Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
Status of Claims
In the amendment filed on October 21st 2025, claims 1, 11 and 20 have been amended, claims 5, 10, 15 and 19 have been cancelled and new claims 21-24 have been added. Therefore, claims 1-4, 6-9, 11-14, 16-18 and 20-24 are pending for examination.
35 USC § 101
Independent claims 1, 11 and 20 are no longer rejected under 35 U.S.C. 101 because the claimed invention is no longer directed to an abstract idea without significantly more. The claim(s) have been amended to include limitations that add significantly more practical application (the consecutively identified behaviors are determined based on analysis of three-dimensional (3D) accelerometer data acquired by a 3D accelerometer comprised in a device attached to the non-human animal)
The rationale above is also applicable to dependent claims 4, 6-9, 11-14, 16-18, and 20.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1-3, 6-8, 11-13, 16, 17 and 20-24 is/are rejected under 35 U.S.C. 103 as being unpatentable over Geissler et al. (US 20090058730 A1) in view of Mottram et al. (US 20100030036 A1), Kuper et al. (US 10354342 B2), Davis et al.(US 20140313303 A1) and Carson et al. (US 20230178246 A1).
In regards to claim 1, Geissler teaches a system for identifying irregularities in behaviors of a non-human animal (Paragraphs 40, 114, 168) such as domesticated animals, livestock, companion animals, wild animals and game animals). Geissler then teaches the system comprising a processing circuitry configured to provide a behavioral baseline including first information on regular behaviors of the non-human animal over a given period of time when no irregularities occur (Paragraphs 119, 169) i.e. the activity log 250 records events occurring throughout each day. In an embodiment, the activity log 250 tracks which locations are visited and/or in which activities an animal engages over the predetermined period of time. In an embodiment, the activity log 250 tracks a length of time spent at each location and/or engaged in each activity over the predetermined period of time; the analyze operation 1106 determines whether any of the animals are displaying normal behavior. For example, in an embodiment, the analyze operation 1106 may determine which animals have eaten or drunk within a predetermined period of time. In another embodiment, the analyze operation 1106 may identify trends of normal behavior (e.g., consistent eating and/or drinking habits).
Thereafter, Geissler teaches obtaining data on a series of consecutively identified behaviors of the non-human animal identified over a second period of time; perform an action upon the data not complying with the behavioral baseline, thereby indicating an irregularity in the non-human animal behavior (Paragraphs 160, 178), i.e. an analyze operation 1106 reviews and processes the received tag update data. In an embodiment, the analyze operation 1106 determines whether any of the animals are displaying abnormal behavior. For example, in an embodiment, the analyze operation 1106 may determine whether any of the animals have not eaten or drunk within a predetermined period of time. In an embodiment, the analyze operation 1106 may determine whether any of the animals have eaten or drank too often within a predetermined period of time. In another embodiment, the analyze operation 1106 may identify trends of abnormal behavior (e.g., increase or decline in eating or drinking habits). In another embodiment, the analyze operation 1106 may determine whether any animals are missing (e.g., tag out of range) or whether any unexpected animals are present (e.g., unknown or unexpected tag in range). Given that the system analyzes the tracked behavior over a predetermined time, it can then determine any abnormal/irregular behavior in the same given predetermined time as the data does not comply with the behavioral baseline, thereby generating an action such as an alert condition.
Geissler fails to teach the consecutively identified behaviors are determined based on analysis of three-dimensional (3D) accelerometer data acquired by a 3D accelerometer comprised in a device attached to the non-human animal.
Mottram on the other hand teaches the consecutively identified behaviors are determined based on analysis of three-dimensional (3D) accelerometer data acquired by a 3D accelerometer comprised in a device attached to the non-human animal (Paragraph 51) i.e. the various sensor outputs indicating the behavioral status 301 of the animal is received by the computer system 119 via the antenna 117. This data is compared to a reference physiological data model of the sensory outputs and the behavioral status 301. The 3-D accelerometer 201 records the spatial orientation and movement of the animal's head. This data is analyzed by the farm computer 119 to indicate behavioral patterns such as time spent lying, standing, walking 401 and time spent feeding or drinking 403. It would have been obvious to a person of ordinary skill in the art before the effective filing of the invention to combine Mottram’s teaching with Geissler’s teaching in order to record and track the spatial orientation and movement of the animal, to which this data is indicative of behavioral patterns such as time spent lying, standing, walking etc.
Geissler modified fails to teach upon the data not complying with the behavioral baseline, thereby indicating an irregularity in the non-human animal behavior, provide one or more irregularity preventing recommendations to a caregiver of the non-human animal based on historical behavioral data associated with the non-human animal. Kuper on the other hand teaches provide one or more irregularity preventing recommendations to a caregiver of the non-human animal based on historical behavioral data associated with the non-human animal (Column 1, lines 53-Column 2, line 3; Column 4, line 65-Column 5, line 8; Column 7, line 62-Column 8, line 16 ), i.e. the present invention optimizes workflow by animal, by facility, by pen, and by producer, based upon historical performance, gender and genetic breed and the management practices of the producer. The artificial intelligence-based modeling applied in the adaptive framework 100 calibrates the predictive recommendation unique to each producer, pen, and animal, to analyze livestock performance by location, weather, veterinary medicine or biological product, over time, by intra-organizational comparison, or benchmarks by gender, breed or by feed ration mix.
The artificial intelligence layer 146 may perform an ensemble-based processing step using the bias-based convergence algorithm 148 to run multiple, concurrent models 150 to determine the output of the ideal model 160 to promote. This multi-model, bias-based, ensemble processing approach promotes the most appropriate or primary livestock growth model 160 and resultant recommendations 173 such as feed program by selecting the most appropriate outcome and operational plan. This convergence approach may assign different weights or biases to different variables 158 among the input data 110, and the artificial intelligence layer 146 may apply one or more techniques to “learn” and adjust weights or biases to be applied based on historical correlations between modeled outcomes and the different variables, and based on the difference between actual growth rate performance and predicted growth rate performance. Many types of recommendations 173 are contemplated, and may include for example recommendations 173 regarding a type of feed 180 to be provided to livestock (such as a type or variety of corn), recommendations as to type and quantity of additives 181 to feed (such as nutrients, antibiotics and veterinary medicines, biological additives, implants, and other animal health products, etc.), mixtures 182 of feed to be provided to livestock 104, and management practice and operational recommendations 183. Examples of management and operational practice recommendations 183 include feed timing 184, frequency of feed deliveries 185, stocking rates 186, labeling and regulatory compliance recommendations 187, facility-specific management practices 188, and veterinary prescriptions 192. Examples of facility-specific management practices 188 include cattle bedding rates, bunk space per head, and cattle movement and handling, such as moving livestock from one pen to another, or one location to another. Many other recommendations 173 are possible.
According to Kuper’s disclosure, the machine learning system takes into account an ideal model based on the specific non-human animal, based on historical study, thereby if the observed study is offset from the ideal model (which by obvious would include abnormal or irregular behavior or study deviated from the ideal model), recommendations would be generated to caregiver to gear the attributes of the given animal to return back to its ideal model, and thereby obvious to one of ordinary skill in the art preventing any further irregularity
It would have been obvious to a person of ordinary skill in the art before the effective filing of the invention to combine Kuper’s teaching with Geissler modified’s teaching in order to use identify trends within and/or between animal populations that are appropriate for the condition(s) being dealt with the animal(s) in focus.
Geissler modified fails to teach providing one or more irregularity preventing recommendations to a caregiver of the non-human animal based on historical behavioral data associated with the non-human animal, and irrespective of past behaviors of non-human animals other than the non-human animal. Davis on the other hand teaches a behavioral and monitoring system where an individual’s physiological conditions and behavior is monitored and recorded such that overtime irregular or abnormal conditions or behavior may be detected, so that suggestions/recommendations may be made from the live readings cross checked by historical readings (Paragraphs 307, 359, ),i.e.
Such a monitoring service may report to the user whenever the sensed data significantly deviates from expected norms. If a person's REM sleep pulse is normally between 56 and 60 beats per second, and one night there is an episode in which the pulse varies from this range by a threshold amount (e.g., more than 5%, 15%, 30%, or 75%), then a message may be dispatched to the user (e.g., by email, text, or otherwise) noting the incident. Possible causes for the disturbance may also be communicated to the user. These causation hypotheses can be pro forma--based on textbook understandings of the noted phenomenon (e.g., caffeine before bed) discerned from stored rule data, or they can be tailored to the user--such as taking into account other user- or ambient-sensor information that might be correlated (e.g., irregular respiration, suggesting sleep apnea or the like; or an unusually warm room--as indicated by temperature data logged by a smartphone sensor as contrasted with historical norms--leading to increased blood flow for convective body cooling). Such information is also logged in a historical data store, and may also be sent for e-charting to the user's physician. [P-307]
In some embodiments, the technology serves as an advisor to a medical professional--offering suggested diagnoses, or further testing, to consider. The offered advice may be tailored in accordance with wishes of the professional, e.g., expressed in stored profile data corresponding to that professional. For example, one practitioner may express a conservative medical philosophy, in which case such an advisory service may offer only observations/suggestions in which there is a high degree of confidence. Conversely, another practitioner may be more open to novel theories and approaches, in which case the system may also present candidate diagnoses (and further testing suggestions) that is more speculative. [P-359]
Furthermore, Davis goes on to elaborate that just as the system and method may be utilized on an human individual, it may also be applicable to individual livestock or non-human animal (Paragraphs 369, 370), i.e.
Many of the techniques described in connection with humans can also be applied to animals. Unusual skin conditions can be expanded to animal hide, fur and feathers (although false positives and hidden conditions may be more likely with complex skin coverings). Vets often face a more difficult challenge than physicians, since animals cannot describe symptoms that might aid in diagnosis, making the notion of providing a candidate list of maladies and being able to quickly test for additional symptoms even more valuable. Pet owners often need to decide whether symptoms warrant a visit to a vet and whether particular visible symptoms can be explained by recent known activities of that pet. Furthermore, livestock owners face the challenge of outbreaks of contagious diseases and need to inspect their animals often to catch such diseases as early as possible. Pet and livestock owners can benefit greatly from the present technology for examining and diagnosing conditions.[P-369]
For livestock owners, an automated early warning system can be set in place where livestock passing through gates or paddocks are routinely examined for unusual skin variations that suggest closer examination is needed. Livestock are often outfitted with RF tags for identification, allowing such a monitoring system to compare individual livestock over time to rule out health conditions that have already been addressed, and to note new, emerging conditions. Wildlife managers can also benefit by setting up imaging systems on commonly traversed paths that are triggered by passing animals. Again, early detection and identification of contagious conditions or dangerous pests is key to maintaining healthy populations.[P-370]
It would have been obvious to a person of ordinary skill in the art before the effective filing of the invention to combine Davis’ teaching with Geissler modified’s teaching in order to effectively examine in isolation and further effectively identify norms versus irregular behaviors of a specific animal and effectively determine accurate remedies for specific situations trends within and/or between animal populations that are appropriate for the condition(s) being dealt with the animal(s) in focus.
Geissler modified fails to teach the behavioral baseline is adapted to past changes in the non-human animal's behaviors over time, utilizing the historical behavioral data associated with the non-human animal. Carson on the other hand teaches the behavioral baseline is adapted to past changes in the non-human animal's behaviors over time, utilizing the historical behavioral data associated with the non-human animal (Abstract; Paragraphs 23, 32), i.e.
A computer-implemented method for using historical pet eating data to determine changes in pet eating behavior is disclosed. The method includes receiving a plurality of historical pet eating data records from a database, determining a subset of the plurality of historical pet eating data records, determining an expected distribution based on the subset of the plurality of historical pet eating data records wherein the expected distribution includes a baseline, an upper threshold, and a lower threshold, receiving current pet data from a pet sensor wherein the current pet data includes a total meal event value, analyzing whether the total meal event value exceeds the upper threshold or the lower threshold, and outputting a notification indicating a result that is responsive to the analyzing[Abstract]
As will be discussed in more detail below, in various embodiments, systems and methods are described for using historical pet eating data to determine changes in pet eating behavior. By collecting and analyzing historical pet eating data, the systems and methods may be able to calculate an expected distribution for future pet eating events, where the expected distribution may include a baseline, an upper threshold, and a lower threshold. The systems and methods may then receive current pet eating data and compare such pet eating data to the expected distribution. The systems and methods may then output a notification indicating a result of the comparison to notify the pet parent of any changes in the pet's eating data.[P-23]
The platform may also display a duration of a behavior, an average duration of the behavior, a previous duration of the behavior, and/or how the behavior compares to a previous time period, such as a previous day. For example, in the “Scratching” section, the platform may display an average duration of “235 seconds/day” with a behavior comparison of “−5 seconds from previous day.” In the “Licking” section, the platform may display an average duration of “28 minutes/day” with a behavior comparison of “−3 minutes from previous day.” In the “Sleeping” section, the platform may display “8.4 duration (hours)” with a behavior comparison of “+10 seconds from baseline.” A number of disruptions may also be displayed (e.g., “2 disruptions”) and/or how the disruptions compare to a disruption baseline (e.g., “−1 disruption from baseline”). In the “Eating” section, the platform may display a previous duration of the behavior of “13 minutes” with a behavior comparison of “+10 seconds from baseline.” In the “Drinking” section, the platform may display a previous duration of the behavior of “2 minutes” with a behavior comparison of “+10 seconds from baseline.” [P-32]
It would have been obvious during the time of the said invention to combine Carson teaching with Geissler modified teaching in order to enable more effective analysis of pet behavior in habitual events
In regards to claim 2, Geissler modified teaches the information on regular behaviors includes, for each regular behavior an indication of a type of behavior (Paragraph 169) i.e. For example, in an embodiment, the analyze operation 1106 may determine which animals have eaten or drunk within a predetermined period of time. In another embodiment, the analyze operation 1106 may identify trends of normal behavior (e.g., consistent eating and/or drinking habits). Furthermore, Geissler teaches one or more of regular frequency range of the behavior, regular duration range for the behavior, regular intensity range for the behavior, regular score range of a score calculated for the behavior (Paragraphs 167, 169) i.e. the analyze operation 1106 may identify trends of normal behavior (e.g., consistent eating and/or drinking habits). In another embodiment, the analyze operation 1106 may determine which animals are in view (e.g., tag is within range), hence using the regular frequency range that the tracked animal trends to perform their normal behavior to further identify what animal is being tracked.
In regards to claim 3, Geissler modified teaches the processing circuitry is further configured to analyze the data to determine a cause for the irregularity (Paragraphs 117, 121, 129, 166-168), i.e. the tag circuitry tracks the frequency of at which a given animal eats an drinks at a given predetermined period over a period of time, to which thereby when a regular consumption of food and water is determined, the moment there is an absence of a recorded regularity, then an irregular activity is detected.
In regards to claim 6, Geissler modified teaches the behavioral baseline is an animal specific behavioral baseline determined using baseline creation data including a baseline series of consecutively identified baseline behaviors of the non-human animal identified over a third period of time in which the non-human animal is assumed to behave regularly (Paragraphs 66) i.e. when the tag 120 approaches this area of interest, the beacon 110 prompts the tag 120 to log the tag's proximity status (e.g., the tag's proximity to the beacon 110 and hence the corresponding area of interest). In an embodiment, the tag 120 periodically increments a beacon counter if the tag 120 determines the tag 120 is located in proximity to the beacon 110. In an embodiment, the tag 120 logs its proximity status by recording a number of separate visits to the beacon 110 (i.e., a number of times the tag 120 has entered and exited a range of the beacon 110). In an embodiment, the tag 120 the tag 120 logs its proximity status by recording dates and times of each visit to the beacon 110. In an embodiment, the tag 120 the tag 120 logs its proximity status by recording the length of time of one or more visits to the beacon 110. For example, the tag 120 can record the duration of time of visits to the beacon 110 that occur between reports to reader 130.
In regards to claim 7, Geissler modified teaches the processing circuitry is further configured to action is trigger an alert to a caregiver of the non-human animal upon the data not complying with the behavioral baseline, thereby indicating the irregularity in the non-human animal behavior. (Paragraphs 9, 250), i.e. the transmitting reader information from the reader transceiver to a data manager. The reader information including the tag information, information generated when the tag information is received at the reader, or a combination thereof. The method also include processing the reader information received by the data manager to determine a status of the animal and presenting an alert if the status of the animal is outside predefined parameters. The data manager can be configured to process data obtained by the animal tag, data generated by the animal tag, or a combination thereof. The data manager can be configured to display information about a status of an animal and to provide an alert if the status of the animal meets an alert condition.
In regards to claim 8, Geissler modified teaches the regular behaviors and the consecutively identified behaviors include one or more of: shaking, grooming, scratching, resting, sleeping, high-activity, medium activity, low-activity, barking, calories burned, walking, running, sitting, lying, jumping, chewing, sniffing, or licking (Paragraph 169) i.e. the tracking of the animal includes tracking behaviors such as chewing and licking, by way of eating and drinking.
In regards to claim 11, Geissler teaches a method for identifying irregularities in behaviors of a non-human animal (Paragraphs 40, 114, 168) such as domesticated animals, livestock, companion animals, wild animals and game animals). Geissler teaches the method comprising providing, by a processing circuitry, a behavioral baseline including first information on regular behaviors of the non-human animal over a given period of time when no irregularities occur(Paragraphs 119, 169) i.e. the activity log 250 records events occurring throughout each day. In an embodiment, the activity log 250 tracks which locations are visited and/or in which activities an animal engages over the predetermined period of time. In an embodiment, the activity log 250 tracks a length of time spent at each location and/or engaged in each activity over the predetermined period of time; the analyze operation 1106 determines whether any of the animals are displaying normal behavior. For example, in an embodiment, the analyze operation 1106 may determine which animals have eaten or drunk within a predetermined period of time. In another embodiment, the analyze operation 1106 may identify trends of normal behavior (e.g., consistent eating and/or drinking habits).
Thereafter, Geissler teaches obtaining, by the processing circuitry, data on a series of consecutively identified behaviors of the non-human animal identified over a second period of time; performing, by the processing circuitry, an action upon the data not complying with the behavioral baseline, thereby indicating an irregularity in the non-human animal behavior (Paragraphs 160, 178), i.e. An analyze operation 1106 reviews and processes the received tag update data. In an embodiment, the analyze operation 1106 determines whether any of the animals are displaying abnormal behavior. For example, in an embodiment, the analyze operation 1106 may determine whether any of the animals have not eaten or drunk within a predetermined period of time. In an embodiment, the analyze operation 1106 may determine whether any of the animals have eaten or drank too often within a predetermined period of time. In another embodiment, the analyze operation 1106 may identify trends of abnormal behavior (e.g., increase or decline in eating or drinking habits). In another embodiment, the analyze operation 1106 may determine whether any animals are missing (e.g., tag out of range) or whether any unexpected animals are present (e.g., unknown or unexpected tag in range). Given that the system analyzes the tracked behavior over a predetermined time, it can then determine any abnormal/irregular behavior in the same given predetermined time as the data does not comply with the behavioral baseline, thereby generating an action such as an alert condition.
Geissler fails to teach the consecutively identified behaviors are determined based on analysis of three-dimensional (3D) accelerometer data acquired by a 3D accelerometer comprised in a device attached to the non-human animal.
Mottram on the other hand teaches the consecutively identified behaviors are determined based on analysis of three-dimensional (3D) accelerometer data acquired by a 3D accelerometer comprised in a device attached to the non-human animal (Paragraph 51) i.e. the various sensor outputs indicating the behavioral status 301 of the animal is received by the computer system 119 via the antenna 117. This data is compared to a reference physiological data model of the sensory outputs and the behavioral status 301. The 3-D accelerometer 201 records the spatial orientation and movement of the animal's head. This data is analyzed by the farm computer 119 to indicate behavioral patterns such as time spent lying, standing, walking 401 and time spent feeding or drinking 403. It would have been obvious to a person of ordinary skill in the art before the effective filing of the invention to combine Mottram’s teaching with Geissler’s teaching in order to record and track the spatial orientation and movement of the animal, to which this data is indicative of behavioral patterns such as time spent lying, standing, walking etc.
Geissler modified fails to teach upon the data not complying with the behavioral baseline, thereby indicating an irregularity in the non-human animal behavior, provide one or more irregularity preventing recommendations to a caregiver of the non-human animal based on historical behavioral data associated with the non-human animal. Kuper on the other hand teaches provide one or more irregularity preventing recommendations to a caregiver of the non-human animal based on historical behavioral data associated with the non-human animal (Column 1, lines 53-Column 2, line 3; Column 4, line 65-Column 5, line 8; Column 7, line 62-Column 8, line 16 ), i.e. the present invention optimizes workflow by animal, by facility, by pen, and by producer, based upon historical performance, gender and genetic breed and the management practices of the producer. The artificial intelligence-based modeling applied in the adaptive framework 100 calibrates the predictive recommendation unique to each producer, pen, and animal, to analyze livestock performance by location, weather, veterinary medicine or biological product, over time, by intra-organizational comparison, or benchmarks by gender, breed or by feed ration mix.
The artificial intelligence layer 146 may perform an ensemble-based processing step using the bias-based convergence algorithm 148 to run multiple, concurrent models 150 to determine the output of the ideal model 160 to promote. This multi-model, bias-based, ensemble processing approach promotes the most appropriate or primary livestock growth model 160 and resultant recommendations 173 such as feed program by selecting the most appropriate outcome and operational plan. This convergence approach may assign different weights or biases to different variables 158 among the input data 110, and the artificial intelligence layer 146 may apply one or more techniques to “learn” and adjust weights or biases to be applied based on historical correlations between modeled outcomes and the different variables, and based on the difference between actual growth rate performance and predicted growth rate performance. Many types of recommendations 173 are contemplated, and may include for example recommendations 173 regarding a type of feed 180 to be provided to livestock (such as a type or variety of corn), recommendations as to type and quantity of additives 181 to feed (such as nutrients, antibiotics and veterinary medicines, biological additives, implants, and other animal health products, etc.), mixtures 182 of feed to be provided to livestock 104, and management practice and operational recommendations 183. Examples of management and operational practice recommendations 183 include feed timing 184, frequency of feed deliveries 185, stocking rates 186, labeling and regulatory compliance recommendations 187, facility-specific management practices 188, and veterinary prescriptions 192. Examples of facility-specific management practices 188 include cattle bedding rates, bunk space per head, and cattle movement and handling, such as moving livestock from one pen to another, or one location to another. Many other recommendations 173 are possible.
According to Kuper’s disclosure, the machine learning system takes into account an ideal model based on the specific non-human animal, based on historical study, thereby if the observed study is offset from the ideal model (which by obvious would include abnormal or irregular behavior or study deviated from the ideal model), recommendations would be generated to caregiver to gear the attributes of the given animal to return back to its ideal model, and thereby obvious to one of ordinary skill in the art preventing any further irregularity
It would have been obvious to a person of ordinary skill in the art before the effective filing of the invention to combine Kuper’s teaching with Geissler modified’s teaching in order to use identify trends within and/or between animal populations that are appropriate for the condition(s) being dealt with the animal(s) in focus.
Geissler modified fails to teach providing one or more irregularity preventing recommendations to a caregiver of the non-human animal based on historical behavioral data associated with the non-human animal, and irrespective of past behaviors of non-human animals other than the non-human animal. Davis on the other hand teaches a behavioral and monitoring system where an individual’s physiological conditions and behavior is monitored and recorded such that overtime irregular or abnormal conditions or behavior may be detected, so that suggestions/recommendations may be made from the live readings cross checked by historical readings (Paragraphs 307, 359, ),i.e.
Such a monitoring service may report to the user whenever the sensed data significantly deviates from expected norms. If a person's REM sleep pulse is normally between 56 and 60 beats per second, and one night there is an episode in which the pulse varies from this range by a threshold amount (e.g., more than 5%, 15%, 30%, or 75%), then a message may be dispatched to the user (e.g., by email, text, or otherwise) noting the incident. Possible causes for the disturbance may also be communicated to the user. These causation hypotheses can be pro forma--based on textbook understandings of the noted phenomenon (e.g., caffeine before bed) discerned from stored rule data, or they can be tailored to the user--such as taking into account other user- or ambient-sensor information that might be correlated (e.g., irregular respiration, suggesting sleep apnea or the like; or an unusually warm room--as indicated by temperature data logged by a smartphone sensor as contrasted with historical norms--leading to increased blood flow for convective body cooling). Such information is also logged in a historical data store, and may also be sent for e-charting to the user's physician. [P-307]
In some embodiments, the technology serves as an advisor to a medical professional--offering suggested diagnoses, or further testing, to consider. The offered advice may be tailored in accordance with wishes of the professional, e.g., expressed in stored profile data corresponding to that professional. For example, one practitioner may express a conservative medical philosophy, in which case such an advisory service may offer only observations/suggestions in which there is a high degree of confidence. Conversely, another practitioner may be more open to novel theories and approaches, in which case the system may also present candidate diagnoses (and further testing suggestions) that is more speculative. [P-359]
Furthermore, Davis goes on to elaborate that just as the system and method may be utilized on an human individual may also be applicable to individual livestock or non-human animal (Paragraphs 369, 370), i.e.
Many of the techniques described in connection with humans can also be applied to animals. Unusual skin conditions can be expanded to animal hide, fur and feathers (although false positives and hidden conditions may be more likely with complex skin coverings). Vets often face a more difficult challenge than physicians, since animals cannot describe symptoms that might aid in diagnosis, making the notion of providing a candidate list of maladies and being able to quickly test for additional symptoms even more valuable. Pet owners often need to decide whether symptoms warrant a visit to a vet and whether particular visible symptoms can be explained by recent known activities of that pet. Furthermore, livestock owners face the challenge of outbreaks of contagious diseases and need to inspect their animals often to catch such diseases as early as possible. Pet and livestock owners can benefit greatly from the present technology for examining and diagnosing conditions.[P-369]
For livestock owners, an automated early warning system can be set in place where livestock passing through gates or paddocks are routinely examined for unusual skin variations that suggest closer examination is needed. Livestock are often outfitted with RF tags for identification, allowing such a monitoring system to compare individual livestock over time to rule out health conditions that have already been addressed, and to note new, emerging conditions. Wildlife managers can also benefit by setting up imaging systems on commonly traversed paths that are triggered by passing animals. Again, early detection and identification of contagious conditions or dangerous pests is key to maintaining healthy populations.[P-370]
It would have been obvious to a person of ordinary skill in the art before the effective filing of the invention to combine Davis’ teaching with Geissler modified’s teaching in order to effectively examine in isolation and further effectively identify norms versus irregular behaviors of a specific animal and effectively determine accurate remedies for specific situations trends within and/or between animal populations that are appropriate for the condition(s) being dealt with the animal(s) in focus.
Geissler modified fails to teach the behavioral baseline is adapted to past changes in the non-human animal's behaviors over time, utilizing the historical behavioral data associated with the non-human animal. Carson on the other hand teaches the behavioral baseline is adapted to past changes in the non-human animal's behaviors over time, utilizing the historical behavioral data associated with the non-human animal (Abstract; Paragraphs 23, 32), i.e.
A computer-implemented method for using historical pet eating data to determine changes in pet eating behavior is disclosed. The method includes receiving a plurality of historical pet eating data records from a database, determining a subset of the plurality of historical pet eating data records, determining an expected distribution based on the subset of the plurality of historical pet eating data records wherein the expected distribution includes a baseline, an upper threshold, and a lower threshold, receiving current pet data from a pet sensor wherein the current pet data includes a total meal event value, analyzing whether the total meal event value exceeds the upper threshold or the lower threshold, and outputting a notification indicating a result that is responsive to the analyzing[Abstract]
As will be discussed in more detail below, in various embodiments, systems and methods are described for using historical pet eating data to determine changes in pet eating behavior. By collecting and analyzing historical pet eating data, the systems and methods may be able to calculate an expected distribution for future pet eating events, where the expected distribution may include a baseline, an upper threshold, and a lower threshold. The systems and methods may then receive current pet eating data and compare such pet eating data to the expected distribution. The systems and methods may then output a notification indicating a result of the comparison to notify the pet parent of any changes in the pet's eating data.[P-23]
The platform may also display a duration of a behavior, an average duration of the behavior, a previous duration of the behavior, and/or how the behavior compares to a previous time period, such as a previous day. For example, in the “Scratching” section, the platform may display an average duration of “235 seconds/day” with a behavior comparison of “−5 seconds from previous day.” In the “Licking” section, the platform may display an average duration of “28 minutes/day” with a behavior comparison of “−3 minutes from previous day.” In the “Sleeping” section, the platform may display “8.4 duration (hours)” with a behavior comparison of “+10 seconds from baseline.” A number of disruptions may also be displayed (e.g., “2 disruptions”) and/or how the disruptions compare to a disruption baseline (e.g., “−1 disruption from baseline”). In the “Eating” section, the platform may display a previous duration of the behavior of “13 minutes” with a behavior comparison of “+10 seconds from baseline.” In the “Drinking” section, the platform may display a previous duration of the behavior of “2 minutes” with a behavior comparison of “+10 seconds from baseline.” [P-32]
It would have been obvious during the time of the said invention to combine Carson teaching with Geissler modified teaching in order to enable more effective analysis of pet behavior in habitual events
In regards to claim 12, Geissler modified teaches the information on regular behaviors includes, for each regular behavior an indication of a type of behavior (Paragraph 169) i.e. For example, in an embodiment, the analyze operation 1106 may determine which animals have eaten or drunk within a predetermined period of time. In another embodiment, the analyze operation 1106 may identify trends of normal behavior (e.g., consistent eating and/or drinking habits).
Furthermore, Geissler teaches one or more of regular frequency range of the behavior, regular duration range for the behavior, regular intensity range for the behavior, regular score range of a score calculated for the behavior (Paragraphs 167, 169) i.e. the analyze operation 1106 may identify trends of normal behavior (e.g., consistent eating and/or drinking habits). In another embodiment, the analyze operation 1106 may determine which animals are in view (e.g., tag is within range), hence using the regular frequency range that the tracked animal trends to perform their normal behavior to further identify what animal is being tracked.
In regards to claim 13, Geissler modifies teaches the processing circuitry is further configured to analyze the data to determine a cause for the irregularity (Paragraphs 117, 121, 129, 166-168), i.e. the tag circuitry tracks the frequency of at which a given animal eats an drinks at a given predetermined period over a period of time, to which thereby when a regular consumption of food and water is determined, the moment there is an absence of a recorded regularity, then an irregular activity is detected.
In regards to claim 16, Geissler modified teaches the behavioral baseline is an animal specific behavioral baseline determined using baseline creation data including a baseline series of consecutively identified baseline behaviors of the non-human animal identified over a third period of time in which the non-human animal is assumed to behave regularly (Paragraphs 66) i.e. when the tag 120 approaches this area of interest, the beacon 110 prompts the tag 120 to log the tag's proximity status (e.g., the tag's proximity to the beacon 110 and hence the corresponding area of interest). In an embodiment, the tag 120 periodically increments a beacon counter if the tag 120 determines the tag 120 is located in proximity to the beacon 110. In an embodiment, the tag 120 logs its proximity status by recording a number of separate visits to the beacon 110 (i.e., a number of times the tag 120 has entered and exited a range of the beacon 110). In an embodiment, the tag 120 the tag 120 logs its proximity status by recording dates and times of each visit to the beacon 110. In an embodiment, the tag 120 the tag 120 logs its proximity status by recording the length of time of one or more visits to the beacon 110. For example, the tag 120 can record the duration of time of visits to the beacon 110 that occur between reports to reader 130.
In regards to claim 17, Geissler modified teaches the regular behaviors and the consecutively identified behaviors include one or more of: shaking, grooming, scratching, resting, sleeping, high-activity, medium activity, low-activity, barking, calories burned, walking, running, sitting, lying, jumping, chewing, sniffing, or licking (Paragraph 169) i.e. the tracking of the animal includes tracking behaviors such as chewing and licking, by way of eating and drinking.
In regards to claim 20, Geissler teaches a non-transitory computer readable storage medium having computer readable program code embodied (Paragraph 63, 171, 207). Therewith, the computer readable program code, executable by at least one processing circuitry of a computer to perform a method for identifying irregularities in behaviors of a non-human animal (Paragraphs 40, 114, 168) such as domesticated animals, livestock, companion animals, wild animals and game animals)
Geissler then teaches the system comprising a processing circuitry configured to provide a behavioral baseline including first information on regular behaviors of the non-human animal over a given period of time when no irregularities occur (Paragraphs 119, 169) i.e. the activity log 250 records events occurring throughout each day. In an embodiment, the activity log 250 tracks which locations are visited and/or in which activities an animal engages over the predetermined period of time. In an embodiment, the activity log 250 tracks a length of time spent at each location and/or engaged in each activity over the predetermined period of time; the analyze operation 1106 determines whether any of the animals are displaying normal behavior. For example, in an embodiment, the analyze operation 1106 may determine which animals have eaten or drunk within a predetermined period of time. In another embodiment, the analyze operation 1106 may identify trends of normal behavior (e.g., consistent eating and/or drinking habits).
Thereafter, Geissler teaches obtaining data on a series of consecutively identified behaviors of the non-human animal identified over a second period of time; perform an action upon the data not complying with the behavioral baseline, thereby indicating an irregularity in the non-human animal behavior (Paragraphs 160, 178), i.e. an analyze operation 1106 reviews and processes the received tag update data. In an embodiment, the analyze operation 1106 determines whether any of the animals are displaying abnormal behavior. For example, in an embodiment, the analyze operation 1106 may determine whether any of the animals have not eaten or drunk within a predetermined period of time. In an embodiment, the analyze operation 1106 may determine whether any of the animals have eaten or drank too often within a predetermined period of time. In another embodiment, the analyze operation 1106 may identify trends of abnormal behavior (e.g., increase or decline in eating or drinking habits). In another embodiment, the analyze operation 1106 may determine whether any animals are missing (e.g., tag out of range) or whether any unexpected animals are present (e.g., unknown or unexpected tag in range). Given that the system analyzes the tracked behavior over a predetermined time, it can then determine any abnormal/irregular behavior in the same given predetermined time as the data does not comply with the behavioral baseline, thereby generating an action such as an alert condition.
Geissler fails to teach the consecutively identified behaviors are determined based on analysis of three-dimensional (3D) accelerometer data acquired by a 3D accelerometer comprised in a device attached to the non-human animal.
Mottram on the other hand teaches the consecutively identified behaviors are determined based on analysis of three-dimensional (3D) accelerometer data acquired by a 3D accelerometer comprised in a device attached to the non-human animal (Paragraph 51) i.e. the various sensor outputs indicating the behavioral status 301 of the animal is received by the computer system 119 via the antenna 117. This data is compared to a reference physiological data model of the sensory outputs and the behavioral status 301. The 3-D accelerometer 201 records the spatial orientation and movement of the animal's head. This data is analyzed by the farm computer 119 to indicate behavioral patterns such as time spent lying, standing, walking 401 and time spent feeding or drinking 403. It would have been obvious to a person of ordinary skill in the art before the effective filing of the invention to combine Mottram’s teaching with Geissler’s teaching in order to record and track the spatial orientation and movement of the animal, to which this data is indicative of behavioral patterns such as time spent lying, standing, walking etc.
Geissler modified fails to teach upon the data not complying with the behavioral baseline, thereby indicating an irregularity in the non-human animal behavior, provide one or more irregularity preventing recommendations to a caregiver of the non-human animal based on historical behavioral data associated with the non-human animal. Kuper on the other hand teaches provide one or more irregularity preventing recommendations to a caregiver of the non-human animal based on historical behavioral data associated with the non-human animal (Column 1, lines 53-Column 2, line 3; Column 4, line 65-Column 5, line 8; Column 7, line 62-Column 8, line 16 ), i.e. the present invention optimizes workflow by animal, by facility, by pen, and by producer, based upon historical performance, gender and genetic breed and the management practices of the producer. The artificial intelligence-based modeling applied in the adaptive framework 100 calibrates the predictive recommendation unique to each producer, pen, and animal, to analyze livestock performance by location, weather, veterinary medicine or biological product, over time, by intra-organizational comparison, or benchmarks by gender, breed or by feed ration mix.
The artificial intelligence layer 146 may perform an ensemble-based processing step using the bias-based convergence algorithm 148 to run multiple, concurrent models 150 to determine the output of the ideal model 160 to promote. This multi-model, bias-based, ensemble processing approach promotes the most appropriate or primary livestock growth model 160 and resultant recommendations 173 such as feed program by selecting the most appropriate outcome and operational plan. This convergence approach may assign different weights or biases to different variables 158 among the input data 110, and the artificial intelligence layer 146 may apply one or more techniques to “learn” and adjust weights or biases to be applied based on historical correlations between modeled outcomes and the different variables, and based on the difference between actual growth rate performance and predicted growth r