System and method for detecting pet eating patterns

Abstract

A computer-implemented method for identifying changes in a pet's eating behavior utilizing pet eating history data is disclosed, the method includes receiving a plurality of pet eating history data records from a database, determining a subset from the plurality of pet eating history data records, determining a predicted distribution based on the subset from the plurality of pet eating history data records, the predicted distribution including a baseline, an upper threshold, and a lower threshold, receiving current pet data from a pet sensor including a meal event total value, analyzing whether the meal event total value exceeds the upper threshold or the lower threshold, and outputting a notification indicative of a result responsive to the analysis.

Description

[Technical Field]

[0001] Various embodiments of the present disclosure generally relate to detecting pet eating patterns, and in some embodiments, the present disclosure relates to systems and methods for utilizing pet eating history data to identify changes in a pet's eating behavior. [Background technology]

[0002] Your pet's appetite and corresponding eating habits are important indicators of their health. For example, if your pet is spending longer or shorter than average time eating, this could be an indication of health issues such as dental problems. Detecting and analyzing eating behavior can be an extremely useful tool for detecting potential issues in your pet before they become major problems.

[0003] Previous methods sometimes involved pet owners tracking and recording when their pets ate. However, because pet owners don't always see everything their pets eat or don't eat, it can be difficult to identify subtle eating trends. For example, previous methods may not account for the possibility that a pet is stealing another pet's food or that another pet is stealing the pet's food. Furthermore, previous techniques may not account for unexpected eating events, such as eating events that occur when the pet owner is not present, during the eating detection process.

[0004] Furthermore, conventional methods may not be able to dynamically adapt to the feeding behavior of individual pets. Feeding detection is not a one-size-fits-all method. For example, feeding styles vary depending on the breed and individual pet. Furthermore, feeding detection can be even more difficult for small pet breeds, as they tend to eat small amounts of food frequently rather than two or three substantial meals.

[0005] The present disclosure is intended to address the above-mentioned problems. The description of the background art in this section is intended to provide a brief overview of the background of the present disclosure. Unless otherwise specified in this specification, the content described in this section is not prior art to the claims of the present application. Therefore, the description in this section is not an admission that it is prior art or suggests prior art. Summary of the Invention

[0006] According to certain aspects of the present disclosure, methods and systems are disclosed for utilizing pet eating history data to identify changes in a pet's eating behavior.

[0007] In one aspect, an exemplary embodiment of a computer-implemented method for identifying changes in a pet's eating behavior using pet eating history data includes receiving, by one or more processors, a plurality of pet eating history data records from a database. Each record in the plurality of pet eating history data records includes a past meal event value and a meal event date. The method may further include determining, by the one or more processors, a subset from the plurality of pet eating history data records. The method may also include determining, by the one or more processors, an expected distribution based on the subset from the plurality of pet eating history data records. The expected distribution includes a baseline, an upper threshold, and a lower threshold, the upper and lower thresholds corresponding to the baseline. The method may also include receiving, by the one or more processors, current pet data from a pet sensor, the current pet data including a meal event total value. The method may further include analyzing, by the one or more processors, whether the meal event total value exceeds the upper threshold or the lower threshold, and outputting, by the one or more processors, a notification indicating a result of the analysis.

[0008] In a further aspect, an exemplary embodiment of a computer system for identifying changes in a pet's eating behavior using companion pet eating history data is disclosed. The computer system comprises at least one memory storing instructions and at least one processor configured to execute the instructions to perform operations. The operations may include receiving a plurality of pet eating history data records from a database. Each record in the plurality of pet eating history data records includes a past meal event value and a meal event date. The operations may also include determining a subset from the plurality of pet eating history data records. The operations may also include determining an expected distribution based on the subset from the plurality of pet eating history data records. The expected distribution includes a baseline, an upper threshold, and a lower threshold, the upper and lower thresholds corresponding to the baseline. The operations may also include receiving current pet data from a pet sensor, including a meal event total value; analyzing whether the meal event total value exceeds the upper or lower threshold; and outputting a notification indicating a result of the analysis.

[0009] In a further aspect, an exemplary embodiment of a non-transitory computer-readable medium is disclosed that contains instructions that, when executed by a processor, cause the processor to perform operations for identifying changes in a pet's eating behavior using companion pet eating history data. The operations may include receiving a plurality of pet eating history data records from a database. Each record in the plurality of pet eating history data records includes a past meal event value and a meal event date. The operations may also include determining a subset from the plurality of pet eating history data records. The operations may also include determining an expected distribution based on the subset from the plurality of pet eating history data records. The expected distribution includes a baseline, an upper threshold, and a lower threshold, the upper and lower thresholds corresponding to the baseline. The operations may also include receiving current pet data from a pet sensor, including a meal event total value; analyzing whether the meal event total value exceeds the upper or lower threshold; and outputting a notification indicating a result of the analysis.

[0010] It is to be understood that the foregoing general description and the following detailed description are merely exemplary of embodiments of the present disclosure as set forth in the claims, and are not intended to limit the disclosure of the embodiments of the present disclosure as set forth in the claims. [Brief explanation of the drawings]

[0011] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate various exemplary embodiments and, together with the following description, serve to explain the principles of embodiments of the present disclosure. [Figure 1A] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1B-1] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1B-2] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1C-1] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1C-2] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1D-1] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1D-2] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1E-1] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1E-2] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1F-1] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1F-2] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1G-1] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1G-2] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1H-1] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1H-2]FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1I-1] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1I-2] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1J-1] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 1J-2] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments. [Figure 2A] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet feeding data, according to one or more embodiments. [Figure 2B] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet feeding data, according to one or more embodiments. [Figure 2C] FIG. 1 illustrates an exemplary environment of a platform for analyzing and displaying pet feeding data, according to one or more embodiments. [Figure 3] 1 is a flowchart illustrating an exemplary method for utilizing pet eating history data to identify changes in a pet's eating behavior, according to one or more embodiments. [Figure 4] 1 is a flowchart further illustrating an exemplary method for determining a subset from a plurality of pet eating history data records for determining a predicted distribution, according to one or more embodiments. [Figure 5] 1 is a flowchart further illustrating an exemplary method for determining whether a baseline of a forecast distribution is valid, according to one or more embodiments. [Figure 6] FIG. 1 illustrates an exemplary environment in which the techniques presented herein can be utilized, according to one or more embodiments. [Figure 7]FIG. 1 illustrates an example of a computing device capable of implementing the techniques presented herein, according to one or more embodiments. DETAILED DESCRIPTION OF THE INVENTION

[0012] According to certain aspects of the present disclosure, a method and system for detecting and analyzing pet eating patterns is disclosed. Conventional techniques may rely on pet owners to track and record their pet's eating events, and may therefore be deemed inadequate for this purpose. Furthermore, conventional techniques may not be able to dynamically adapt to the individual eating habits of a pet. Therefore, there is a need for improved techniques for detecting and analyzing pet eating patterns.

[0013] The amount of time a pet spends eating can be very significant. For example, if a pet's eating time becomes longer or shorter than average, pet owners may want to investigate for potential health issues. Longer feeding times may indicate that the pet is eating more carefully or may not feel hungry. Potential health issues associated with changes in eating behavior include dental problems, gastrointestinal issues, and the pet's picky eating habits. Small changes such as changing the food bowl, type of food, or food form can also affect a pet's eating habits.

[0014] Therefore, there is a need for an eating detection technology that detects eating events in a pet and analyzes the detected eating events to identify patterns in the eating events. The eating detection technology disclosed herein can objectively indicate to a pet owner whether their pet's eating behavior is changing. Such changes in the pet's eating behavior can be an indicator of a potential health problem or whether the pet should be fed more or less. Furthermore, information about a pet's eating events can be shared with the pet's veterinarian to help the pet owner provide the veterinarian with context about what is happening in the pet's daily life.

[0015] As described in more detail below, various embodiments describe systems and methods for identifying changes in a pet's eating behavior by utilizing historical pet eating data. The systems and methods can collect and analyze historical pet eating data to calculate a predicted distribution of future eating events for the pet. The predicted distribution can include a baseline, an upper threshold, and a lower threshold. The systems and methods can receive the pet's current eating data and compare the pet's current eating data to the predicted distribution. The systems and methods can notify the pet owner of any changes in the pet's eating data by outputting a notification indicating the results of the comparison.

[0016] Exemplary Wellness Data Platform 1A-1J-2 illustrate an exemplary environment of a platform for analyzing and displaying pet wellness data, according to one or more embodiments.

[0017] 1A illustrates a "Dashboard" page in an exemplary environment of a platform for collecting, analyzing, and displaying pet data, according to one or more embodiments. The platform may display the pet's overall wellness score and one or more of the following behaviors: "Scratching," "Licking," "Sleeping," "Eating," and "Drinking." The platform may also display options to contact a veterinarian (e.g., "Chat with a vet"), send summary data to a recipient (e.g., "Share health report"), participate in a research program (e.g., "Contribute to research"), or any combination of these options.

[0018] The Platform may also display a "Dashboard" page while it is still in the early stages of collecting data from your pet. For example, while it is still collecting data from your pet, there may not be enough data to analyze and display the data. Therefore, the Platform may display "Gathering Data" for one or all of the displayed wellness scores, such as "Scratching Behavior" data, "Licking Behavior" data, "Sleep" data, "Eating" data, and "Water Intake" data.

[0019] 1B-1 and 1B-2 further illustrate a "Dashboard" page in an exemplary environment of a platform for collecting, analyzing, and displaying pet wellness data, according to one or more embodiments.

[0020] The platform may display the pet's overall wellness score and one or more of the following behavioral items: "Scratching," "Licking," "Sleeping," "Eating," and "Water Intake." While the platform is collecting data to establish a baseline, the platform may display "Establishing Baseline" next to any of the displayed behavioral items. In some embodiments, while the platform is in the process of establishing a baseline, the platform may display a duration value for each behavioral item (e.g., "28 minutes" for "Licking," "235 seconds" for "Scratching," "8.4 hours of sleep with two interruptions" for "Sleep," "13 minutes" for "Eating," and "2 minutes" for "Water Intake"). Duration may be expressed, for example, in seconds, minutes, hours, or any combination thereof. The platform may also display options to contact a veterinarian (e.g., "Chat with a Veterinarian"), to send summary data to a recipient (e.g., "Share Health Report"), to participate in a research program (e.g., "Contribute to Research"), or any combination of these options.

[0021] 1C-1 and 1C-2 further illustrate a "Health Insights" page in an exemplary environment of a platform for collecting, analyzing, and displaying pet wellness data in accordance with one or more embodiments.

[0022] The platform may display the pet's overall wellness score and one or more of the following behavioral categories: "scratching," "licking," "sleeping," "eating," and "water intake." The pet's overall wellness score may be a score (e.g., "88") based on a comprehensive analysis of all (or some) of the pet's behaviors. The platform may also display an image showing where the wellness score falls on a rating scale and a comparison of the wellness score to a previous wellness score (e.g., in FIG. 1C-1 , the value "8" and a downward arrow indicate a decrease of "8" points from the previous score). The platform may also display a description of the pet's current health status based on the wellness score (e.g., "Otto's Doing Well"). In some embodiments, if the platform does not have enough data to display the overall wellness score, the platform may display an indication that the platform is in a "collecting data" state, as shown in FIG. 1D-1 .

[0023] Once the platform has completed setting a baseline for a particular behavioral item, the platform may display an image showing a comparison of the behavioral baseline and the pet's current behavior. For example, in the "Scratching" category, the pet's current behavior may be "Infrequent," "Occasional," "Elevated," and / or "Severe" compared to the pet's scratching baseline. In the "Licking" category, the pet's current behavior may be "Very Infrequent," "Occasional," "Elevated," and / or "Very Extensive" compared to the pet's licking baseline. In the "Sleep" category, the pet's current behavior may be "Restful," "Slightly Disrupted," and / or "Disrupted" compared to the pet's sleep baseline. In the "Eating" category, the pet's current eating behavior may be "Below average," "Average," and / or "Above average" compared to the pet's eating baseline. The "Water Intake" section allows the pet's current water intake behavior to be "below average," "average," and / or "above average" compared to the pet's water intake baseline.

[0024] The platform may also display the duration of the behavior, the average duration of the behavior, the previous duration of the behavior, and / or a comparison with a previous period for the behavior (e.g., the previous day). For example, for the "scratching behavior" item, the platform may display an average duration of "235 seconds per day" and a behavior comparison of "-5 seconds compared to the previous day." For the "licking behavior" item, the platform may display an average duration of "28 minutes per day" and a behavior comparison of "-3 minutes compared to the previous day." For the "sleep" item, the platform may display a behavior comparison of "8.4 hours of sleep" and "+10 seconds compared to baseline." The platform may also display the number of interruptions (e.g., "2 interruptions") and a comparison with the "interruption" baseline (e.g., "-1 interruption compared to baseline"). For the "eating" item, the platform may display a previous duration of "13 minutes" and a behavior comparison of "+10 seconds compared to baseline." For the "Fluid Intake" item, the platform can display the previous duration of "2 minutes" and the behavioral comparison of "Baseline Ratio + 10 seconds."

[0025] The platform may also display options to view past or current data. When a user selects this option, the platform may display details of previously collected data. For example, the platform may display an option for viewing the "Last 7 day average" under the "Scratching Behavior" category. The platform may also display an option for viewing the "Last 7 day average" under the "Licking Behavior" category. The platform may also display an option for viewing detailed information about "Last night" under the "Sleep" category. The platform may also display an option for viewing detailed information about "Yesterday" under the "Food Intake" category. The platform may also display an option for viewing detailed information about "Yesterday" under the "Water Intake" category. The platform may also display an option for contacting a veterinarian (e.g., "Chat with a Vet"), sending summary data to a recipient (e.g., "Share Health Report"), participating in a research program (e.g., "Contribute to Research"), or any combination of these options.

[0026] 1E-1 and 1E-2 further illustrate a "Wellness Score" page in an exemplary environment of a platform for collecting, analyzing, and displaying pet wellness data, according to one or more embodiments.

[0027] The platform may display a wellness score (e.g., a score of "88"), a semicircular ring or arc indicating where the wellness score lies on a spectrum, or both. The wellness score may be a score corresponding to a pet's health status. For example, the wellness score may be a score based on an analysis of one or all of the pet's behaviors. The platform may also display a display corresponding to a wellness score label (e.g., "Low," "Okay," or "Excellent"). A score between 0 and 59 may be associated with the label "Low," a score between 60 and 79 may be associated with the label "Okay," and a score between 80 and 100 may be associated with the label "Excellent." In some embodiments, a color may be associated with each label. For example, a red color may be associated with the label "Low," a yellow color may be associated with the label "Okay," and a green color may be associated with the label "Excellent." In some embodiments, the platform may display a bar graph showing the wellness score over the past day or days, or over the past month or months. The graph can also be color coded so that the color of the wellness score label for a given day corresponds to the color of the graph for that day.

[0028] In some embodiments, as shown in FIG. 1F-1, if there is not enough data to generate a wellness score, the platform may display a "Not Enough Data" label. Additionally, a color, such as gray, may be associated with the "Not Enough Data" label. For example, if a displayed graph contains one or more days labeled "Not Enough Data," the one or more days labeled "Not Enough Data" may be displayed in gray on the graph.

[0029] The platform may also display options to learn more about feeding metrics (e.g., "Learn about eating levels") and to get advice from a veterinarian (e.g., "Chat with a vet").

[0030] 1G-1 and 1G-2 further illustrate an "Eating" page in an exemplary environment of a platform for collecting, analyzing, and displaying pet wellness data, according to one or more embodiments.

[0031] The platform may display whether the pet's current eating behavior is "below average," "average," or "above average" compared to the pet's eating baseline. The platform may also display the average amount of time the pet spends eating (e.g., "13 minutes per day on average").

[0032] The platform may also display a graph showing the times the pet was eating, which may track all of the pet's eating events. In some embodiments, the eating data may be captured by a sensor or electronic device worn by the pet. The eating times may be displayed in a graph format with date on the y-axis and time of day on the x-axis. The graph may include intervals showing the start and end of the pet's eating time. The start of the interval is when the pet starts eating, and the end of the interval is when the pet stops eating. The platform may also display when the most recent meal event occurred (e.g., "Last meal event at 4:42 pm (3 hours ago)").

[0033] The platform may also display a bar graph visually representing the number of minutes per day the pet spends feeding on a weekly (as shown in FIG. 1G-1) or monthly (as shown in FIG. 1H-1) basis. The platform may display the bar graph for that day in a color that corresponds to whether the pet's feeding behavior on that day is "below average," "average," or "above average" compared to the pet's feeding baseline. In some embodiments, while the platform is in the process of collecting pet feeding data, the graph may not display any data (as shown in FIG. 1I-1).

[0034] The platform may also display options to learn more about feeding metrics (e.g., "Learn about feeding levels") and to consult with a veterinarian (e.g., "Chat with a vet").

[0035] 1J-1 and 1J-2 further illustrate a "Drinking" page in an exemplary environment of a platform for collecting, analyzing, and displaying pet wellness data, according to one or more embodiments.

[0036] The platform may display whether the pet's current water intake behavior is "below average," "average," or "above average" compared to the pet's water intake baseline. The platform may also display the average amount of time the pet spends drinking water (e.g., "an average of 3 minutes per day").

[0037] The platform may also display a bar graph visually representing the number of minutes per day the pet spends drinking on a weekly or monthly basis. The platform may also display the bar graph for that day in a color that corresponds to whether the pet's drinking behavior on that day is "below average," "average," or "above average" compared to the pet's drinking baseline. In some embodiments, the platform may not display data on the graph while it is still collecting the pet's drinking data.

[0038] Exemplary Feeding Data Platform 2A-2C illustrate an exemplary environment of a platform for analyzing and displaying pet feeding data, according to one or more embodiments.

[0039] FIG. 2A illustrates an "Eating Events" interface in an exemplary environment of a platform for displaying pet eating data, according to one or more embodiments. The platform may display the number of eating events that occurred in a particular time period (e.g., "2 events yesterday"). The number of eating events corresponds to the number of times the pet eats food, treats, etc. In some embodiments, the eating events may be captured by a sensor or electronic device attached to the pet. The platform may also display the length of time the pet spent eating (e.g., "120 seconds"). The length of time the pet spent eating corresponds to the sum of the lengths of multiple eating events. The length of time the pet spent eating may also be described, for example, in seconds, minutes, hours, or any combination thereof.

[0040] FIG. 2B illustrates an "Eating" interface in an exemplary environment of a platform for displaying pet eating data, according to one or more embodiments. The platform may display eating events that occurred within a particular time period, such as a day, a month, or a year. The platform may display a list of eating events that occurred within a particular time period (e.g., "February 9th"). In some embodiments, each displayed eating event may include a length (e.g., "Length: 120 seconds"), a confidence level (e.g., "Confidence: 58%"), or both. "Length" may correspond to the duration of a particular eating event. "Confidence" may correspond to how confident the platform is in determining the eating event. Additionally, in some embodiments, each eating event may be colored with a particular shade of color corresponding to the confidence level. For example, the color shade of an eating event may be darker for higher confidence levels (e.g., dark green for 99% confidence) and lighter for lower confidence levels (e.g., light green for 25% confidence).

[0041] 2C illustrates a "Feeding" interface in an exemplary environment of a platform for displaying pet feeding data, according to one or more embodiments. The platform may display a timeline corresponding to a particular time period, such as a day, a month, or a year. In some embodiments, the platform may display a line at the location of the feeding event. The line may also be tinted with a particular color corresponding to, for example, the confidence level of the feeding event. The "confidence level" may correspond to how confident the platform is in determining the feeding event.

[0042] Exemplary Methods for Identifying Changes in Pet Eating Behavior FIG. 3 illustrates an exemplary process 300 for utilizing pet eating history data to identify changes in a pet's eating behavior, according to one or more embodiments.

[0043] The method may include receiving, by one or more processors, a plurality of pet eating history data records from a database (step 302). Each pet eating history data record includes a past eating event value and a eating event date. The database may store each pet eating history data record in real time. Alternatively, the database may store each pet eating history data record after a predetermined time (e.g., end of day). A pet sensor, an electronic device, or both attached to a pet may capture eating events in real time, and the database may receive the pet eating history data from the pet sensor, the electronic device, or both. The pet sensor, the electronic device, or both may continuously transmit the pet eating history data to the database, either in real time or after a predetermined period of time. For example, the pet sensor, the electronic device, or both may transmit updated pet eating history data to the database every minute, every hour, every day, every week, etc. The database that receives the pet eating history data may store the pet eating history data in the pet eating history data records. Additionally, if the database has already received pet eating history data for a particular meal event date and stored it in a pet eating history data record, the database can overwrite (update) that stored pet eating history data record with the most recently received pet eating history data for that meal event date.

[0044] Each record in the plurality of pet eating history data records may include a past eating event value and a eating event date. The past eating event value may include the sum of the durations of all eating events that occurred on that eating event date. For example, the past eating event value may be "120 seconds," which is the total length of time the pet spent eating, and the corresponding date may be "February 1, 2021." The past eating event value may be expressed in seconds, minutes, hours, or any combination thereof.

[0045] Additionally, each pet eating history data record may also include a past pet identifier, a past sensor wear rate, or both. The past pet identifier may include a unique identifier corresponding to a sensor and / or electronic device worn by the pet. The past sensor wear rate may correspond to the percentage of time the pet wore the pet sensor on the meal event date. For example, the past sensor wear rate may be 0.5, which may mean that the pet wore the sensor 50% of the time on the meal event date.

[0046] The method may also include determining, by one or more processors, a subset from the plurality of pet eating history data records (step 304). The subset from the plurality of pet eating history data records may include at least one pet eating data record. In some embodiments, the subset from the plurality of pet eating history data records may include all of the pet eating data records of the plurality of pet eating history data records. In some embodiments, the subset is stored in a database. Note that the process of determining the subset from the plurality of pet eating history data records is described in more detail in steps 402-408 of FIG. 4.

[0047] The method may further include determining, by one or more processors, an expected distribution based on a subset of the plurality of pet eating history data records (step 306), the expected distribution including a baseline and upper and lower thresholds. The upper and lower thresholds correspond to the baseline. The baseline may be an expected total length of meal events. The expected total length of meal events may be based on an average of past meal event values ​​corresponding to the subset of the plurality of pet eating history data records. The baseline may be updated periodically (e.g., daily) based on the most recent average of past meal event values. In some embodiments, the baseline may be an average of a subset of the plurality of pet eating history data records that does not include one or more outliers (described in more detail in steps 402-408). Note that determining the validity of the baseline is described in more detail in steps 502-508 of FIG. 5.

[0048] The upper and lower thresholds can correspond to a baseline, and the upper and / or lower thresholds can define a range for the total length of meal events. For example, the upper and / or lower thresholds can be set at ±0.84 standard deviations from the baseline. In this case, approximately 40% of the pet's days would be considered above or below average (20% according to the upper threshold and 20% according to the lower threshold), and 60% of the pet's days would be considered average. The upper and / or lower thresholds can provide flexibility. For example, if the pet eats an extra meal, this behavior can be considered above the upper threshold ("above average"). Also, if the pet skips a meal, this behavior can be considered above the lower threshold ("below average").

[0049] The method may further include receiving, by the one or more processors, current pet data from the pet sensor, including a meal event total value (step 308). The pet sensor may be a pet sensor attached to the pet, an electronic device, or both. The current pet data may also include a pet identifier, a corresponding date, a sensor wear rate, or any combination thereof. The pet identifier may include a unique identifier corresponding to the pet sensor. The corresponding date may include a date corresponding to when the meal event total value occurred. The pet sensor wear rate may correspond to the proportion of time the pet wore the pet sensor on the corresponding date. The meal event total value may include the sum of the durations of all meal events that occurred on the corresponding date. For example, the meal event total value may be "50 seconds," which is the total length of time the pet spent eating, and the corresponding date may be "December 21, 2021." The meal event total value may also be measured in seconds, minutes, hours, or any combination thereof.

[0050] The method may also include analyzing, by one or more processors, whether the meal event total value exceeds an upper threshold or a lower threshold (step 310). The meal event total value may be compared to the upper and lower thresholds. For purposes of this disclosure, the meal event total value may exceed the upper threshold if the meal event total value is above the upper threshold, and may exceed the lower threshold if the meal event total value is below the lower threshold.

[0051] The method may also include outputting, by the one or more processors, a notification indicating results responsive to the analysis (step 312). This output results in a notification being displayed on a user interface of an electronic device, such as a mobile phone. The notification may be in the form of an alert notification, a graphic image (e.g., a graph), or both. Exemplary user interfaces are shown in FIGS. 1F-1 through 1H-2.

[0052] The notification may include at least one of an above average eating notification, an average eating notification, and a below average eating notification. An above average eating notification may indicate that the pet is eating more than usual. For example, an above average eating notification may correspond to a total number of eating events meeting or exceeding an upper threshold. An above average eating notification may also be associated with the pet eating an extra treat, a large mealtime portion, or a longer-than-usual eating event. Meanwhile, an average eating notification may indicate that the pet is eating as usual. For example, an average eating notification may correspond to a total number of eating events below an upper threshold and above a lower threshold. Another below average eating notification may indicate that the pet is eating less than usual. For example, a below average eating notification may correspond to a total number of eating events meeting or exceeding a lower threshold. Additionally, notifications about below average feeding can be related to if the pet misses a treat (one or two times), if the portion is small at mealtime, or if the eating event is shorter than normal.

[0053] It should be noted that while Figure 3 illustrates exemplary blocks of the exemplary method 300, in some implementations, the exemplary method 300 may include additional blocks, fewer blocks, modified blocks, or reordered blocks compared to those illustrated in Figure 3. Additionally or alternatively, two or more blocks of the exemplary method 300 may be performed simultaneously.

[0054] 4 illustrates an exemplary method 400 for determining a subset from a plurality of pet eating history data records, according to one or more embodiments. Note that the method 400 illustrated in FIG. 4 corresponds to step 304 of FIG. 3.

[0055] The method may include identifying, by one or more processors, one or more pet eating history data records from the plurality of pet eating history data records that represent outliers (step 402). For example, determining whether a pet eating history data record represents an outlier may include determining whether the pet eating history data record meets or exceeds an outlier threshold. Such determination may include subtracting the baseline value of the pet eating history data record from the meal event total value and dividing the result by the square root of the variance of the expected distribution. For example, if the result meets or exceeds a predetermined outlier threshold, the method may skip (exclude) the pet eating history data record (step 404) and proceed to analyze the next pet eating history data record in the plurality of pet eating history data records.

[0056] The method may further include excluding one or more pet eating history data records that exhibit outliers (step 404). As described in step 402, the method may further include excluding the pet eating history data records if the analysis of the pet eating history data records results in the pet eating history data records meeting or exceeding an outlier threshold. In some embodiments, excluding one or more pet eating history data records may include skipping the one or more pet eating history data records so that the skipped records are not included in the subset of the plurality of pet eating history data records. Furthermore, in some embodiments, excluding one or more pet eating history data records may include deleting the one or more pet eating history data records from the database.

[0057] The method may further include identifying one or more pet eating history data records from the plurality of pet eating history data records, each having a historical sensor wear rate below a sensor wear threshold (step 406). In some embodiments, the sensor wear threshold may be established to ensure that the pet sensor has been worn for at least a minimum length of time, and the pet sensor wear threshold may correspond to a percentage of time that the pet has worn the pet sensor. For example, the historical sensor wear rate value may be 0.5, which may mean that the sensor was worn for at least 50% of the time on each of several consecutive days.

[0058] In some embodiments, the historical sensor attachment rates of one or more pet eating history data records not excluded in step 404 may be compared to a sensor attachment threshold. One or more pet eating history data records each having a historical sensor attachment rate that meets or exceeds the sensor attachment threshold may then be added to the subset of the plurality of pet eating history data records. Additionally, one or more pet eating history data records each having a historical sensor attachment rate that is below the sensor attachment threshold may be excluded from the subset of the plurality of pet eating history data records (as described in more detail in step 408).

[0059] The method may further include excluding one or more pet eating history data records (step 408), each having a historical sensor attachment rate below the sensor attachment threshold. As described above in step 406, one or more pet eating history data records may be excluded if each of the one or more pet eating history data records has a historical sensor attachment rate below the sensor attachment threshold. In some embodiments, excluding one or more pet eating history data records may include skipping the one or more pet eating history data records so that the skipped records are not included in the subset of the plurality of pet eating history data records. Further, in some embodiments, excluding one or more pet eating history data records may include deleting the one or more pet eating history data records from the database.

[0060] It should be noted that while Figure 4 illustrates exemplary blocks of the exemplary method 400, in some implementations, the exemplary method 400 may include additional blocks, fewer blocks, modified blocks, or reordered blocks compared to those illustrated in Figure 4. Additionally or alternatively, two or more blocks of the exemplary method 400 may be performed simultaneously.

[0061] 5 illustrates an exemplary method 500 for determining whether a baseline is valid, according to one or more embodiments. Note that the method 500 illustrated in FIG. 5 may correspond to or relate to step 306 of FIG. 3.

[0062] The method may include determining whether the baseline is valid (step 502), which is described in more detail below in steps 504 and 506. As described in steps 402-408, the baseline may be determined based on a subset from the plurality of pet eating history data records that does not include one or more outliers.

[0063] The method may include determining whether a subset of the plurality of pet eating history data records includes a predetermined number of pet eating history data records associated with meal event dates within a predetermined time range (step 504). In some embodiments, in order to establish a baseline, the subset must include a predetermined number of pet eating history data records associated with meal event dates within a predetermined time range to ensure sufficient data is captured for establishing the baseline. This predetermined time range may be days, weeks, months, years, or any combination thereof. For example, the predetermined number of pet eating history data records may be 7, and the predetermined time range may be 30 days. In this example, the determination would be whether the subset includes at least 7 pet eating history data records with meal event dates within the past 30 days.

[0064] The method may include determining whether each of the predetermined number of pet eating history data records is further associated with a historical sensor wear rate that meets or exceeds a baseline sensor wear threshold (step 506). In some embodiments, the historical sensor wear rates of one or more pet eating history data records may be compared to the baseline sensor wear threshold. The baseline may then be determined to be valid if one or more pet eating history data records have a historical sensor wear rate that meets or exceeds the baseline sensor wear threshold.

[0065] The method may also include displaying the baseline via a user interface in response to determining that the baseline is valid (step 508). For example, the baseline may be displayed on a user interface of a mobile device. The baseline may be displayed as a chart, graph, or the like. The baseline may also be displayed according to the exemplary environments shown in FIGS. 1A-1J-2.

[0066] It should be noted that while Figure 5 illustrates exemplary blocks of the exemplary method 500, in some implementations, the exemplary method 500 may include additional blocks, fewer blocks, modified blocks, or reordered blocks compared to those illustrated in Figure 5. Additionally or alternatively, two or more blocks of the exemplary method 500 may be performed simultaneously.

[0067] Exemplary Environment and Exemplary Device 6 illustrates an example environment 600 in which the techniques presented herein can be utilized. One or more user devices 605, one or more external systems 610, and one or more server systems 615 can communicate via a network 601. As described in more detail below, the one or more server systems 615 can communicate with one or more other components of the environment 600 via the network 601. The one or more user devices 605 can be associated with a user.

[0068] In some embodiments, the components of environment 600 are associated with a public entity, such as a veterinarian, clinic, animal specialist, research center, etc. In some embodiments, one or more of the components of environment 600 are associated with a different entity than the other components. The systems and devices of environment 600 can communicate in any configuration.

[0069] The user device 605 may be configured to allow a user to access and interact with other systems in the environment 600 through the user device 605. For example, the user device 605 may be a computer system such as a desktop computer, a mobile device, a tablet, etc. In some embodiments, the user device 605 may include one or more electronic applications (e.g., programs, plug-ins, browser extensions, etc.) installed on the memory of the user device 605.

[0070] The user device 605 may include a display / user interface (UI) 605A, a processor 605B, a memory 605C, a network interface 605D, or any combination thereof. The processor 605B enables the user device 605 to execute an operating system (O / S) and at least one electronic application, all of which are stored in the memory 605C. The electronic application may be a desktop program, a browser program, a web client, a mobile application program (which may be a browser program in a mobile O / S), an applicant-specific program, system control software, system monitoring software, a software development tool, or the like. For example, the environment 600 may extend the information of a web client accessible through a web browser. In some embodiments, the electronic application may be associated with one or more of the other components in the environment 600. The application may manage the memory 605C, such as a database, and send streaming data to the network 601. The display / UI 605A may be a display with a touch panel or other input system (e.g., a mouse, a keyboard, etc.) that allows a user to interact with the application and the O / S. Network interface 605D can be a TCP / IP network interface (e.g., for Ethernet or wireless communication with network 601). Processor 605B can generate data, receive user input from display / UI 605A, send and receive messages to server system 615, or any combination thereof, in parallel with executing applications, and can perform one or more further steps before providing output to network 601.

[0071] External system 610 can be, for example, one or more third party and / or auxiliary systems that can be integrated into or communicate with server system 615 to perform various eating detection tasks. External system 610 can communicate with other devices or systems in environment 600 via one or more networks 601. For example, external system 610 can communicate with server system 615 on one or more networks 601 via API (application programming interface) access and with user devices 605 on one or more networks 601 via web browser access.

[0072] In various embodiments, network 601 can be a wide area network ("WAN"), a local area network ("LAN"), a personal area network ("PAN"), or the like. In some embodiments, network 601 includes the Internet, and the provision of information and data between various systems occurs online. The term "online" can refer to connecting to or accessing a source of data or information from a location separate from other devices or networks connected to the Internet. Alternatively, the term "online" can refer to connecting to or accessing a network (wired or wireless) via a mobile communication network or device. The Internet is a global system of computer networks, a web of networks that enables parties at networked computers or other devices to obtain information from other computers and communicate with parties at other computers or devices. The most widely used part of the Internet is the World Wide Web (often abbreviated "WWW" or simply referred to as the "Web"). The term "website page" broadly encompasses any location or data store that is made accessible online, for example, by being hosted or operated by a computer system, and that may contain data that is configured to cause a program, such as a web browser, to perform operations such as sending and receiving data, processing, displaying visually, or generating an interactive interface.

[0073] Server system 615 may comprise an electronic data system and may comprise computer-readable memory, such as a hard drive, flash drive, disk, etc. In some embodiments, server system 615 provides and / or interacts with application programming interfaces for exchanging data with other systems (e.g., one or more of the other components in the environment).

[0074] The server system 615 may include a database 615A and at least one server 615B. The server system 615 may be a computer, a computer system (e.g., a rack server), a cloud service computer system, or any combination thereof. The server system may store or access the database 615A (e.g., hosted on a third-party server or in memory 615E). The server may include a display / UI 615C, a processor 615D, memory 615E, a network interface 615F, or any combination thereof. The display / UI 615C may be a display with a touch panel or other input system (e.g., a mouse, keyboard, etc.) that allows a person operating the server 615B to control the functions of the server 615B. The server system 615 may run an operating system (O / S) and at least one instance of a servlet program, both of which are stored in memory 615E, via the processor 615D.

[0075] 6 depicts the components of environment 600 as separate components, it should be understood that in some embodiments, a component or portion of a component of environment 600 may be integrated with or incorporated into one or more other components. For example, a portion of display 615C may be integrated into user device 605, etc. In some embodiments, the operations or aspects of one or more components described above may be distributed among one or more other components. Any suitable arrangement and integration of the various systems and devices of environment 600 may be used.

[0076] It should be noted that in the method descriptions above and below, components shown in FIG. 6 (e.g., server system 615, user device 605, or components therein) may be described as performing various operations. However, it should be understood that in various embodiments, various components of the environment 600 described above may execute instructions or perform operations, including those described above. When a device performs an operation, a processor, actuator, etc. associated with the device may be considered to perform the operation. It should also be understood that various steps may be added, omitted, or reordered in any suitable manner in various embodiments.

[0077] In general, any process or operation described in this disclosure that is understood to be computer-implementable, such as the processes illustrated in FIGS. 1A-5, may be performed by one or more processors of a computer system (e.g., any of the systems or devices of environment 600 illustrated in FIG. 6), as described above. Processes or processing steps performed by one or more processors may also be referred to as operations. One or more processors may be configured to perform such operations by accessing instructions (e.g., software or computer-readable code) that, when executed by the one or more processors, cause the one or more processors to perform such operations. These instructions may be stored in the memory of the computer system. The processor may be a central processing unit (CPU), a graphics processing unit (GPU), or any suitable type of processing device.

[0078] A computer system (e.g., a system or device that performs the processes or steps illustrated in the above examples) may include one or more computing devices (e.g., one or more of the systems or devices illustrated in FIG. 6). One or more processors of a computer system may be included in a single computing device or may be distributed across multiple computing devices. Additionally, the memory of the computer system may include memory of each of the multiple computing devices.

[0079] FIG. 7 is a simplified functional block diagram of a computer 700 that can be configured as a device for executing the environments and / or methods shown in FIGS. 1A-5 according to an exemplary embodiment of the present disclosure. For example, the device 700 can include a central processing unit (CPU) 720. The CPU 720 can be any type of processor device, such as any type of special-purpose or general-purpose microprocessor device. As will be appreciated by those skilled in the art, the CPU 720 can also be one processor in a multi-core / multi-processor system operating alone or as a cluster of multiple computing devices operating as a cluster or server farm. The CPU 720 can also be connected to a data communications infrastructure 710 (e.g., a bus, message queue, network, or multi-core message passing scheme).

[0080] The device 700 may also include a main memory 740 (e.g., random access memory (RAM)) and may further include a secondary memory 730. The secondary memory 730 (e.g., read-only memory (ROM)) may be, for example, a hard disk drive or a removable storage drive. Such a removable storage drive may be, for example, a floppy disk drive, a magnetic tape drive, an optical disk drive, or flash memory. The removable storage drive in this example reads and writes to a removable storage unit in a well-known manner. The removable storage unit may be a floppy disk, magnetic tape, optical disk, or the like, which may be read and written by the removable storage drive. As will be appreciated by those skilled in the art, such a removable storage unit typically includes a computer-usable storage medium having computer software, data, or both stored thereon.

[0081] In alternative embodiments, secondary memory 730 may comprise other similar means by which computer programs or other instructions can be loaded into device 700. Examples of such means include a program cartridge and cartridge interface (e.g., as found in video game devices) or a combination of a removable storage unit and interface that allows software and data to be transferred from a removable storage unit to device 700, such as a removable memory chip and its corresponding socket (e.g., EPROM or PROM).

[0082] Device 700 may also include a communications interface ("COM") 760. Communications interface 760 allows software and data to be transferred between device 700 and external devices. Communications interface 760 may include a modem, a network interface (e.g., an Ethernet card), a communications port, a PCMCIA slot and card, etc. The software and data transferred through communications interface 760 may be in the form of signals receivable by communications interface 760, such as electronic, electromagnetic, or optical signals. These signals may be provided to communications interface 760 via a communications path in device 700. Such a communications path may be implemented using, for example, a communications channel such as wire or cable, optical fiber, a telephone line, a cellular phone link, or an RF link.

[0083] The hardware elements, operating systems, and programming languages ​​of such equipment are conventional in nature and are presumed to be sufficiently familiar to those skilled in the art. Device 700 may also include input / output ports 750 for connecting input / output devices such as a keyboard, mouse, touch panel, monitor, display, etc. Of course, various server functions may be distributed across multiple similar platforms to distribute the processing load. Alternatively, the server may be implemented by appropriate programming of a single computer hardware platform.

[0084] The program aspects of the present technology may be considered "products" or "articles of manufacture," typically in the form of executable code and / or associated data carried or embodied by any type of machine-readable medium. The "storage" medium type includes any or all of the tangible memory of a computer, processor, or the like, or its associated modules (e.g., various semiconductor memories, tape drives, disk drives, etc.), capable of providing non-transitory storage for software programming at any time. All or portions of the software may also be transmitted over various communications networks, such as the Internet. Such communications may, for example, enable software to be loaded from one computer or processor to another, such as from a management server or host computer in a mobile communications network to load software onto a server computer platform, or from a server to a mobile device. Accordingly, other types of media that may carry software elements include optical waves, radio waves, and electromagnetic waves (e.g., those used in physical interfaces between local devices, wired and optical fixed-line networks, and various air links). Additionally, the physical elements that carry such waves (e.g., wired or wireless links, optical links, etc.) may also be considered media carrying the software. As used herein, except when limited to non-transitory, tangible "storage" media, terms such as computer "readable medium" and machine "readable medium" refer to any medium that participates in providing instructions to a processor for execution.

[0085] Where reference is made in this disclosure to particular activities, such description is for convenience only and is not intended to limit the disclosure. Those skilled in the art will recognize that the concepts underlying the disclosed devices and methods can be applied to any suitable activity. This disclosure can also be understood by reference to the above description and the accompanying drawings, in which like elements are designated by the same reference numerals.

[0086] The terms used in the above description should be interpreted in the broadest reasonable sense, even if they are used to describe in detail a particular embodiment of the present disclosure. Indeed, while this point may be emphasized for some terms in the above description, if a term is intended to be interpreted in a restrictive manner, the term will be clearly and specifically so defined in the "Detailed Description of the Invention" section above. Both the general description and the detailed description are merely illustrative of the present disclosure and are not intended to limit the features set forth in the claims.

[0087] In this disclosure, the phrase "based on" means "based at least in part on." The singular forms "a," "an," and "the" are intended to include reference to the corresponding plural forms unless the context clearly dictates otherwise. Additionally, the word "exemplary" is used in its "example" sense, not its "ideal" sense. The terms "comprise," "comprising," "include," "including," and other variations thereof are intended to encompass a non-exclusive inclusion. Thus, when a process, method, or article "comprises" ("includes" or "has") enumerated elements, it does not necessarily include only the enumerated elements but can also include other elements not expressly enumerated and elements inherent to such process, method, article, or apparatus. Additionally, the term "or" is used disjunctively, i.e., the phrase "at least one of A or B" includes (A), (B), (A and A), (A and B), etc. Relative terms such as "substantially" and "generally" are used to indicate that there may be a ±10% variation from the stated or implied value.

[0088] As used herein, terms such as "user" broadly encompass one or more pet parents. Terms such as "pet" broadly encompass a user's pet, and the term "pet" can encompass multiple pets. Terms such as "provider" broadly encompass a pet care business.

[0089] In the foregoing description of exemplary embodiments of the present invention, various features of the present invention may be grouped together in a single embodiment, figure, or description thereof. It should be understood that this is done for the purpose of streamlining the disclosure and facilitating understanding of one or more of the various aspects of the present invention. However, this method of disclosure should not be interpreted as reflecting an intention that the present invention requires more features than are expressly recited in each claim. Rather, as reflected in the following claims, the number of features conferring inventive step on the present invention is fewer than all of the features shown in the single embodiment disclosed above. Accordingly, the claims following this Detailed Description of the Invention are expressly incorporated into the Detailed Description of the Invention, and each claim herein stands on its own as an embodiment of the present invention.

[0090] Furthermore, while some embodiments described herein may include some features of other embodiments but not others, those skilled in the art will recognize that combinations of features from different embodiments are also within the scope of the present invention, and that such combinations are intended to form a variety of different embodiments. For example, in the following claims, any of the embodiments defined by the claims may be used in any combination.

[0091] Thus, while particular embodiments have been described, those skilled in the art will recognize that other and further modifications may be made without departing from the spirit of the claims, and that all such modifications and variations are intended to be included within the scope of the present invention. For example, functions shown in block diagrams may be added or deleted, steps may be interchanged between functional blocks, etc. Steps may also be added or deleted to methods described within the scope of the present invention.

[0092] The subject matter of the present disclosure has been described above, but should be considered illustrative and not limiting, and the appended claims are intended to encompass all modifications, extensions, and other embodiments falling within the true spirit and scope of the present disclosure. Accordingly, the scope of the present disclosure should be determined to the fullest extent permitted by law by interpreting the following claims and their equivalents in the broadest possible sense, and should not be limited or constrained by the above detailed description of the invention. While various embodiments of the present disclosure have been described above, it will be apparent to those skilled in the art that many more embodiments are possible within the scope of the present disclosure. Accordingly, the present disclosure is not to be limited except as limited by the claims and their equivalents. Preferred embodiments of the present invention will be described below in detail. Embodiment 1 1. A computer-implemented method for identifying changes in a pet's eating behavior utilizing pet eating history data, comprising: receiving, by one or more processors, a plurality of pet eating history data records from a database, each record in the plurality of pet eating history data records including a past meal event value and a meal event date; determining, by the one or more processors, a subset from the plurality of pet eating history data records; determining, by the one or more processors, a predicted distribution based on the subset from the plurality of pet eating history data records, the predicted distribution including a baseline, an upper threshold, and a lower threshold, the upper threshold and the lower threshold corresponding to the baseline; receiving, by the one or more processors, current pet data from a pet sensor, the current pet data including a meal event total; analyzing, by the one or more processors, whether the meal event total exceeds the upper threshold or the lower threshold; outputting, by the one or more processors, a notification indicating a result responsive to the analysis; A method comprising: Embodiment 2 2. The computer-implemented method of embodiment 1, wherein the baseline is determined based on the subset from the plurality of pet eating history data records that does not include one or more outliers. Embodiment 3 3. The computer-implemented method of embodiment 2, wherein the upper and lower thresholds are determined based on at least one standard deviation from the baseline. Embodiment 4 determining the subset from the plurality of pet eating history data records; identifying, by the one or more processors, one or more pet eating history data records from the plurality of pet eating history data records that represent outliers; filtering, by the one or more processors, the one or more pet eating history data records that exhibit outliers; 2. The computer-implemented method of claim 1, comprising: Embodiment 5 determining the subset from the plurality of pet eating history data records; identifying, by the one or more processors, one or more pet eating history data records from the plurality of pet eating history data records, each having a historical sensor attachment rate below a sensor attachment threshold; filtering, by the one or more processors, the one or more pet eating history data records each having a historical sensor wear rate below the sensor wear threshold; 2. The computer-implemented method of claim 1, comprising: Embodiment 6 determining the subset from the plurality of pet eating history data records; identifying, by the one or more processors, one or more pet eating history data records from the plurality of pet eating history data records that represent outliers; identifying, by the one or more processors, one or more pet eating history data records from the plurality of pet eating history data records, each having a historical sensor attachment rate below a sensor attachment threshold; filtering, by the one or more processors, the one or more pet eating history data records that represent outliers and the one or more pet eating history data records that each have a historical sensor wear rate below the sensor wear threshold; 2. The computer-implemented method of claim 1, comprising: Embodiment 7 A computer-implemented method as described in embodiment 1, wherein the current pet data includes a pet identifier, a corresponding date, and a sensor wearing rate indicating the percentage of time the companion pet was wearing the pet sensor on the corresponding date. Embodiment 8 8. The computer-implemented method of embodiment 7, wherein the meal event total value comprises a sum of the durations of all meal events that occurred on the corresponding date. Embodiment 9 9. The computer-implemented method of embodiment 8, wherein the meal event total value is measured in seconds, minutes, or hours. Embodiment 10 2. The computer-implemented method of embodiment 1, wherein the notification includes at least one of a notification that eating is above average, a notification that eating is average, or a notification that eating is below average. Embodiment 11 A computer-implemented method as described in embodiment 1, wherein the baseline is determined to be valid if the subset from the plurality of pet eating history data records includes a predetermined number of pet eating history data records associated with past meal event dates within a predetermined time range. Embodiment 12 12. The computer-implemented method of claim 11, wherein each of the predetermined number of pet eating history data records is further associated with a historical sensor attachment rate that meets or exceeds a baseline sensor attachment threshold. Embodiment 13 at least one memory for storing instructions; at least one processor configured to perform operations by executing the instructions; 1. A computer system for utilizing companion pet eating history data to identify changes in a pet's eating behavior, comprising: The operation is receiving a plurality of pet eating history data records from a database, each record in the plurality of pet eating history data records including a past meal event value and a meal event date; determining a subset from the plurality of pet eating history data records; determining a predicted distribution based on the subset from the plurality of pet eating history data records, the predicted distribution including a baseline, an upper threshold, and a lower threshold, the upper threshold and the lower threshold corresponding to the baseline; receiving current pet data from the pet sensor, the current pet data including a meal event total; analyzing whether the meal event total exceeds the upper threshold or the lower threshold; outputting a notification indicating results responsive to the analysis; 2. A computer system comprising: Embodiment 14 14. The computer system of embodiment 13, wherein the baseline is determined based on the subset from the plurality of pet eating history data records that does not include one or more outliers. Embodiment 15 15. The computer system of embodiment 14, wherein the upper and lower thresholds are determined based on at least one standard deviation from the baseline. Embodiment 16 determining the subset from the plurality of pet eating history data records; identifying one or more pet eating history data records from the plurality of pet eating history data records that represent outliers; removing the one or more pet eating history data records that exhibit outliers; 14. The computer system of embodiment 13, comprising: Embodiment 17 determining the subset from the plurality of pet eating history data records; identifying one or more pet eating history data records from the plurality of pet eating history data records, each having a historical sensor attachment rate below a sensor attachment threshold; removing the one or more pet eating history data records each having a historical sensor wear rate below the sensor wear threshold; 14. The computer system of embodiment 13, comprising: Embodiment 18 determining the subset from the plurality of pet eating history data records; identifying one or more pet eating history data records from the plurality of pet eating history data records that represent outliers; identifying one or more pet eating history data records from the plurality of pet eating history data records, each having a historical sensor attachment rate below a sensor attachment threshold; filtering out the one or more pet eating history data records that exhibit outliers and that each have a historical sensor attachment rate below the sensor attachment threshold; 14. The computer system of embodiment 13, comprising: Embodiment 19 A non-transitory computer-readable medium containing instructions, comprising: the instructions, when executed by a processor, cause the processor to perform an operation for utilizing companion pet eating history data to identify changes in the eating behavior of a pet; The operation is receiving a plurality of pet eating history data records from a database, each record in the plurality of pet eating history data records including a past meal event value and a meal event date; determining a subset from the plurality of pet eating history data records; determining a predicted distribution based on the subset from the plurality of pet eating history data records, the predicted distribution including a baseline, an upper threshold, and a lower threshold, the upper threshold and the lower threshold corresponding to the baseline; receiving current pet data from the pet sensor, the current pet data including a meal event total; analyzing whether the meal event total exceeds the upper threshold or the lower threshold; outputting a notification indicating results responsive to the analysis; 1. A non-transitory computer-readable medium, comprising: Embodiment 20 A non-transitory computer-readable medium as described in embodiment 19, wherein the current pet data includes a pet identifier, a corresponding date, and a sensor wearing rate indicating the percentage of time the companion pet was wearing the pet sensor on the corresponding date. [Explanation of symbols]

[0093] 600 Environment 601 Network 605 User Devices 605A User Device Display / User Interface 605B User Device Processor 605C User Device Memory 605D User Device Network Interface 610 External Systems 615 Server System 615A Database 615B Server 615C Server System Display / User Interface 615D Server System Processor 615E Server System Memory 615F Server System Network Interface 700 devices (computers) 710 Data Communication Infrastructure 720 Central Processing Unit 730 Auxiliary Memory 740 main memory 750 input / output ports 760 Communication Interface

Claims

1. 1. A computer-implemented method for identifying changes in a pet's eating behavior utilizing pet eating history data, comprising: receiving, by one or more processors, a plurality of pet eating history data records from a database, each record in the plurality of pet eating history data records including a past meal event value and a meal event date; determining, by the one or more processors, a subset from the plurality of pet eating history data records; determining, by the one or more processors, a predicted distribution based on the subset from the plurality of pet eating history data records, the predicted distribution including a baseline, an upper threshold, and a lower threshold, the upper threshold and the lower threshold corresponding to the baseline; receiving, by the one or more processors, current pet data from a pet sensor, the current pet data including a meal event total; analyzing, by the one or more processors, whether the meal event total exceeds the upper threshold or the lower threshold; outputting, by the one or more processors, a notification indicating a result responsive to the analysis; A method comprising:

2. The computer-implemented method of claim 1 , wherein the baseline is determined based on the subset from the plurality of pet eating history data records that does not include one or more outliers.

3. The computer-implemented method of claim 2 , wherein the upper and lower thresholds are determined based on at least one standard deviation from the baseline.

4. determining the subset from the plurality of pet eating history data records; identifying, by the one or more processors, one or more pet eating history data records from the plurality of pet eating history data records that represent outliers; filtering, by the one or more processors, the one or more pet eating history data records that exhibit outliers; 10. The computer-implemented method of claim 1, comprising:

5. determining the subset from the plurality of pet eating history data records; identifying, by the one or more processors, one or more pet eating history data records from the plurality of pet eating history data records, each having a historical sensor attachment rate below a sensor attachment threshold; filtering, by the one or more processors, the one or more pet eating history data records each having a historical sensor wear rate below the sensor wear threshold; 10. The computer-implemented method of claim 1, comprising:

6. determining the subset from the plurality of pet eating history data records; identifying, by the one or more processors, one or more pet eating history data records from the plurality of pet eating history data records that represent outliers; identifying, by the one or more processors, one or more pet eating history data records from the plurality of pet eating history data records, each having a historical sensor attachment rate below a sensor attachment threshold; filtering, by the one or more processors, the one or more pet eating history data records that represent outliers and the one or more pet eating history data records that each have a historical sensor wear rate below the sensor wear threshold; 10. The computer-implemented method of claim 1, comprising:

7. 2. The computer-implemented method of claim 1, wherein the current pet data includes a pet identifier, a corresponding date, and a sensor wearing rate indicating the percentage of time the companion pet was wearing the pet sensor on the corresponding date.

8. The computer-implemented method of claim 7 , wherein the meal event total comprises a sum of the durations of all meal events that occurred on the corresponding date.

9. 10. The computer-implemented method of claim 8, wherein the meal event total is measured in seconds, minutes, or hours.

10. 10. The computer-implemented method of claim 1, wherein the notification includes at least one of an above average eating notification, an average eating notification, and a below average eating notification.

11. 2. The computer-implemented method of claim 1, wherein the baseline is determined to be valid if the subset from the plurality of pet eating history data records includes a predetermined number of pet eating history data records associated with past meal event dates within a predetermined time range.

12. 12. The computer-implemented method of claim 11, wherein each of the predetermined number of pet eating history data records is further associated with a historical sensor attachment rate that met or exceeded a baseline sensor attachment threshold.

13. at least one memory for storing instructions; at least one processor configured to perform operations by executing the instructions; 1. A computer system for utilizing companion pet eating history data to identify changes in a pet's eating behavior, comprising: The operation is receiving a plurality of pet eating history data records from a database, each record in the plurality of pet eating history data records including a past meal event value and a meal event date; determining a subset from the plurality of pet eating history data records; determining a predicted distribution based on the subset from the plurality of pet eating history data records, the predicted distribution including a baseline, an upper threshold, and a lower threshold, the upper threshold and the lower threshold corresponding to the baseline; receiving current pet data from the pet sensor, the current pet data including a meal event total; analyzing whether the meal event total exceeds the upper threshold or the lower threshold; outputting a notification indicating results responsive to the analysis; 2. A computer system comprising:

14. 14. The computer system of claim 13, wherein the baseline is determined based on the subset from the plurality of pet eating history data records that does not include one or more outliers.

15. The computer system of claim 14 , wherein the upper and lower thresholds are determined based on at least one standard deviation from the baseline.

16. determining the subset from the plurality of pet eating history data records; identifying one or more pet eating history data records from the plurality of pet eating history data records that represent outliers; removing the one or more pet eating history data records that exhibit outliers; 14. The computer system of claim 13, comprising:

17. determining the subset from the plurality of pet eating history data records; identifying one or more pet eating history data records from the plurality of pet eating history data records, each having a historical sensor attachment rate below a sensor attachment threshold; removing the one or more pet eating history data records each having a historical sensor wear rate below the sensor wear threshold; 14. The computer system of claim 13, comprising:

18. determining the subset from the plurality of pet eating history data records; identifying one or more pet eating history data records from the plurality of pet eating history data records that represent outliers; identifying one or more pet eating history data records from the plurality of pet eating history data records, each having a historical sensor attachment rate below a sensor attachment threshold; filtering out the one or more pet eating history data records that exhibit outliers and that each have a historical sensor attachment rate below the sensor attachment threshold; 14. The computer system of claim 13, comprising:

19. A non-transitory computer-readable medium containing instructions, comprising: the instructions, when executed by a processor, cause the processor to perform an operation for utilizing companion pet eating history data to identify changes in the eating behavior of a pet; The operation is receiving a plurality of pet eating history data records from a database, each record in the plurality of pet eating history data records including a past meal event value and a meal event date; determining a subset from the plurality of pet eating history data records; determining a predicted distribution based on the subset from the plurality of pet eating history data records, the predicted distribution including a baseline, an upper threshold, and a lower threshold, the upper threshold and the lower threshold corresponding to the baseline; receiving current pet data from the pet sensor, the current pet data including a meal event total; analyzing whether the meal event total exceeds the upper threshold or the lower threshold; outputting a notification indicating results responsive to the analysis; 1. A non-transitory computer-readable medium, comprising:

20. 20. The non-transitory computer-readable medium of claim 19, wherein the current pet data includes a pet identifier, a corresponding date, and a sensor wear rate indicating the percentage of time the companion pet was wearing the pet sensor on the corresponding date.

Images