewhere in the specification to provide further guidance in describing the compositions and methods of the present disclosure, and how to make and use the same.

[0016] As used in this specification and the appended claims, the singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a compound" includes a mixture of compounds.

[0017] The term "animal" or "pet" as used in accordance with the present disclosure refers to domestic animals, including but not limited to, domestic dogs, domestic cats, horses, cows, ferrets, rabbits, pigs, rats, mice, gerbils, hamsters, goats, and the like. Domestic dogs and domestic cats are specific non-limiting examples of pets. The term "animal" or "pet" as used in accordance with the present disclosure can further refer to wild animals, including but not limited to, bison, elk, deer, venison, ducks, poultry, fish, and the like.

[0018] As used herein, the terms "comprises," "comprising," or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, system, or apparatus that includes a list of elements does not include only those elements, but may include other elements that are not expressly listed or that are inherent to such process, method, article, or apparatus.

[0019] In the detailed description of this specification, references to "embodiment", "an embodiment", "one embodiment", "in various embodiments", "certain embodiment", "some embodiment", "other embodiment", "certain other embodiment", etc. indicate that the described embodiment may include a particular feature, structure, or characteristic, but not all embodiments may necessarily include the particular feature, structure, or characteristic. Moreover, such phrases do not necessarily refer to the same embodiment. Furthermore, when a particular feature, structure, or characteristic is described in relation to an embodiment, it is submitted that it is within the knowledge of a person skilled in the art to affect such feature, structure, or characteristic in relation to other embodiments, whether or not explicitly described. After reading the description, it will be apparent to a person skilled in the art how to implement the present disclosure in alternative embodiments.

[0020] Generally, terms can be understood at least in part from their usage in context. For example, terms such as "and", "or", or "and / or" as used herein can include various meanings that can depend at least in part on the context in which such terms are used. Typically, when "or" is used to relate a list such as A, B, or C, it is intended to mean A, B, and C, which are used herein in an inclusive sense, as well as A, B, or C, which are used herein in an exclusive sense. Furthermore, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in a singular sense, or can be used to describe a combination of features, structures, or characteristics in a plural sense, depending at least in part on the context. Similarly, terms such as "a", "an", or "the" can also be understood to convey a singular use or a plural use, depending at least in part on the context. In addition, it can be understood that the term "based on" is not necessarily intended to convey an exclusive set of factors, but instead can allow for the existence of additional factors not necessarily explicitly described, again depending at least in part on the context.

[0021] The term "data" includes, but is not limited to, any type of digital or non-digital data related to, for example, a pet or pet supplies. In certain embodiments, the data may be any measurements related to the pet's health, breed, physical attributes, disease, diagnosis, location, activity, nutritional intake, prescription, wellness plan, genetic information, and / or deoxyribonucleic acid (DNA), or any other information related to the pet. In some other embodiments, the data may include any information related to the habits, purchases, or activities of the pet owner, whether or not related to the pet itself. The data may also include searching, browsing, or purchasing habits on one or more Internet websites.

[0022] The term "first-party data" may include data that is collected and / or owned directly by a business. First-party data may be collected, for example, from consumers who use products or services offered by a given business.

[0023] The term "third-party data" may include data collected by other companies. Third-party data may be accessed or purchased using the data management platform. For example, a company may purchase third-party data to expand its target audience.

[0024] The term "pet products" includes, but is not limited to, any type of product, service, or equipment designed, manufactured, or used by pets. For example, pet products can be toys, chewables, food, clothing, collars, medications, and / or health or location tracking devices. In another example, pet products can include genetic or DNA testing services for pets.

[0025] The term "pet owner" may include any person, organization, or collection of people responsible for the care of a pet.

[0026] The term "digital side platform" can be a system or software that facilitates the purchase of digital advertisements. In other words, a "digital side platform" allows advertisers to purchase digital advertisements, also known as impressions, across a range of websites. Advertisements can be targeted to specific users based on data or information related to the users. For example, advertisements can be specifically targeted to pet owners based on data related to the pets. In certain embodiments, the digital side platform can help manage an inventory of available ad space provided by publishers.

[0027] The term "real-time bidding" may refer to a programmed auction that allows buyers to purchase available advertising space. In certain embodiments, real-time bidding between one or more buyers may be managed using a digital side platform.

[0028] The term "data management platform" may be a system or software used to collect, organize, manage, and / or activate large sets of data from disparate sources. A data management platform may include, for example, one or more of data collection, integration, organization, activation, and / or analysis. For example, a data management platform may use one or more artificial intelligence or machine learning algorithms to process and analyze data sets. In some embodiments, the data management platform collects anonymous web and / or digital data. Records in the data management platform may be updated individually using a batch process.

[0029] The term "customer data platform" can be a system or software used to collect data and create a unified customer database accessible to other systems. In certain embodiments, the customer data platform can collect first-party data from one or more sources, clean and / or reformat the data, and aggregate or combine the data to form a single customer or pet profile. Thus, the customer data platform can collect data linked to an identifiable person, consumer, or pet. In some embodiments, the customer data platform can collect data continuously or discretely to keep the profile up-to-date and accurate.

[0030] The term "data lake" may be a database, a data library, a data repository, or any other storage medium. In certain embodiments, a data lake may be centralized or decentralized. The data maintained in a data lake may be structured, unstructured, or semi-structured. For example, a data lake may include raw, first-party data that may be considered unstructured.

[0031] The term "personal data" may be any information that may be used to infer or determine the identity of a person or pet. In certain embodiments, personal data may be referred to as "personally identifying information" or "personally identifiable information." For example, name, government identification number, date and place of birth, mother's maiden name, and / or biometric records may be considered personal data. Other personal information may be an Internet Protocol address, geolocation information, and / or a patient ID provided by a medical facility. Any other information that may be associated with a person or pet, such as medical, educational, financial, and / or employment information, may also be considered personal data.

[0032] The term "geofence zone", "geofence location", or "geofencing" may be a user-selected, pre-determined, pre-selected, or known geographic area or location. A geofence zone or location may be used to define a geographic area or location familiar to a pet or animal, such as the residence of a pet owner or caregiver. In some examples, a geofence zone or location may be determined using a Global Positioning System (GPS) or Global Navigation Satellite System (GLONASS) receiver to determine the latitude and longitude of a device. In other examples, a geofence zone, location, or presence may be determined using a pre-determined, pre-selected, or known service set identifier (SSID) of a wireless land area network (WLAN) network. When a geofence zone or location is determined using an SSID scan or any other characteristic or measurement associated with a WLAN, the geofence zone or location may be referred to as a "beacon zone". In other words, in certain non-limiting embodiments, a client station may be determined to be in a given zone or location when it is within the transmission range of a given access point. To determine whether a client station is located inside or outside a geofenced location or zone, the client station may transmit probe requests and receive probe responses from access points (APs) of the WLAN network.

[0033] The term "terminal device" refers to, for example, but not limited to, a personal computer, a laptop computer, a workstation, a television, a mobile device, a terminal device, or any other user equipment. In some non-limiting examples, the terminal device may include a graphical user interface used to display advertisements related to pet supplies. In certain embodiments, a web-based application may be installed on the user's terminal device. In other non-limiting embodiments, the terminal device may be a microelectromechanical system (MEMS) device or a pet tracking device having an accelerometer.

[0034] B. Data Collection or Aggregation In certain non-limiting embodiments, data may be collected from one or more sources. The collected data may then be aggregated and coordinated to create a user, customer, or pet profile. The data may include first-party data, second-party data, and / or third-party data. For example, first-party data may be collected from health and location tracking devices, DNA or genetic testing services, and / or veterinary clinic point-of-sale (POS) devices.

[0035] FIG. 1 illustrates a system or apparatus for data collection or aggregation according to certain non-limiting embodiments. In particular, FIG. 1 illustrates a pet health and / or location tracking device 110, which may be a source from which data can be collected. The pet health and / or location tracking device 110 may be a computing device used to monitor and / or track the activity of a pet. In some non-limiting embodiments, the pet health and / or location tracking device 110 may be configured to collect data generated by various hardware or software components. Examples of hardware or software components include a global positioning system (GPS) receiver and / or one or more sensors or transducers, such as accelerometers, gyroscopes, or any other device or component used to record, collect, or receive data regarding the movement or activity of a pet wearing or otherwise carrying the tracking device 110. The pet health and / or location tracking device 110 may include one or more processors, memories, transducers, and / or any other hardware components used to receive, collect, process, store, and / or transmit data.

[0036] Examples of pet health and / or location tracking devices 110 are described in U.S. Patent Application No. 16 / 570,771, U.S. Patent Application No. 16 / 182,057 (now U.S. Patent No. 10,708,709), U.S. Patent Application No. 15 / 291,882 (now U.S. Patent No. 10,142,773), U.S. Patent Application No. 15 / 287,544, U.S. Patent Application No. 14 / 231,615 (now U.S. Patent No. 10,420,401), U.S. Provisional Applications Nos. 62 / 970,575, 62 / 867,226, and 62 / 768,414, U.S. Design Application No. 29 / 696,311, U.S. Design Application No. 29 / 696,315, and International Patent Applications Nos. PCT / US17 / 55220 and PCT / US17 / 55224. The above referenced applications and patents are incorporated herein by reference in their entirety.

[0037] In certain non-limiting embodiments, the health and location tracking device 110 may initially collect information from retail channels 101 and / or consumer data 102. Information from retail channels 101 may be any information or data related to a merchant or retailer from which the health and location tracking device 110 is purchased. Retail channels 101 may include, for example, one or more of a mass merchandiser, a club store, a drug store, a health store or pharmacy, a pet specialty store, an e-commerce store, or a pet related store. The health and location tracking device 110 may be purchased online, through a retailer or merchant, or through any other means. The consumer data 102 may be any information, personal or otherwise, related to either the pet owner purchasing the tracking device 110 or the pet wearing the tracking device 110. The consumer data 102 may be ascertained from the pet owner during initial startup or setup of the tracking device 110.

[0038] The consumer data 102 may include, for example, household income, home ownership, spending habits, geographic location, lifestyle attributes, weather patterns or information, environmental data, and household purchasing habits. Other consumer data 102 may include demographic, lifestyle, vehicle data, census, creditworthiness, socio-economic data, consumer attitudes, behaviors, preferences, purchases, lifestyle, health, wellness, finances, and / or wealth. In certain non-limiting embodiments, the consumer data 102 may include loyalty card data that many retailers use to identify individuals without regard to bidding. Loyalty card data may include details regarding purchased items. In some non-limiting embodiments, the consumer data 102 may include transaction totals from payment card issuers, and / or panel data from consumer panels that scan all purchases at retail locations. The panel data may be used to plan sales. In other non-limiting embodiments, the consumer data 102 may include exposure data, print circulation data from newspapers and magazines, mobile phone and radio data, and / or media data from Nielsen. Exposure data may include publisher data such as page views, stores, length of time viewing a given webpage or website. Nielsen media data may include television audience panel data. In some other non-limiting embodiments, consumer data 102 may include purchase data, which may include any data related to consumer purchases. For example, purchase data may include frequent shopper card data, such as UPC scans or card IDs, for which promotions and messages may be triggered based on shopper purchasing insights. Promotions and / or messages may be delivered at the point of sale, for example, via a full-color high-speed printer.

[0039] The health and location tracking device 110 may collect geographic location or network connectivity information. The network connectivity information may be used to determine the location of the health and / or location tracking device 110 as well as other network metrics that may provide information about the pet or pet owner. In a specific non-limiting embodiment, the health and location tracking device 110 may collect information such as Global System for Mobile communications (GSM) frequencies 121, GPS tracking 122, WLAN, fourth generation (4G) or fifth generation (5G) connectivity 123, geofencing 124, park locations 127, retail store locations 128, and / or boarding locations 129. GSM is a standard developed by the European Telecommunications Standards Institute (ETSI) to define protocols for second generation (2G) digital cellular networks. The retail store locations 128 may include the location and / or identity of a retail store visited by the pet or pet owner. The boarding locations 129 may include the location and / or identity of a pet boarding facility. Park locations 127 may include outdoor or indoor parks visited by pets wearing health and location tracking devices 110 .

[0040] Other information collected by the health and location tracking device 110 may include pet activities 125. Pet activities 125 may include any body movement detectable by the health and location tracking device 110. For example, pet activities 125 may include scratching, clawing, licking, walking, drinking, eating, sleeping, and wagging, and / or any other body movement associated with an action performed by a pet. The health and location tracking device 110 may also be used to identify pet activities 125, such as a pet jumping around, excitedly moving around for food, actively eating, and / or drinking from a bowl on a wall. Pet activities 125, also referred to as pet behaviors, may be specific to a type of pet. For example, there may be behaviors that are attributed to cats and other behaviors that are attributed to dogs. Some behaviors may be specific to cats or dogs, although one or more behaviors may overlap. One or more behaviors may be, or may be indicative of, a symptom associated with a health condition or disease, in certain embodiments. In some non-limiting embodiments, pet scratches 126 may be collected separately from other pet activity.

[0041] The raw data collected from the health and location tracking devices 110 can be forwarded to the data lake 130. The data can then be forwarded to the data consent framework 140. The data consent framework 140 can help ensure that the processing of the data complies with regulatory guidelines. After the data is collected and cleaned, the fidelity and accuracy of the data can be ensured. For example, the data consent framework 140 can be a framework created by the Internet Advertising Bureau (IAB) that uses Transparency and Consent Strings (TC Strings). The TC Strings can be used to encapsulate the relevant details of how the transparency and consent are established and can be encoded to apply to the purpose, special purpose, features, and special features. In particular, the TC Strings can encapsulate and encode all information disclosed to the user and / or an expression of the user's preferences for the processing of the user's personal data under the General Data Protection Regulation (GDPR) or other international, national, state, or local regulations. A Consent Management Platform (CMP) can be used to capture the information into an encoded, compact, HTTP transferable string that can enable transparency and communication of consent information to one or more entities or vendors that process the user's personal data, including, for example, the California Consumer Privacy Act. The entity or vendor can then decode the TC string and determine whether it can process the user's personal data for its purposes based on existing international, national, state, or local regulations.A simple string data format may enable a CMP to persistently retrieve user preferences and forward that information to one or more entities or vendors.

[0042] In certain non-limiting embodiments, the TC string may include one or more of general metadata, user consent, legitimate interest, published restrictions, published transparency and consent, out-of-band legal basis, and / or disclosure of specific jurisdictions. General metadata may include details about the TC string, such as the encoding version, last update, initial creation time, details about the terms of the transparency and consent values, such as a global vendor list, and / or a marker indicating the CMP used. User consent may be a user expression of consent given to process the user's personal data on a per purpose or per vendor basis. Legitimate interest may be, for example, a record of the CMP establishing legitimate interest transparency for a vendor or purpose, and / or whether the user has exercised a right to object. Publisher transparency and consent may be a segment of the TC string that a publisher can use to establish transparency with the user or receive consent from the user to the user's own legal basis to process personal data and / or share personal data with a vendor. An out-of-band lawful basis may be at least two segments used to represent a vendor's use of a lawful basis outside of the framework to process personal data. For example, a first segment may be a list of vendors disclosed to the user, while a second segment may be a list of vendors that may allow the disclosed vendors to use an out-of-band lawful basis.

[0043] Once processed through the data outlet framework 140, the information can be forwarded to a predictive tool 530, as shown in FIG. 5. The predictive tool 530 can be a customer data platform (CDP) and / or can utilize artificial intelligence or machine learning to federate the data and create one or more consumer or user profiles. The data federation can utilize an identity resolution process. The predictive tool 530 can test, for example, the predictability of dog owners who have visited a veterinarian in the past year, the predictability of one or more dog owners who have purchased skin treatment products in the past year and / or visited a veterinarian in the past year. In yet another example, the predictive tool 530 can test the predictability of one or more dog owners who belong to a dog toy category, purchased skin treatment products in the past year, and / or visited a veterinarian in the past six months or any other period. Different combinations of data points can be used to predict which will provide the best, largest, or most effective response to the advertisement from consumers and / or impact on the ultimate sale.

[0044] In some non-limiting embodiments, the prediction tool 530 can use analysis of covariance (ANCOVA), which can be a general linear model utilizing analysis of variance (ANOVA) and / or regression. ANCOVA can be used to assess whether the mean of a dependent variable (DV) is equal across levels of a categorical independent variable (IV), which can be referred to as a factor or treatment, while statistically controlling for the effects of other continuous variables that are not of primary interest, which can be referred to as covariates (CV) or interfering variables. ANCOVA can be used when there are differences between baseline groups, but can also be used in pre-test or post-test analyses when regression to the mean can affect post-test measurements.

[0045] In certain non-limiting embodiments, ANCOVA can be used as an extension of multiple regression analysis. Similar to regression analysis, ANCOVA can be used to evaluate how independent variables affect dependent variables. ANCOVA can, in non-limiting embodiments, remove any effects of covariates. For example, ANCOVA can be used to determine whether a new drug works against depression, using three treatment groups and one control group. ANCOVA can be used to determine whether a treatment works while controlling for other factors that may affect outcomes, such as family life, work status, or drug use. In other non-limiting embodiments, ANCOVA can be used as an extension of ANOVA to control for covariates and / or test combinations of categorical or continuous variables as predictors. In some non-limiting embodiments, the covariate can be the variable of interest, rather than the variable being controlled.

[0046] ANCOVA can be used to test or explain within-group variance. For example, ANCOVA can take the unexplained variance from the ANOVA test and explain the unexplained variance with confounding variables or one or more other covariates. A weak covariate can reduce the statistical power of the test, while a strong covariate can increase the statistical power of the test. In a specific non-limiting embodiment, the following process or method can be performed: performing a regression between an independent variable and a dependent variable, identifying residual values ​​from the results of the performed regression, performing an ANOVA on the residual values, and inserting the assumption of ANCOVA. This assumption can include at least two independent variables as categorical variables, and the dependent variable and the covariate can be continuous, as measured on an interval scale or a ratio scale, and / or ensure that the observations are independent.

[0047] After performing the ANCOVA analysis, a p-value can be calculated. In certain embodiments, the p-value can represent the probability of obtaining a result at least as significant as the observed result of a statistical hypothesis test where the null hypothesis can be assumed to be correct. In certain non-limiting embodiments, the p-value can be used as a surrogate for a rejection point that provides a minimum level of significance at which the null hypothesis can be rejected. The p-value can be inversely proportional to the support that the alternative hypothesis is correct. That is, the smaller the p-value, the higher the probability that the alternative hypothesis is correct. In certain non-limiting embodiments, a calculated p-value that indicates a confidence level of about 80% can be selected. In alternative embodiments, a calculated p-value that indicates a confidence level of more than about 80% can be selected. In such non-limiting embodiments, the calculation of the p-value can be performed multiple times after the ANCOVA analysis. In further non-limiting embodiments, a calculated p-value that indicates a confidence level of less than about 80% can be selected. In alternative embodiments, a new ANCOVA analysis can be performed after the calculation of a p-value that indicates less than the desired confidence level. In further alternative embodiments, it is not necessary to perform a p-value calculation at all.

[0048] In certain non-limiting embodiments, data cleansing or data cleaning can be utilized. Data cleansing or data cleaning can be used to detect, correct, and / or remove corrupted or inaccurate records from a record set, table, or database. For example, data cleansing or data cleaning can include identifying incomplete, incorrect, inaccurate, or irrelevant portions of data and / or replacing, correcting, or removing dirty or rough data. Data cleansing or data cleaning can be performed interactively with a data writing tool or as a batch process through scripting. In certain non-limiting embodiments, data cleansing or data cleaning may not result in changes to the data. For example, data cleansing or data cleaning can detect that the data is free of errors. Alternatively, but not by way of limitation, data cleansing or data cleaning can be configured to ignore certain errors. Additionally, data cleansing or data cleaning can be configured to identify commonly misidentified errors, for example, to identify data that is often identified as an error but should still be included in the resulting data set.

[0049] The cleansed data set can be made consistent with other similar data sets in the system. The detected or removed inconsistencies may have originally been caused by, for example, user input errors, corruption in transmission or storage, or different data dictionary definitions of similar entities in different stores. In some non-limiting embodiments, data cleansing or data cleaning can differ from data validation in that validation can be performed at input rather than on a batch of data, meaning that data is rejected from the system at input. Data cleansing or data cleaning can include, for example, removing typos or validating and / or correcting values ​​against a known list of entities. Validation can be strict, such as rejecting any address that may not have a valid zip code, or can be non-strict, such as correcting records that partially match existing or known records. In certain non-limiting embodiments, data cleansing solutions can clean data by cross-checking with validated data sets. Data cleansing can also include data enhancement, where data can be made more complete by adding relevant information. For example, one or more phone numbers can be added to an address. In some other embodiments, data cleansing can include data harmonization (or normalization), which can include consolidating data from different file formats, naming conventions, and columns, and / or converting the data into one cohesive data set. For example, abbreviations such as st, rd, etc. can be expanded to street, road, etc.

[0050] An identity may refer to an anonymous profile of a consumer collected across one or more user equipment or devices. For example, building an individual's identity may include combining data collected from laptop browsers, cell phones, email subscriptions, and / or offline purchases into a pool. The combined data may then be anonymized so that marketers, or any other entity or person with access to the identity, do not have access to the consumer's identifying information. Personal identifying information may be, for example, name, email address, phone number, address, etc. In some non-limiting embodiments, other information related to the consumer, such as the consumer's gender, age, location, and / or purchasing or browsing activities, may be included as part of the identity, which may be vetted by marketers or any other entity or person with access to the identity. In certain non-limiting embodiments, identity resolution may be the compilation of all information into one profile. For example, identity resolution may indicate that a consumer conducts business activities on one browser, but personal activities, such as personal shopping, on a second, different browser. In yet another example, identity resolution may indicate that a consumer's mobile device contains more data or better reflects the consumer's habits during non-work time, such as the television shows the consumer likes or the personal products the consumer searches for on one or more internet browsers. Identity resolution provides a complete picture of the consumer to marketers, or any other entity or person with access to identity resolution. Thus, identity resolution may connect many different identifiers from multiple platforms and / or devices, enabling person-based targeting, personalization, or measurement. In some non-limiting embodiments, identity resolution may be built or aggregated in real time.

[0051] 2 illustrates a system for data collection or aggregation according to certain non-limiting embodiments. In particular, FIG. 2 illustrates a DNA or genetic testing service 210 for pets. The DNA or genetic testing service 210 may be one of the sources from which data may be collected and aggregated. In certain non-limiting embodiments, the DNA or genetic testing service 210 may first collect information from retail channels 201 and / or consumer data 202. The retail channels 201 and consumer data 202 may be similar to the retail channels 101 and consumer data 102 illustrated in FIG. 1.

[0052] The DNA or genetic testing services 210 may be in the form of an in-home test kit provided to the pet owner and / or a test performed by a veterinarian. In those embodiments involving an in-home test kit, the test kit may be purchased by the pet owner. The pet owner may then use one or more swabs from the test kit to collect skin cells from the pet's mouth. For example, the pet owner may swab the inside of the pet's cheek. After the pet owner collects the sample, the pet owner may mail the sample to a testing laboratory for analysis. In certain non-limiting embodiments, the pet owner may be asked to activate the in-home test kit using the internet. As part of the activation, the pet owner may be asked to answer one or more questions related to the pet or the pet owner. These answers may be collected as consumer data 202.

[0053] The DNA or genetic testing service 210 may be used to determine and collect various biological, physical, health, or pedigree information related to the pet. For example, the pet's breed 221, potential diseases 223, health conditions 224, DNA information 225, physical characteristics 226, the pet's relatives 227, and / or pedigree 229 may be collected. Other information may include consumer direct sales 222, bid payments 228, and / or test kits 231. For example, consumer sales 222 may include any product or service sold on an online website or in a store. Bid payments 228 may include information collected from the purchase of a product or service using a payment card. Test kits 231 may be DNA or disease test kits. The raw data collected from the DNA or genetic testing service 210 may be transferred to a data lake 240. The data may then be transferred to a data outlet framework 250, which may be similar to the data outlet framework 140. Once processed through the data outlet framework 250, the information can be forwarded to a predictive tool 530, as shown in Figure 5. The predictive tool 530, which may be a CDP, can then federate the data and create one or more consumer or user profiles.

[0054] The pet breeds 221 may include dog breeds, cat breeds, or any other pet or animal breed. Some examples of dog breeds include Affenpinscher, Afghan Hound, Afghan Shepherd, Aidi, Airedale Terrier, Akbash, Akita, Alano Español, and Alaskan Husky. Some examples of cat breeds include Abyssinian, Aegean, American Bobtail, American Curl, American Shorthair, American Wirehair, Aphrodite Giant, Arabian Mau, and Asian Cat. The potential diseases 223 may be diseases specific to dogs, cats, or any other pets. For example, dog diseases may include abnormal elbow development, abnormal eyelids, abnormal growth of the lower intestine, abnormal health rhythms, abnormal development of molar teeth, abnormal passages between arteries and veins, abnormal passages between the oral cavity and nasal cavity, abnormal protein production, abnormal urine flow due to bladder dysfunction, or any other dog-related disease. Cat diseases may include, for example, abnormal cavity inflammation, abnormal diaphragm opening, abnormal eyelids, abnormal growth in the lower intestine, abnormal heart rhythm, abnormal passageways between arteries and veins, abnormal passageways between the oral and nasal cavities in cats, abnormal protein production, abscesses, or any other cat-related disease.

[0055] FIG. 3 illustrates a system for data collection or aggregation according to certain non-limiting embodiments. In particular, FIG. 3 illustrates information obtained from a pet health care facility, such as a pet medical facility or hospital. The information can be obtained from a veterinary clinic POS device 310 or any other device in the veterinary clinic with access to pet data, such as pet medical charts or records. The data collected or aggregated by the veterinary clinic POS device 310 can be various biological, physical, or health data related to the pet. For example, pet attributes 321, multiple pets 322, such as the number of pets owned by a given pet owner, pet prescriptions 323, such as any medications, drugs, or treatments prescribed for the pet, pet medical or health exam 324, pet health records 325, pet nutrition information 326, such as any information regarding the pet's nutritional consumption, pet adherence 328, wellness plan 331, and / or laboratory diagnosis 332. Pet adherence 328 can be the pet's adherence to a medical treatment or routine prescribed by a veterinarian and / or behavioral adherence to the pet's owner. Other collected data can include household information, pet purchases 327 using the POS device, ad responses 330 to ads shown on the POS device or at the veterinary clinic, or payment type 329 whether credit, debit, store credit, virtual currency, online payment, cash, and / or pet insurance and co-payment for the pet's owner. Pet purchases 327 can include, for example, pet treats or pet food, toys, nutrition, snacks, clothing, collars, leashes, harnesses, crates, kennels, apparel, medicines, beds, flea and tick products, gates, doors, health and wellness products, bowls, Internet of Things devices, genetic testing products, insurance, wellness plans, and / or tracking devices.

[0056] Ad responses 330 may include, for example, responses to post campaign analysis (PCA). In certain non-limiting embodiments, marketing or advertising campaigns may use ad responses to evaluate the performance of the campaign toward building brand awareness, influencing consideration, driving action and / or engagement. Metrics used to evaluate the effectiveness of a promotional or marketing campaign may be, for example, cost per value view (CPVV), percentage of target audience reached, frequency, which may be the time an advertisement is served to consumers across one or more different channels, view-through rate, which may be a measure of the percentage of a video viewed, active earned media, which may be a measure of where people actively share content, and / or brand buzz, which may relate to the number of conversations that take place around a brand involved in the campaign. In some non-limiting embodiments, metrics used to evaluate influencing consideration and / or driving action may include, for example, quality score, click-through rate, impressions, average position, and / or conversion rate, which may be the number of people who click on an advertisement and perform a desired action on the advertised website. In other non-limiting embodiments, metrics used to evaluate driving action and / or engagement may include, for example, total traffic, traffic by channel, bounce rate, which may be the percentage of visitors who leave before taking a desired action, conversion, which may be a quantifiable measure of how well visitors perform a desired action, or data capture, which may be the quality of data obtained from visitors arriving on a website.

[0057] The POS devices may include electronic cash registers and / or software to reconcile data collected from daily purchases. Retailers can increase functionality by installing a network of data capture devices such as card readers or barcode scanners. For example, consumers can be identified by the POS by using customer or loyalty cards, email addresses, phone numbers, or through payment card information. In some non-limiting embodiments, the POS devices can be used to monitor inventory and purchasing trends, help retailers avoid customer service issues such as out-of-stock sales, and align purchasing and marketing with consumer behavior. The collected data can then be forwarded to the data lake 340 for aggregation. The data outlet framework 350 can then receive or retrieve the aggregated data from the data lake 340.

[0058] In certain non-limiting embodiments, the data collected from one or more of the sources shown in FIG. 1, FIG. 2, and / or FIG. 3 may be health care data that includes personal or identifiable information (PII) of the pet or the pet's owner. For example, DNA 225 of FIG. 2 and pet health records 325 of FIG. 3 may include PII. This PII may be removed before or after aggregation of the data in the data lakes 130, 240, and 340. In certain embodiments, the data outlet framework 140, 250, and / or 350 may be a CDP used to remove PII from collected or aggregated data. For example, the consumer data may be brought into an area with restricted access in data / network security. Names and / or addresses may then be removed and a pseudonymous identity may be assigned. The consumer data may then be used with the pseudonymous identity. In some other embodiments, the data outlet framework 140, 250, and / or 350 may be a data management platform (DMP).

[0059] For example, as described above, the data outlet framework 140, 250 and / or 350 can be used to remove PII from collected or aggregated data. In certain non-limiting embodiments, the PII can be transmitted using data or network security to areas with limited access, such as within a marketer's or entity's internal network. Names, addresses, or any other PII can be removed and a pseudonymous ID can be assigned. Use of the consumer data can be made using the pseudonymous ID rather than the PII. The pseudonymous ID can then be matched to one or more third parties, for example, using a SHA-256 cryptographic hashing algorithm.

[0060] A cryptographic hash, which may also be referred to as a digest, may be a type of signature for a text or data file. For example, the SHA-256 cryptographic hash algorithm may generate a nearly unique 256-bit (32-byte) signature for text. A hash, in certain non-limiting embodiments, is not encrypted, meaning that it cannot be decrypted back to the original text. Rather than comparing the original text, hashed versions of the text may be compared to each other.

[0061] Any other data, whether first party data, second party data, and / or third party data, may be collected and aggregated. Data may include, for example, animal symptoms, patient observations, health reports, laboratory results, treatment plans, nutritional records, activity-based information, animal genetic information, interest-based reading material by the pet owner, media exposure by the pet owner, purchasing habits by the pet owner, spending by the pet owner, and / or owner insurance policies.

[0062] After being collected and / or aggregated, the data in the data lakes 130, 240 and 340 may be categorized into datasets based on one or more attributes. An attribute may be a category or classification that describes each dataset. For example, a dataset may be attributed to the health of the pet, the pet owner such as consumer data, physical or behavioral characteristics of the dog or cat, and / or any other attribute. Health datasets may include information related to veterinary clinics and veterinary hospitals such as consumer pet ownership data, diagnoses, number of visits in a given time period, prescriptions, pet body condition scores, cat age ranges, dog age ranges, cat age categories, and / or dog age categories. A pet body condition score may be the pet's version of a human body mass index. In certain non-limiting embodiments, a pet body condition score may be a determination made by a veterinary professional indicating a classification of underweight, underweight, ideal weight, overweight, or obesity. For example, a pet's body condition score can range from 1 to 5, where 1 (1 / 5) is very underweight or underweight, 2 (2 / 5) is underweight, 3 (3 / 5) is ideal weight, 4 (4 / 5) is overweight, and 5 (5 / 5) is obese. In another example, a pet's body condition score can range from 1 to 9, where 1 (1 / 9) is underweight, 2 (2 / 9) is very underweight, 3 (3 / 9) is underweight, 4 (4 / 9) is underweight, 4.5 to 5 (4.5 or 5 / 9) is ideal weight, 6 (6 / 9) is overweight, 7 (7 / 9) is severely overweight, 8 (8 / 9) is obese, and 9 (9 / 9) is severely obese.

[0063] In certain non-limiting embodiments, a score of 1 / 5 or 1 / 9 can be assigned to pets with prominent ribs, spine or pelvis bones, pets that show reduced muscle mass and / or have severe abdominal wrinkles and dramatic waistlines. A score of 1.5 / 5 or 2 / 9 can be assigned to pets with visible ribs, spine or pelvis bones, only slight reduction in muscle mass, and / or severe waistlines and abdominal wrinkles. A score of 2 / 5 or 3 / 9 can be assigned to pets with easily palpated and partially visible ribs, pelvis or spine, and / or severe waistlines and abdominal wrinkles. A score of 2.5 / 5 or 4 / 9 can be assigned to pets with easily palpated but not visible ribs, pelvis or spine, and / or obvious waistlines and abdominal wrinkles. A score of 3 / 5 or 5 / 9 can be assigned to pets whose ribs, pelvis or spine are palpable, have a thin layer of fat covering, the waistline and abdominal folds are evident but have a more gentle curve and are not severe, and / or have minimal abdominal fat pads in front of the hind legs. A score of 3.5 / 5 or 6 / 9 can be assigned to pets whose ribs, spine or pelvis have a slight layer of fat that is more difficult to palpate, abdominal folds are present but minimal, the waistline is visible but not prominent, and / or have minimal fat pads. A score of 4 / 5 or 7 / 9 can be assigned to pets whose ribs are covered with a heavy layer of fat that requires finger pressure to feel, the spine or pelvis is difficult to feel, the waistline is not evident, abdominal folds are slightly visible, and / or have moderate abdominal fat pads. A score of 4.5 / 5 or 8 / 9 can be assigned to ribs, pelvis and spine covered by a thick layer of fat, palpable with extreme pressure, and / or with no abdominal crease or waistline. A score of 5 / 5 or 9 / 9 can be assigned to ribs and spine not palpable under a thick layer of fat, abdominal distension projecting downward (which may be the opposite of an abdominal crease), an outward or protruding waistline, caudal-cephalic fat deposits covering the legs, face or pelvis, and / or extensive abdominal fat pads and a pendulous abdomen.In some non-limiting embodiments, a BCS of 4.5 or 7 / 9 may correlate to 30% body fat, or any other body fat percentage.

[0064] Age ranges for dogs, also referred to as dog life stages, can be classified as young (5 years or younger), middle-aged (greater than 5 years and less than 9 years), senior (greater than 9 years and less than 13 years), and very senior (greater than 13 years). In some other non-limiting embodiments, life stages for dogs can be classified as puppies (newborn until reproductive maturity), juveniles (reproductively mature, still growing), adult dogs (complete growth, structurally and socially mature), mature (middle-aged to about the last 25% of expected lifespan, which may be a time frame around the expected half-life of the breed), senior (maturity to expected lifespan, about the last 25% of expected lifespan), and / or geriatric (beyond expected lifespan). Age ranges for cats, also referred to as cat life stages, can be kittens (birth to 6 months), juveniles (7 months to 2 years), newborns (3 to 6 years), matures (7 to 10 years), senior (11 to 14 years), and geriatrics (over 15 years). A given period of visits can be 3 months, 6 months, 12 months, 24 months, 36 months, or any other period ranging from 0 to 144 months. In certain non-limiting embodiments, a kitten can be 0 to 6 months, a juvenile can be 6 months to 2 years, a primary cat can be 3 to 6 years, a mature cat can be 7 to 10 years, and / or a senior cat can be 11 years or older.

[0065] The pet ownership dataset may include any information related to pet owners, such as cat or dog ownership counts, meaning the number of cats or dogs owned by a given pet owner, the age of the owner, any other consumer related data, or any other demographic information related to the pet owner. Consumer related data may include, for example, household income, home ownership, spending habits, geolocation information, lifestyle attributes, weather patterns, environmental data, and / or household purchasing habits. In some non-limiting embodiments, the physical or behavioral characteristics of the dog or cat dataset may include, for example, activity data, daily scratching time, nutritional consumption, bionomics data, and / or genetics data and location data. One or more databases may include partial overlap, meaning that there may be some common data included in multiple databases.

[0066] C. Data integration and audience or product predictions As mentioned above, in certain non-limiting embodiments, data federation can be performed or done using identity resolution. An identity can refer to an anonymous profile of a consumer collected across one or more user equipment or devices. For example, building an individual's identity can include combining data collected from laptop browsers, cell phones, email subscriptions, and / or offline purchases into a pool. In this case, the combined data can be anonymized so that marketers, or any other entity or person with access to the identity, do not have access to the consumer's identifying information. Personal identifying information is, for example, name, email address, phone number, address, etc. In some non-limiting embodiments, other information related to the consumer, such as the consumer's gender, age, location, and / or purchasing or browsing activity, can be included as part of the identity, which can be scrutinized by marketers or any other entity or person with access to the identity.

[0067] Identity resolution can be the compilation of all information into one profile. For example, identity resolution can indicate that a consumer performs business activities on one browser, but personal activities such as personal shopping on a second, different browser. In yet another example, identity resolution can indicate that a consumer's mobile device contains more data or better reflects the consumer's habits during non-work time, such as the television shows the consumer likes or the personal products the consumer searches for on one or more internet browsers. Identity resolution provides a complete picture of the consumer to marketers, or any other entity or person with access to identity resolution. Thus, identity resolution can connect many different identifiers from multiple platforms and / or devices, enabling person-based targeting, personalization, or measurement. In some non-limiting embodiments, identity resolution can be built or aggregated in real time.

[0068] In other non-limiting embodiments, data federation can be performed based on device ID federation rather than using identity resolution. Device ID federation can match a list of cookie IDs, such as a pet care ID, to one or more mobile device IDs, such as an Identifier for Advertiser (IDFA) or Google or Android advertising identification (GAID). A probabilistic device graph can be used as part of device ID federation. In some non-limiting embodiments, a deterministic graph can be used to match IDs obtained from multiple providers and indexed to the same ID. If both the probabilistic graph and the deterministic graph indicate device linking, the device ID linking is said to be a true positive, or an exact match.

[0069] In some non-limiting embodiments, the probabilistic graph may show a link without the deterministic graph showing a similar device link. Such embodiments may occur when the deterministic graph does not recognize one or more device IDs included in the link. If the deterministic graph cannot recognize one or more device IDs, the accuracy of the link may be considered unknown and may be excluded from the device ID association analysis. In other non-limiting embodiments, the deterministic graph may recognize one or more device IDs, but one or more device IDs may be associated with IDs other than those shown as associated in the probabilistic graph. These other embodiments are known as inexact matches or false positives. If a link is not in either the probabilistic graph or the deterministic graph, the link may be referred to as a potential link. A potential link may be counted as a true negative or may not be counted as part of the process or analysis.

[0070] In certain non-limiting embodiments, a deterministic graph may indicate a link between two or more devices, but a probabilistic graph may not indicate a similar link between two or more devices. When the probabilistic graph does not recognize at least one of the device IDs known in the deterministic graph, the link may be considered unknown. On the other hand, when the probabilistic graph recognizes one or more devices, but simply fails to associate the devices, the link may be considered a false negative.

[0071] Once the above quantities have been identified (e.g., true positives, false negatives, false positives, or unknown links), the accuracy and reach of the device ID linking can be calculated. Accuracy can be, for example, the ratio of true positives to total positives. This can be calculated using the formula (true positives / (true positives + false positives)). Reach can be, for example, the ratio of true positives to all true links. This can be calculated using the formula (true positives / (true positives + false negatives)). The accuracy and / or reach measurements calculated using the above formulas can be lower bounds of true statistics. For example, the calculated accuracy can be about 90% and the reach can be about 75%. In another example, the accuracy can range from about 65% to about 97% and the reach can range from 20% to 80%. Increasing the accuracy by about 2-3% can decrease the reach by about 50%.

[0072] In some non-limiting embodiments, the federation may include associating or aggregating multiple touch points of a consumer. For example, a consumer may have two email addresses, such as a personal email address and a business email address. Information or data from a consumer database company may be used to federate the two email addresses. The consumer's full name, physical address, and / or email address may then be federated into one profile or identity resolution. The profile or identity resolution may also include other attributes of the consumer, such as a mailing address, a phone number, a mobile phone number, a pet attribute, gender, and / or any other attribute.

[0073] 4 illustrates a federated system according to certain non-limiting embodiments. In particular, FIG. 4 may include a data lake 410, which may be similar to data lakes 130, 240, and 340, and a data outlet framework 420, which may be similar to data outlet frameworks 140, 250, and 350. Data contained in one or more datasets may be utilized to create a health management profile for the pet. The profile may be created using any attributes known about the pet. For example, the profile may include the following information:

[0074] [Table 1]

[0075] Any known CDP or data management platform (DMP) can be used to create one or more datasets and / or health care profiles for the pet. Creating one or more datasets and / or health care profiles for the pet can include associating aggregated data from one or more sources or one or more datasets. The health care profile can include one or more health care needs of the pet. For example, a given pet's health care profile can indicate that the pet has dental issues or poor dental hygiene. Using the predictive tool 430 can help predict pet products and meet the pet's health care needs. For example, the predictive tool 430 can determine that a particular pet chewable can help improve, solve, or address the pet's dental issues, thereby meeting the pet's health care needs. In another example, the predictive tool 430 can help determine services, products, medicines based on one or more attributes. In certain non-limiting embodiments, the predictive tool can utilize artificial intelligence or machine learning algorithms.

[0076] In some non-limiting embodiments, the predictive tool can utilize a method or process called gradient boosting for machine learning. The method or process can start with a single sector data, such as pet tracking data. Decision tree learning, including one or more decision trees, can then be used to model multiple scenarios and incrementally compare one computational method to another. For example, based on pet movement data, it can be determined whether a pet could use better nutritional food to support activity levels. After creating the changes, Empirical Risk Minimization (ERM) can be used to validate the model. ERM can be a statistical learning theory that can define a family of learning algorithms used to provide theoretical bounds on their performance. The EMR formula is: Given id features x j and label y j Using the data set, the following equation

[0077]

number

[0078] Other non-limiting embodiments may utilize one or more analytical models such as classification trees, regression trees, boosted trees, or bootstrapped ensembles.

[0079] In certain non-limiting embodiments, the prediction tool 430 can take into account advertisements 431, media exposures 433, product purchases 435, advertisement responses 432, and / or no response 434. No response 434 can mean that the consumer did not respond and / or did not provide a data point to be measured. For example, time series data such as advertisement exposure or store purchases of pet care products can be input. A model can be run based on this data to determine the next best product to offer to the customer. Testing or modeling can then be run on another sample to determine whether the performance can be replicated without the time series data. For example, for a single scenario, media exposure + product purchase can provide a 90% confidence in predicting a purchase, media exposure + product purchase + advertisement response can provide a 93.2% confidence in predicting a purchase, and / or media exposure + product purchase + advertisement response + product purchase can provide a 93.7% confidence in predicting a purchase. However, for multiple scenarios involving different points of data input, product purchase may provide a 70% confidence in predicting a purchase, product purchase + ad response may provide a 93.1% confidence in predicting a purchase, and / or product purchase + ad response + product purchase may provide a 93.4% confidence in predicting a purchase.

[0080] The product purchases 435 and advertising responses 432 may include the pet owner's past behavior. One or more of these inputs, along with data from the pet profile, may be processed by the predictive tool 430 to determine pet products or services that will help meet the pet's health care needs. In other words, the predictive tool 430 may not only predict pet products or services that will help meet the pet's health care needs, but may also predict the purchasing behavior of a given pet owner. In some non-limiting embodiments, the predictive tool 430 may also be used to determine an audience to advertise or offer pet products to.

[0081] FIG. 5 illustrates a system or method for aggregation and federation, according to certain non-limiting embodiments. In particular, in step 510, data can be collected from one or more sources and aggregated into a data lake. In this case, PII contained within the aggregated data can be cleaned, meaning that the PII can be removed or separated from the data. In some non-limiting embodiments, the cleaned data can be sorted into one or more data sets based on attributes. A pet profile can then be created based on the sorted data in the one or more data sets. A CDP such as Epsilon can be used to clean the PII from the aggregated data, create the pet profile, and / or sort the one or more data sets. As shown in step 520, the aggregated data can be cleaned and / or reformatted to a uniform threshold or standard level of quality. After at least one of the aggregation, cleaning, sorting, and / or creation of a pet profile has been performed on the data, the data can be federated or connected, as shown in step 530. The data can be federated or connected to an analytical model to perform related or related tasks. For example, a marketing engine can utilize breed information, but not the pet's pharmaceutical attributes. In another example, the supporting science can consider genetics and laboratory diagnosis rather than nutritional data. In step 540, the linked data can be analyzed to predict pet products based on collected or aggregated data that can help meet pet health care needs. In certain non-limiting embodiments, the data can be analyzed in a DMP. In steps 550 and 560, advertisements for pet products can be shown on displays or graphic user interfaces targeted to pet owners or audience members. In some non-limiting embodiments, steps 550 or 560 can include the use of a digital side platform (DSP) including real-time bidding.While step 550 can include analytical use case delivery, step 560 can include delivering advertisements to pet owners or any other target audience. For example, step 550 can be relevant because the output can be in a summary form that is not aggregated. Step 560 can be broken down to a pseudonym identity level that matches other pseudonym identities.

[0082] FIG. 6A illustrates a system or method for aggregation and federation, according to certain non-limiting embodiments. In particular, FIG. 6A illustrates a targeting process based on first-party data. The first-party data can be collected, for example, from health or location tracking devices 110, DNA or genetic tests 210, veterinary clinic POS devices 310, and / or any other first-party sources. In certain non-limiting embodiments, third-party data or second-party data can also be used to associate with the first-party data. As shown in step 610, the first-party data can be extracted, aggregated, and / or mapped. The data can be extracted discretely, for example, hourly, daily, weekly, and / or monthly. In step 611, the data can be aggregated and sorted into a data set, and / or a pet or pet owner profile can be created. In some non-limiting embodiments, step 611 can be performed by a CDP. For example, as shown in step 611, the data set can be matched by matching hashed emails, device IDs, and / or any other methods, and / or a pet or pet owner profile can be created. The pet or pet owner profile in certain embodiments may be referred to as a pet care identifier.

[0083] In step 612, the pet care ID can be matched with a cookie or device ID and / or a DMP. In other words, step 612 can be used to update the DMP with the data. In step 613, the DMP can enable the creation of a data audience. Advertisements for pet products can then be served or sent to the data audience, as shown in step 614. The target audience can be an audience selected to be best suited to see, read, or listen to the advertisement. The audience can include pet owners or any other members to whom the advertised pet products may be relevant. In a particular non-limiting embodiment, step 615 can indicate matching by uploading a hashed email to a social networking site and / or a search engine. The advertisement can then be distributed via the social networking site and / or the search engine.

[0084] FIG. 6B illustrates a system or method for aggregation and federation, according to certain non-limiting embodiments. In particular, FIG. 6B illustrates a system or method for measuring the effectiveness of the systems or methods illustrated in FIG. 5 and FIG. 6A. In step 620, search engines and / or social media networks can collect measurements or metrics related to pet supply ads, referred to as exposure in FIG. 5 and FIG. 6A. The measurements and / or metrics can be aggregated in step 621 and transferred to a data lake 622. The data lake 622 can be similar to the data lakes 130, 240, 340, and 410. In certain non-limiting embodiments, a monthly upload of an exposure file can be sent, as illustrated in step 630. The exposure file can be non-aggregated event-level data from an advertising campaign that can typically be reported by a publisher or media entity. The data may be raw data that can be collected from ad server logs that may include, for example, an Internet Protocol (IP) address representing the address of the user making the request, a user agent, which is a text string sent by the browser to the server that provides certain identifying information about the browser, the time of exposure, the date and time of exposure, the ad content, the publisher, the ad unit that can identify the location of the ad placed on the publisher site, the line item that can identify the respective customer campaign or creative, ID classification, and / or other information related to the event. Other measurements may include pop-up blockers, non-Flash browsers, JavaScript disabled or disabled browsers, ad blocking software, image rendering disablement, and / or auto-refresh.

[0085] In step 631, the exposure file can be matched with cookies or device IDs via the CDP. From the CDP, the matching and updated data can be sent to a data lake 632, which can be similar to data lake 622.

[0086] FIG. 7 illustrates a system or method for aggregation and federation according to certain non-limiting embodiments. FIG. 7 outlines a system for ingesting data, classifying, processing handling data, and then developing these created audiences. In particular, FIG. 7 illustrates the use of known data 710 and unknown data 720. The known data 710 may include sales, service, marketing, commerce, and / or any other external data. The unknown data 720 may include web, mobile applications, Internet of Things (IOT), media information, and / or any second or third party information. The known data 710 and unknown data 720 may be collected and transmitted to a pet activation platform 730. The pet activation platform 730 may be similar to the consent frameworks 140, 250, 350, and 420 shown in FIGS. 1-4. In some non-limiting embodiments, the pet activation platform 730 may be cloud-based. The pet activation platform 730 can use information that is already compliant within data privacy and data protection regardless of region. Alternatively or additionally, the pet activation platform 730 can assist in targeting audiences for known and / or unknown customers through digital marketing. The pet activation platform 730 can be used for digital experiences that can be personalized for one or more customers. In other non-limiting embodiments, the pet activation platform 730 can be used to connect with third-party advertising platforms.

[0087] In certain non-limiting embodiments, a DMP, also referred to as a unified data management platform (UDMP), can be a centralized system for collecting and / or analyzing large data sets derived from disparate sources. The pet activation platform 730 can be, for example, a DMP. A DMP can create a combined development and distribution environment that provides consistent, accurate, and / or timely data to one or more users. As described above, the simplest DMP can be a NoSQL database management system that can import data from many systems and / or allows marketers and publishers to view data in a consistent manner. Other DMPs can combine, for example, data management techniques and data analysis tools into a single software suite, which can include an intuitive or easy-to-navigate executive dashboard.

[0088] A DMP can be used to collect structured and / or unstructured data from a range of internal and external sources and / or to consolidate and store data. A DMP can also be used to analyze or organize data to provide data driver insights for marketing and / or advertising campaigns. For example, the data incorporated into a data management platform can be first-party data, second-party data, and / or third-party data. Third-party data can be used to fill holes in a company's own data and partner data. In certain non-limiting embodiments, any DMP known in the art can be used.

[0089] In step 740, the data can be personalized. This means that a pet profile can be created, an audience can be determined, and / or the pet's health care needs can be predicted. Based in part on the pet's health care needs, an advertisement can be pushed to the pet owner via known email, mobile device, search engine, social network, and / or short message service, as shown in step 750. This can be referred to as known activation. Alternatively or in addition, the advertisement can be targeted to unknown activation. The unknown activation can be, for example, a search advertisement, an on-site advertisement, an off-site advertisement, a social network advertisement, and / or a designated pet care website or application. In step 760, measurements and / or metrics related to the advertisement can be collected and / or transmitted.

[0090] In certain non-limiting embodiments, the advertisements may conform to, for example, Interactive Advertising Bureau (IAB) standards. The advertisements may be, for example, fixed size advertisements, flexible size advertisements, native advertisements, and / or lightweight advertisements. The advertisements may have various sizes, and the size may be based on the number of pixels on the display that the advertisement may occupy. The pixel size may be, for example, billboard size, smartphone banner size, leaderboard size, portrait size, skyscraper size, or a small, medium, or large banner for a feature phone.

[0091] D. Results of the Methods and Systems Described Herein FIG. 8 illustrates a graph according to a specific, non-limiting embodiment. In particular, FIG. 8 can illustrate daily impressions and / or performance for the specific embodiment described above. As illustrated in FIG. 8, the daily impressions graph includes information related to XYZ 810, Pet Care 820, and Predictive Pet Care 830. XYZ 810 can be, for example, a purchase-based targeting audience that can be built from a collection of audiences that have purchased a particular pet-related product. Pet-related products can be purchased, for example, at grocery stores, drug stores, mass merchandisers, e-commerce stores, and / or pet specialty stores. In a specific, non-limiting embodiment, XYZ 810 can illustrate third-party audience partners and / or audience targeting results daily, illustrating the total number of viewable impressions for the advertisement. Pet Care 820 can illustrate the total number of daily viewable impressions for the collective audience and / or advertisement to achieve the audience targeting. Predictive Pet Care 830 can show aggregate audiences to achieve audience targeting expanded to include audiences similar to the base audience. The line can represent the total number of daily viewable impressions for the advertisement.

[0092] In some non-limiting embodiments, Predictive Pet Care 830 can show daily impressions based on the system or method used in Figures 1-7. As shown in Figure 8, Predictive Pet Care 830 can receive more daily impressions than Pet Care 820. Furthermore, Figure 8 can also show a bar graph showing the performance to date of XYZ 810, Pet Care 820, and Predictive Pet Care 830. The viewability of XYZ 810, Pet Care 820, and Predictive Pet Care 830 can be 78.70%, 80.30%, and 77.96%, respectively. Meanwhile, the total conversions / matched impressions (VCR or CVR) of XYZ 810, Pet Care 820, and Predictive Pet Care 830 can be 71.6%, 75.8%, and 75.7%, respectively. This shows that the system or method shown in Figures 1-7 provides a significant technical improvement with significant advantages over systems used in the past.

[0093] E. Flowcharts of the methods described herein FIG. 9 illustrates a flow chart according to a specific, non-limiting embodiment. In particular, FIG. 9 illustrates a method 9000 performed by the system illustrated in FIGS. 5-7 to meet pet health care needs. In step 910, the system may collect data from one or more disparate data sources. The one or more disparate data sources may include health and location tracking devices, DNA or genetic testing services, or veterinary clinic point-of-sale devices. The data may include at least one of first party data, second party data, or third party data. The collected data may include pet health information. In step 920, the method may include aggregating the collected data from the one or more disparate sources in a data lake. The method may also include clearing personally identifiable information from the aggregated data in the data lake, as illustrated in step 930. In a specific, non-limiting embodiment, the method may include sorting the cleared data into one or more data sets based on one or more attributes of the pet or the pet's owner. The one or more data sets may include at least one of the pet's health, the pet's ownership, and the pet's physical or behavioral characteristics.

[0094] In some non-limiting embodiments, the method may include reformatting data from one or more disparate data sources to a uniform quality level. At step 940, the method may include sorting the cleaned data into one or more data sets based on one or more attributes of the pet or the pet owner. The method may include creating a pet profile based on the data included in the one or more data sets at step 950. Pet products useful for meeting the pet's healthcare needs may be determined at step 960. The aggregating, cleaning, sorting, creating, and determining may be performed by a CDP or a DMP. In other non-limiting embodiments, the method may include predicting a target audience for advertising the pet product. The target audience may include the pet owner and one or more other pet owners. The determining or predicting may use machine learning algorithms to predict the target audience or to determine the pet products useful for meeting the pet's healthcare needs.

[0095] In certain non-limiting embodiments, the method may include targeting the pet owner with an advertisement for the pet product, as shown in step 970. The method may also include displaying the advertisement or offer for the pet product to the pet owner via a graphical user interface of the terminal device, as shown in step 980.

[0096] F. Diagrams of the Systems and Apparatus Described Herein FIG. 10 illustrates a diagram of a system 1000 according to certain non-limiting embodiments. In particular, certain non-limiting embodiments can include distributed resources, which may include one or more hardware or cloud servers configured to perform any of the collecting, processing, transmitting, or storing described above in FIGS. 1-7. For example, in one embodiment of the disclosed subject matter, a system 1000 is provided. The system 1000 may include one or more servers capable of collecting data from one or more components, such as one or more sources, data lakes, data outlet frameworks, and / or predictive tools. With reference to the embodiment of FIG. 10, for purposes of illustration and not limitation, the system may include a central server 1100 that collects data from one or more individual servers 1200, 1300, 1400. In certain embodiments, the central server 1100 may include a server computer, a desktop computer, a laptop computer, a cloud-based computing device, among other available computing devices. In some embodiments, the central server 1100 may include multiple computers.

[0097] Further, in certain embodiments, one or more of the individual servers 1200, 1300, 1400 may include server computers, desktop computers, laptop computers, cloud-based computing devices, among other available computing devices. In this non-limiting embodiment, the individual servers 1200, 1300, 1400 may collect data from one or more distributed resources 1210-1230, 1310-1330, and 1410-1430, respectively, that are used to process data of inspected pet supplies. The distributed resources 1210-1230, 1310-1330, and / or 1410-1430 may be any imaging or non-imaging sensor. In addition to static data, such as, but not limited to, resource identification information, including resource or hostname, processor architecture (i.e., multiple cores), and / or location of the resource, data collected from the resource may include, among other measurable information, memory usage and / or availability (GB), CPU speed (MHz), and start and end times, such as the time the resource is available or running.

[0098] In the embodiment of FIG. 10, for purposes of illustration and not limitation, the collected data may be processed by at least a processing component, such as a processing server 1600 of the system 1000, configured with logic to collect, analyze, process, and / or store data received from one or more resources. In certain embodiments, the processing server 1600 may include a server computer, a desktop computer, a laptop computer, a cloud-based computing device, among other available computing devices. The processing server may include one or more processors contained within one or more other servers, or may alternatively be a stand-alone component configured to receive information from and transmit information to another server, such as, for example, the central server 1100, as depicted by dashed lines in the embodiment of FIG. 10.

[0099] Based on the collected data, the system 1000 can target audiences and / or pet owners with pet supply advertisements. The advertisements can be viewed by the pet owners or audience members on terminal devices 1500. The terminal devices 1500 can include PCs, workstations, user equipment, and / or mobile devices. Thus, in some embodiments, the advertisements can be displayed on a user interface of a graphical user interface.

[0100] By way of example and not limitation, in one embodiment, data relating to one or more teeth of a pet may be collected by one or more individual servers 1200, 1300, 1400 from distributed resources 1210-1230, 1310-1330, 1410-1430 and collected and stored in files on the individual servers 1200, 1300, 1400. The files may be any of a number of file types, such as flat files, database files, markup language files, etc. The central server 1100 of the embodiments described herein may receive two or more batch file transfers of data collected from the individual servers 1200, 1300, 1400, respectively. Thus, the individual servers 1200, 1300, 1400 may be specifically configured to manage the data and transmit it over a network (not shown) to the central server using memory components and file transfer techniques.

[0101] FIG. 11 is a diagram of an apparatus or system 1110 according to certain non-limiting embodiments. In certain embodiments, one or more computer systems 1110 may perform one or more steps of the methods described or illustrated herein, such as the steps illustrated in FIGS. 1-9. In some embodiments, one or more computer systems 1110 provide the functionality of the servers and / or computing devices described or illustrated herein. In certain embodiments, software executing on one or more computer systems 1110 performs one or more steps of one or more methods described or illustrated herein or provides the functionality described or illustrated herein. Certain embodiments include one or more portions of one or more computer systems 1110. As used herein, references to a computer system may encompass a computing device, and vice versa, where appropriate. Additionally, references to a computer system may encompass one or more computer systems, where appropriate. The computer system 1110 may include one or more monitors, displays, and / or graphical user interfaces that enable pet owners and / or audience members to view advertisements for pet supplies.

[0102] The present disclosure contemplates any suitable number of computer systems 1110. The present disclosure contemplates computer systems 1110 taking any suitable physical form. By way of example and not limitation, computer system 1110 may be an embedded computer system, a system on a chip (SOC), a single board computer system (SBC) (e.g., a computer on module (COM) or system on module (SOM)), a desktop computer system, a laptop or notebook computer system, an interactive kiosk, a mainframe, a mesh of computer systems, a mobile phone, a personal digital assistant (PDA), a server, a tablet computer system, an augmented / virtual reality device, or a combination of two or more of these. Where appropriate, computer system 1110 may include one or more computer systems 1110, may be unitary or distributed, may span multiple locations, may span multiple machines, may span multiple data centers, or may exist in a cloud. The cloud may include one or more cloud components in one or more networks. If desired, one or more computer systems 1110 may perform one or more steps of one or more methods described or illustrated herein without substantial spatial or temporal limitations. By way of example and not limitation, one or more computer systems 1110 may perform one or more steps of one or more methods described or illustrated herein in real time or in batch mode. One or more computer systems 1110 may perform one or more steps of one or more methods described or illustrated herein at different times or in different locations, if desired.

[0103] In a particular embodiment, computer system 1110 includes a processor 1112, memory 1113, storage 1114, input / output (I / O) interface 1115, communication interface 1116, and a bus 1111. Although this disclosure describes and illustrates a particular computer system having a particular number of particular components in a particular arrangement, this disclosure contemplates any suitable computer system having any suitable number of any suitable components in any suitable arrangement.

[0104] In particular embodiments, the processor 1112 includes hardware for executing instructions, such as those that make up a computer program. By way of example and not limitation, to execute instructions, the processor 1112 may retrieve (or fetch) instructions from an internal register, an internal cache, memory 1113, or storage 1114, decode and execute them, and then write one or more results to the internal register, internal cache, memory, or storage 1114. In particular embodiments, the processor 1112 may include one or more internal caches for data, instructions, or addresses. This disclosure contemplates the processor 1112 including any suitable number of any suitable internal caches, as appropriate. By way of example and not limitation, the processor 1112 may include one or more instruction caches, one or more data caches, and one or more translation lookaside buffers (TLBs). Instructions in an instruction cache may be copies of instructions in memory or storage 1113, and the instruction cache may speed up retrieval of such instructions by the processor 1112. The data in the data cache may be a copy of data in memory or storage 1113 for the functioning of instructions executing on the processor 1112, results of past instructions executed by the processor 1112 for access by subsequent instructions executing on the processor 1112 or for writing to memory or storage 1113, or other suitable data. The data cache may speed up read or write operations by the processor 1112. The TLB may speed up virtual address translations for the processor 1112. In particular embodiments, the processor 1112 may include one or more internal registers for data, instructions, or addresses. This disclosure contemplates the processor 1112 including any suitable number of any suitable internal registers, as appropriate. As appropriate, the processor 1112 may include one or more arithmetic logic units (ALUs), may be a multi-core processor, or may include one or more processors 1112.Although this disclosure describes and illustrates a particular processor, this disclosure contemplates any suitable processor.

[0105] The processor 1112 may be embodied by any computational or data processing device, such as a central processing unit (CPU), digital signal processor (DSP), application specific integrated circuit (ASIC), programmable logic device (PLD), field programmable gate array (FPGA), digitally enhanced circuit, or equivalent device, or combination thereof. The processor may also be implemented as a single controller, or multiple controllers or processors.

[0106] In a particular embodiment, the memory 1113 includes a main memory for storing instructions for the processor 1112 to execute or data for the processor 1112 to operate on. By way of example and not limitation, the computer system 1110 may load instructions into the memory 1113 from storage or another source (such as another computer system 8000). The processor 1112 may then load the instructions from the memory 1113 into an internal register or cache. To execute an instruction, the processor 1112 may retrieve and decode the instruction from the internal register or cache. During or after the execution of an instruction, the processor 1112 may write one or more results (which may be intermediate or final results) to the internal register or cache. The processor 1112 may then write one or more of these results to the memory 1113. In particular embodiments, the processor 1112 executes only instructions in one or more internal registers or caches or in the memory 1113 and operates only on data in one or more internal registers or caches or in the memory 1113 (as opposed to storage or elsewhere). One or more memory buses (which may each include an address bus and a data bus) may couple the processor 1112 to the memory 1113. The bus 1111 may include one or more memory buses, as described below. In particular embodiments, one or more memory management units (MMUs) reside between the processor 1112 and the memory 1113 to facilitate accesses to the memory 1113 requested by the processor 1112. In particular embodiments, the memory 1113 includes random access memory (RAM). The RAM may be volatile memory, where appropriate. The RAM may be dynamic RAM (DRAM) or static RAM (SRAM), where appropriate. Further, the RAM may be single-ported or multi-ported RAM, where appropriate. This disclosure contemplates any suitable RAM. The memory 1113 may, where appropriate, include one or more memories 1113. Although this disclosure describes and illustrates a particular memory, this disclosure contemplates any suitable memory.

[0107] The one or more memories 1113 may be shared memory, distributed memory, and / or hybrid shared distributed memory. A shared memory architecture may be based on a global memory space that may allow all nodes to share memory. On the other hand, in a distributed memory architecture, the processor has its own memory and / or a communication network and protocol to connect each computing node. A hybrid shared distributed memory may include both a shared memory architecture and a distributed memory architecture.

[0108] In certain embodiments, computer system 1110 may also include storage 1114, which may include mass storage for data or instructions. By way of example and not limitation, storage 1114 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Storage 1114 may include removable or non-removable (or fixed) media, as appropriate. Storage 1114 may be internal or external to computer system 1110, as appropriate. In certain embodiments, storage may be non-volatile solid-state memory. In certain embodiments, storage may include read-only memory (ROM). As appropriate, this ROM may be a mask program ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM), or a flash memory, or a combination of two or more of these. This disclosure contemplates mass storage taking any suitable physical form. Storage 1114 may include one or more storage control units to facilitate communication between processor 1112 and storage 1114, as appropriate. Storage may include one or more storages, as appropriate. Although this disclosure describes and illustrates particular storage, this disclosure contemplates any suitable storage.

[0109] In certain embodiments, the I / O interface 1115 includes hardware, software, or both that provide one or more interfaces for communication between the computer system 1110 and one or more I / O devices. The computer system 1110 may include one or more of these I / O devices, as appropriate. One or more of these I / O devices may enable communication between a person and the computer system 1110. By way of example and not limitation, the I / O devices may include a keyboard, a keypad, a microphone, a monitor, a mouse, a printer, a scanner, a speaker, a still camera, a stylus, a tablet, a touch panel, a trackball, a video camera, another suitable I / O device, or a combination of two or more of these. The I / O devices may include one or more sensors. This disclosure contemplates any suitable I / O device and any suitable I / O interface 1115 for the I / O device. As appropriate, the I / O interface 1115 may include one or more device or software drivers that enable the processor 1112 to drive one or more of these I / O devices. I / O interface 1115 may include one or more I / O interfaces 1115, where appropriate. Although this disclosure describes and illustrates a particular I / O interface, this disclosure contemplates any suitable I / O interface.

[0110] In particular embodiments, the communication interface 1116 includes hardware, software, or both that provide one or more interfaces for communication (e.g., packet-based communication, etc.) between the computer system 1110 and one or more other computer systems 1110 or one or more networks. By way of example and not limitation, the communication interface 1116 may include a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wired-based network, or a wireless NIC (WNIC) or wireless adapter for communicating with a wireless network, such as a WI-FI network. This disclosure contemplates any suitable network and any suitable communication interface 1116 therefor. By way of example and not limitation, the computer system 1110 may communicate with one or more portions of an ad-hoc network, a personal area network (PAN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), or the Internet, or a combination of two or more of these.

[0111] One or more portions of one or more of these networks may be wired or wireless. As an example, the computer system 1110 may communicate with a wireless PAN (WPAN) (e.g., a BLUETOOTH WPAN, etc.), a WI-FI network, a WI-MAX network, a cellular network (e.g., a Global System for Mobile Communications (GSM) network, etc.), or other suitable wireless networks, or a combination of two or more of these. The computer system 1110 may include any suitable communication interface 1116 for any of these networks, as appropriate. The communication interface 1116 may include one or more communication interfaces 1116, as appropriate. Although this disclosure describes and illustrates a particular communication interface, this disclosure contemplates any suitable communication interface. The communication interface may be used to receive and / or transmit in connection with one or more teeth of a pet.

[0112] In particular embodiments, the bus 1111 includes hardware, software, or both that couple components of the computer system 1110 together. By way of example, and not limitation, the bus 1111 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCIe) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or another suitable bus, or a combination of two or more of these. The bus 1111 may include one or more buses 8120, as appropriate. Although this disclosure describes and illustrates particular buses, this disclosure contemplates any suitable bus or interconnect.

[0113] As used herein, the one or more computer-readable non-transitory storage media may include, where appropriate, one or more semiconductor-based or other integrated circuits (ICs) (e.g., field programmable gate arrays (FPGAs) or application specific ICs (ASICs)), hard disk drives (HDDs), hybrid hard drives (HHDs), optical disks, optical disk drives (ODDs), magneto-optical disks, magneto-optical drives, floppy disks, floppy disk drives (FDDs), magnetic tapes, solid state drives (SSDs), RAM drives, secure digital cards or drives, any other suitable computer-readable non-transitory storage media, or any suitable combination of two or more of these. The computer-readable non-transitory storage media may be volatile, non-volatile, or a combination of volatile and non-volatile, where appropriate.

[0114] The above embodiments provide important technical improvements and advantages. In particular, the above-mentioned features provide streamlining of data into a categorized structure that allows multiple applications to be run simultaneously, rather than running a single application for each database separately. For example, running multiple applications simultaneously is also known as parallel processing of data-intensive or computer-intensive applications. Parallel processing can be categorized as computation-intensive and / or data-intensive. Data-intensive applications face two major challenges, including processing exponentially growing amounts of data and drastically reducing data analysis cycles for the purpose of making timely decisions. Computation-intensive applications, on the other hand, can be used to write application programs that are computation-bound. Such computer-intensive applications use small amounts of data, as they can devote most of their execution time to computational requirements as opposed to input / output. In certain non-limiting embodiments, applications can be both data-intensive and computation-intensive.

[0115] The classification between data-intensive and compute-intensive parallel processing may also be relevant to grid computing. A computing grid may be heterogeneous in nature, meaning that the grid may use different computing nodes and / or multiple geographically distributed nodes using wide area network communication. A grid may be used to solve complex compute-intensive computational problems. On the other hand, a data-intensive computing system may be a homogenous cluster, meaning that the nodes in the computing cluster are identical and may use local area communication between the nodes. Grid computing may virtualize resources and provide the basis for cloud computing services. Thus, cloud computing services may be used for data-intensive parallel computing. In other words, the specific non-limiting embodiments described above may utilize one or more cloud computer services. The one or more cloud computing services may include a large pool of configurable virtual resources that may be scaled to accommodate various parallel processing loads. This fluctuating processing load may include big data.

[0116] The scope of the present disclosure encompasses all changes, substitutions, variations, modifications and alterations to the exemplary embodiments described or illustrated herein that would be understood by a person skilled in the art. The scope of the present disclosure is not limited to the exemplary embodiments described or illustrated herein. Furthermore, although the present disclosure describes and illustrates each embodiment herein as including certain components, elements, features, functions, operations or steps, any of these embodiments may include any combination or permutation of any of the components, elements, features, functions, operations or steps described or illustrated anywhere herein that would be understood by a person skilled in the art. Furthermore, any reference in the appended claims to an apparatus or system or an apparatus or system component that is adapted, arranged, capable, configured, enabled, operable or operates to perform a particular function encompasses that apparatus, system, component or that particular function thereof, whether or not that apparatus, system, component or that particular function is activated, turned on or unlocked, so long as that apparatus, system, or component is so adapted, arranged, capable, configured, enabled, operable or operates. Additionally, although the present disclosure describes or illustrates particular embodiments as providing certain advantages, the particular embodiments may provide none, some, or all of these advantages.

[0117] Preferred embodiments of the present invention will be described below in detail.

[0118] EMBODIMENT 1 1. A method for meeting the health care needs of a pet, comprising: collecting data from one or more heterogeneous data sources; aggregating data collected from one or more heterogeneous data sources into a data lake; removing personally identifiable information from the aggregated data in the data lake; sorting the cleaned data into one or more data sets based on one or more attributes of the pet or the pet's owner; creating a pet profile based on data contained in said one or more data sets; determining a pet product that will help meet the health care needs of the pet; targeting the pet owners with advertisements for the pet products; A method comprising:

[0119] EMBODIMENT 2 The method comprises: Displaying the advertisement for the pet product to the pet owner via a graphical user interface of a terminal device. 2. The method of embodiment 1, further comprising:

[0120] EMBODIMENT 3 3. The method of embodiment 1 or 2, wherein the data includes at least one of first party data, second party data, or third party data.

[0121] EMBODIMENT 4 The method of any one of embodiments 1 to 3, wherein the one or more heterogeneous data sources include health and location tracking devices, DNA or genetic testing services, or veterinary point-of-sale devices.

[0122] EMBODIMENT 5 The method of any one of embodiments 1 to 4, wherein the collected data includes pet health information.

[0123] EMBODIMENT 6 The method of any one of embodiments 1 to 5, wherein the aggregating, deleting, sorting, creating, and determining steps are performed by a consumer data platform or a data management platform.

[0124] EMBODIMENT 7 The method comprises: Reformatting data from one or more disparate data sources to a uniform level of quality 7. The method of any one of embodiments 1 to 6, further comprising:

[0125] EMBODIMENT 8 The method comprises: predicting a target audience for said pet product advertisement; 8. The method of any one of the preceding claims, further comprising: wherein the target audience can include the pet owner and one or more other pet owners.

[0126] EMBODIMENT 9 The method of any one of embodiments 1 to 8, wherein the determining step or the predicting step uses a machine learning algorithm for predicting the target audience or determining pet products that will help meet the pet's health care needs.

[0127] EMBODIMENT 10 10. The method of any one of the preceding claims, wherein the one or more datasets include at least one of pet health, pet ownership, and physical or behavioral characteristics of the pet.

[0128] EMBODIMENT 11 The method of any one of embodiments 1 to 10, wherein the one or more heterogeneous data sources is first-party data collected from health and location tracking devices.

[0129] EMBODIMENT 12 The method of any one of embodiments 1 to 10, wherein the one or more heterogeneous data sources are one or more genetic testing services.

[0130] EMBODIMENT 13 13. The method of embodiment 12, wherein the data lake includes a data outlet framework.

[0131] EMBODIMENT 14 14. The method of embodiment 13, wherein the data consent framework includes transparency and consent strings.

[0132] EMBODIMENT 15 The step of predicting further comprises a covariance analysis, the covariance analysis comprising: assessing whether multiple means of a dependent variable are equal across multiple levels of a categorical independent variable; controlling for a plurality of effects from a plurality of other variables; Including, The covariance analysis is used in either the pre-test or post-test analysis. The method of any one of embodiments 8 to 14.

[0133] EMBODIMENT 16 A system for meeting pet health care needs, comprising: At least one processor; at least one memory containing computer program code; Including, The computer program code, when executed by the at least one processor, provides the system with: collecting data from one or more heterogeneous data sources; aggregating the data collected from the one or more heterogeneous data sources into a data lake; and removing personally identifiable information from the aggregated data in the data lake; and Sorting the cleaned data into one or more data sets based on one or more attributes of the pet or the pet's owner; creating a pet profile based on data included in said one or more data sets; determining a pet product useful for meeting the health care needs of said pet; targeting the pet owners with advertisements for the pet products; A system configured to:

[0134] EMBODIMENT 17 The computer program code, when executed by the at least one processor, provides the system with: Displaying advertisements for the pet products to the pet owners via a graphical user interface of a terminal device. 17. The system of embodiment 16, configured as follows:

[0135] EMBODIMENT 18 18. The system of claim 16 or 17, wherein the data includes at least one of first party data, second party data, or third party data.

[0136] EMBODIMENT 19 The system of any one of embodiments 16 to 18, wherein the one or more heterogeneous data sources include health and location tracking devices, DNA or genetic testing services, or veterinary point-of-sale devices.

[0137] EMBODIMENT 20 The system of any one of embodiments 16 to 19, wherein the collected data includes pet health information.

[0138] EMBODIMENT 21 The system of any one of embodiments 16 to 20, wherein the aggregating, deleting, sorting, creating, and determining are performed by a consumer data platform or a data management platform.

[0139] EMBODIMENT 22 The computer program code, when executed by the at least one processor, provides the system with: Reformat data from one or more disparate data sources to a uniform level of quality 22. The system of any one of embodiments 16 to 21, configured as follows:

[0140] EMBODIMENT 23 The computer program code, when executed by the at least one processor, provides the system with: Predicting a target audience for said pet product advertisements wherein the target audience may include the pet owner and one or more other pet owners. A system described in any one of embodiments 16 to 22.

[0141] EMBODIMENT 24 The system of any one of embodiments 16 to 23, wherein the determining or predicting uses a machine learning algorithm for predicting the target audience or determining pet products that will help meet the pet's health care needs.

[0142] EMBODIMENT 25 The system of any one of embodiments 16 to 24, wherein the one or more datasets include at least one of pet health, pet ownership, and physical or behavioral characteristics of the pet.

[0143] EMBODIMENT 26 The system of any one of embodiments 16 to 25, wherein the one or more heterogeneous data sources is first-party data collected from health and location tracking devices.

[0144] EMBODIMENT 27 The system of any one of embodiments 16 to 25, wherein the one or more heterogeneous data sources are one or more genetic testing services.

[0145] EMBODIMENT 28 27. The system of any one of embodiments 16 to 26, wherein the data lake includes a data outlet framework.

[0146] EMBODIMENT 29 29. The system of embodiment 28, wherein the data outlet framework includes transparency and an outlet string.

[0147] Implementation form 30 The computer program code, when executed by the at least one processor, is configured to cause the system to perform a covariance analysis, the covariance analysis comprising: assessing whether multiple means of a dependent variable are equal across multiple levels of a categorical independent variable; Controlling for multiple effects from multiple other variables; The device is configured to: The covariance analysis is used in either the pre-test or post-test analysis. A system described in any one of embodiments 23 to 27.

Claims

[Claim 1] 1. A method for meeting the health care needs of a pet, comprising: collecting data from one or more heterogeneous data sources; aggregating data collected from one or more heterogeneous data sources into a data lake; removing personally identifiable information from the aggregated data in the data lake; sorting the cleaned data into one or more data sets based on one or more attributes of the pet or the pet's owner; creating a pet profile based on data contained in the one or more data sets; determining a pet product that will help meet the health care needs of the pet; targeting the pet owners with advertisements for the pet products; A method comprising:

Images