US20200042933A1 - Determining item mortality based on tracked environmental conditions during transit - Google Patents

Abstract

Item mortality, such as failure rates and expected remaining lifespan, may be determined based on tracked environmental conditions during transit, such as vibration, temperature, and other conditions. For complex items, multiple different internal components may have varying degrees of susceptibility to damage from unfavorable conditions, with each of the components able to individually cause a failure of the entire item. Thus, the specific set of internal components may drive item mortality prediction. Sensors may be located in shipping containers that share data collected throughout the supply chain, using a blockchain, to increase confidence in the integrity of the data. The use of mortality models generated with anonymized component or process data may enable manufacturers to protect trade secrets, such as the specific components or manufacturing processes used, even while leveraging the manufacturer's detailed knowledge of an item.

Description

BACKGROUND
• Environmental conditions during transit can negatively impact the condition and expected remaining lifespan of some items when presented to users or consumers. Conditions experienced during transit, such as subjection to vibration, shock, heat, humidity, corrosive conditions, may either be unknown or misrepresented. The uncertainty regarding possible exposure to damaging conditions leads to less predictability in item lifespan and reliability, and thus can negatively impact both consumer confidence and retailers' confidence in suppliers and transporters.
SUMMARY
• Systems and methods are disclosed for determining item mortality based on tracked environmental conditions during transit of goods, such as vibration, temperature, humidity, shock, corrosive conditions, and other conditions that may cause degradation. For complex items, multiple different internal components may have varying degrees of susceptibility to damage from unfavorable conditions, with each of the components able to individually cause a failure of the entire item. Thus, the specific set of internal components may drive item mortality prediction, such as predicted failure rates and remaining lifespan. Sensors may be located in shipping containers that share data collected throughout the supply chain, using a blockchain, to increase confidence in the integrity of the data. The use of mortality models generated with anonymized component or process data may enable manufacturers to protect trade secrets, even while leveraging the manufacturer's knowledge of the specific components or processes used in complex items to enhance precision of the mortality models.
• Some embodiments of a system for determining item mortality based on tracked environmental conditions during transit implemented on at least one processor may comprise a processor; and a computer-readable medium storing instructions that are operative when executed by the processor to: receive sensor data for environmental conditions experienced by an item during transit; based at least on the received sensor data, determine mortality data for a first component of the item; based at least on the received sensor data, determine mortality data for a second component of the item, different from the first component; based at least on mortality data for the first component and mortality data for the second component, determine mortality data for the item; and based at least on the mortality data for the item and disposition rules, generate a disposition recommendation for the item. The disposition recommendation may be for a retail outlet, regarding whether to accept the goods into inventory or for a consumer, regarding whether to accept delivery of an item.
BRIEF DESCRIPTION OF THE DRAWINGS
• The disclosed examples are described in detail below with reference to the accompanying drawing figures listed below:
• FIG. 1 provides a comparison of sensor reading events and remaining lifespan values;
• FIG. 2 illustrates a notional link among sensor measurements (or other data), environmental conditions experienced during transit, and item mortality;
• FIG. 3 illustrates a transit arrangement including sensors to track environmental conditions during transit;
• FIG. 4 illustrates two functionally similar items having differing susceptibility to adverse environmental conditions due to differing internal components;
• FIG. 5 illustrates a data distribution arrangement that uses a blockchain to increase confidence in sensor measurement data;
• FIG. 6 illustrates an item mortality prediction scheme that can advantageously use data obtained from the arrangement ofFIG. 5;
• FIGS. 7-8 show flow charts illustrating exemplary operations involved in determining item mortality based on tracked environmental conditions during transit; and
• FIG. 9 is a block diagram of an example computing device for implementing aspects disclosed herein.
• Corresponding reference characters indicate corresponding parts throughout the drawings.
DETAILED DESCRIPTION
• A more detailed understanding may be obtained from the following description, presented by way of example, in conjunction with the accompanying drawings. The entities, connections, arrangements, and the like that are depicted in, and in connection with the various figures, are presented by way of example and not by way of limitation. As such, any and all statements or other indications as to what a particular figure depicts, what a particular element or entity in a particular figure is or has, and any and all similar statements, that may in isolation and out of context be read as absolute and therefore limiting, may only properly be read as being constructively preceded by a clause such as “In at least some embodiments, . . . ” For brevity and clarity of presentation, this implied leading clause is not repeated ad nauseum.
• Environmental conditions during transit can negatively impact the condition and expected remaining lifespan of some items when presented to users or consumers at a retail establishment. Conditions experienced during transit, such as subjection to vibration, shock, heat, humidity, corrosive conditions, may either be unknown or misrepresented. The uncertainty regarding possible exposure to damaging conditions leads to less predictability in item lifespan and reliability, and thus can negatively impact both consumer confidence and retailers' confidence in suppliers and transporters. For example, excessive heat, vibration, and conditions leading to corrosion or oxidation can cause premature failures in certain electronic devices, without the damage being noticeable from a visual inspection at the time of delivery or purchase. If a consumer purchases an item that has latent damage incurred during transit, the retailer may lose money and additionally suffer reputation damage.
• It may therefore be advantageous for retailers (and others in the supply chain), to ascertain whether an incoming shipment of goods has been subjected to unfavorable environmental conditions during transit, so the retailer can reject the shipment, or demand a reduced price that reflects the lower value of the damaged goods. Some of the advantages may be more pronounced for longer journeys, covering greater distances, while passing through the possession of multiple different carriers—for example, international transit of expensive electronic goods.
• Referring to the figures, examples of the disclosure enable determining item mortality based on tracked environmental conditions during transit of goods, such as vibration, temperature, humidity, shock, corrosive conditions, and other conditions that may damage the goods. For complex items, multiple different internal components may have varying degrees of susceptibility to damage from unfavorable conditions, with each of the components able to individually cause a failure of the entire item. Thus, the specific set of internal components may drive item mortality prediction, such as predicted failure rates and remaining lifespan, that uses sensor measurement and other data. Sensors may be located on or in shipping containers that share data collected from throughout the supply chain, using a blockchain, in order to increase confidence in the integrity of the data.
• In some embodiments, containers, pallets, and transportation vehicles may be supplied with sensor devices that can send information, that eventually reaches and analysis node that can determine the condition of the items. Sensors in each container can monitor the exposure of the items within the container to various conditions, as the container is transported from a manufacturer's location to a destination. Similarly, sensors in the different transport vehicles may monitor the exposure of containers to various conditions, as the container is transported by that particular vehicle. Thus, if multiple transport carriers handled an item that was damaged, the incident causing the damage may be isolated to the responsible carrier.
• Sensor measurement data may be continually streamed, sent on a periodic interval or perhaps certain conditions may trigger a data recording or transmission event, such as some sensor measurement exceeding a threshold or being outside recommended values. Sensor measurement data and other data, such as location and time information, may be recorded in a blockchain, for distribution and to increase confidence in the data's integrity. The measurement and other data may then be used with a mortality model to generate a mortality prediction, including expected lifespan and failure rates. The mortality model may use input from the manufacturer, based on internal components and manufacturing processes. For some embodiments, rules applied to a mortality prediction may determine acceptance criteria and recommended disposition.
• The ability to confidently identify transit conditions, and their potential impact on individual components of a complex item, can enable identifying when an item may have endured latent damage. This additional insight into item history can improve confidence in items that have not been subjected to unfavorable transit or storage conditions. Items known to have been subjected to adverse environmental conditions may be rejected by a retailer, or marked in a manner to alert customers to potential performance and reliability issues and priced accordingly. The retailer may then experience a lower return rate for defective products. Additionally, the use of mortality models generated with anonymized component or process data may enable manufacturers to protect trade secrets, even while leveraging the manufacturer's knowledge of the specific components or processes used in complex items to enhance precision of the mortality models.
• FIG. 1 provides a comparison of sensor reading events and remaining lifespan values. Ingraph100,measurement data102 is plotted for a first sensor (Sensor #1), with the sensor measurement magnitude given as a function of time. Similarly,measurement data104 is plotted for a second sensor (Sensor #2), also with the sensor measurement magnitude given as a function of time. Athreshold106 is also illustrated.Plot100 is notional, without units specified. For example,measurement data102 may be temperature, scaled ingraph100 so thatthreshold106 represents a first threshold (a temperature threshold), above which damage may be expected. Andmeasurement data104 may be shock (g-force), scaled ingraph100 so thatthreshold106 represents a second threshold (a shock threshold), above which damage may be expected.Measurement data102 andmeasurement data104 stop at adelivery event110. However, illustrated withingraph100 are three events that have occurred during transit: afirst temperature spike112, a shock (high g-force)event114, and asecond temperature spike116. In some situations, damage may not be a binary determination, but may be probabilistic, such as altering a failure rate from a first percentage to a second, higher percentage.
• Ingraph120, a predictedlifespan122 for an undamaged item is plotted with the expected remaining life given as a function of time. A predictedlifespan124 for a damaged item is also plotted with the expected remaining life given as a function of time. These are notional plots, and should not be interpreted as being representative of any particular item. As illustrated ingraph120, the expected remaining life of the damaged item terminates while an undamaged item still has some expected remaining life.
• Graph120 is aligned withgraph100, so thatevents112,114, and116 coincide. As can be seen ingraph120, predictedlifespan124 experiences rapid decreases coinciding withfirst temperature spike112,shock event114, andsecond temperature spike116. The result is that, at the time of delivery (delivery event110), the damaged item has a shortened expected remaininglife126. The difference128 (lost lifespan) may be ascertained atdelivery event110, and used to determine a disposition of the item, such as acceptance, acceptance as a discounted price, diversion to a secondary market, or refusal of delivery. Although predictedlifespan124 is illustrated as having reductions atdiscrete events112,114, and116, some items may be able to tolerate short or infrequent adverse incidents, with damage caused by prolonged or repeated exposure.
• FIG. 2 illustrates anotional triad200 linking sensor measurements (or other data), environmental conditions experienced during transit, and item mortality. The environment experienced during transit and storage and impact item mortality, such as by degrading the item or item components. The environment experienced during transit can also be measured by sensors, to produce a data log. The data log, containing data from sensors and other data sources, can be used to predict item mortality. Thus, the sensor measurements (or other data), environmental conditions experienced during transit, and item mortality may be linked.
• FIG. 3 illustrates atransit arrangement300 including sensors to track environmental conditions during transit. Transit arrangement may represent any type of transit, including postal service delivery to a consumer (such as the USPS), railroad carriage, truck trailers, air cargo, and trans-oceanic cargo ships. Atransport container302 has a sensor set304a, which may be located inside ofcontainer302, outside ofcontainer302, or a combination. Sensor set304ais shown in detail, as containingsensors306a,306b, and306c. Although sensors306a-306care illustrated as being located together, it should be understood that any feasible physical arrangement may be used. Additionally, it should be understood that, although three sensors are illustrated, any number of sensors may be used. Sensors306a-306cmay include any of temperature, humidity, air pressure, condensation and moisture pooling, salinity (or other corrosive conditions), CO₂levels (and other gasses), time, shock and vibration, location (including altitude and latitude/longitude), and other sensors, including duplicates of any sensor type. Some sensors may measure conditions indicative of damage, whereas other sensors, for example location, may indicate country-of-origin and transit routes. In some scenarios, location data may be useful for customs inspectors. Other data sources may include the identity of shipping entities, planned routes, dates, weather, and other information.
• Shown withintransport container302 areother containers310aand310b, each also having asensor set304band304c, respectively. Sensor sets304band304cmay have a similar or different set of individual sensors as sensor set304a. Shown withincontainer310aare twoitem containers320aand320b, each also having asensor set304dand304e, respectively. Sensor sets304dand304emay have a similar or different set of individual sensors as sensor set304a.Container310bmay also hold similar item containers.Containers302,310a,310b,320a, and320bmay variously represent any of a tote, a rail car, a truck trailer, a shipping container, a drone bay, an automatic guided vehicle (AGV) hold, or another container used in the transport of goods. In the illustrated arrangement,containers320a,320b,310a, and310bhaveidentification barcodes312a,312b,312c, and312d, respectively, although it should be understood that another type of tracking, such as 2D barcodes, radio frequency identification (RFID) tags, near-field communication (NFC), or another identification scheme may be used.
• This nested arrangement of containers having sensor sets, within another container having a sensor set may be repeated for a number of levels. The sensor sets may be configured and positioned to sense conditions experienced by a particular portion of an item or container, perhaps to correspond with a particular susceptible component, such a moisture sensor set at a height to trigger an alarm only if moisture has pooled to a sufficient depth to cause damage but not trigger an alarm for lesser pooling.
• Also, as illustrated inFIG. 3,container310ahas alock unit322a, which includes akeypad324, alogic module326, apower source328, and awireless communication module330.Keypad324 may operate an electronic door lock, and record all access (unlocking and/or opening) events and attempts, possibly in conjunction with a door position sensor (not shown).Logic module326 is in communication with sensor set304band has processing logic and storage for data, such as the access events and data from sensor set304b. If logic module326ais also in communication with sensor sets304dand304e, it can record data from those sensor sets, also.Power source328 may include a battery and/or a solar cell, and possibly include a wireless charging capability.Power source328 provides power forkeypad324,logic module326, andwireless communication module330.Wireless communication module330 may be Wi-Fi or Bluetooth™, and permits data stored inlogic module326 to be sent to external storage and monitoring locations. Similarly,container310bhas alock unit322bthat may be equivalent to lock322a, or have different capabilities.
• Lock units322aand322bmay be blockchain-enabled, including a tamper-evident blockchain-registered component that renders unauthorized access or modification detectable.Lock units322aand322bmay further generate a new blockchain entry at certain events, stored locally, and communicated to acontroller unit340 ontransport container302, perhaps wirelessly.Controller unit340 includes alogic module342, analarm344, apower source346, acargo sensor348, and awireless communication module330.).Logic module326 is in communication with sensor set304band has processing logic and storage for data, such as the access events and data from sensor set304aand data received fromlock units322aand322b. Logic module326ais also in communication withalarm344 andcargo sensor348, in order to create alerts when cargo is missing or iflock units322aor322bare tampered with.Power source328 may include a battery and/or a solar cell, and possibly include a wireless charging capability.Power source328 provides power for the components ofcontroller unit340.Alarm344 may generate an audible alarm to alert humans and/or an alarm signal for detection by a monitoring station.
• Cargo sensor348 may be a camera, a barcode reader (to read any of barcodes312a-312dthat are visible), an NFC reader, an RFID transponder, or any other type of sensor that can detect whethercontainers310aand310bhave been loaded, removed, or are present. In this manner,controller unit340 can record products entering or leaving the blockchain enabled container.Wireless communication module350 may be Wi-Fi or Bluetooth™, or even cellular, and permits data stored inlogic module326 to be sent to external storage and monitoring locations or received from external sources. Althoughlock units322aand322bare illustrated oncontainers310aand310b, respectively, and in communication withcontroller unit340 ontransport container302, it should be understood that a communication relationship may exist among any of the different tiers in a nested arrangement, and may even skip a tier. For example, a lock unit, similar to lockunit322a, may be placed oncontainer320afor communication either withlock unit322a(with the information relayed to controller unit340), or skippinglock unit322aand communicating directly withcontroller unit340. In some embodiments,controller unit340 may intake prior-generated data relating tocontainers310aand310bwhen they are loaded, for example, perhaps wirelessly from a smart fork lift that is loadingcontainers310aand310bintotransport container302.Controller unit340 may also generate data for registration in a blockchain everytime container302 is opened, or any containers are added or removed. Any or all of this data may then be stored inlogic module342 and transferred to the next recipient.
• Stored withinlogic module326 are adata log352, which holds the data described above for upload to a blockchain, acargo manifest354 listing cargo that should be on-board transport container302, and alist356 of containers (for example,310aand310b, possibly down to the level of detail ofcontainers320aand320b) that are actually on-board. In the event of a discrepancy betweencargo manifest354 andlist356,logic module342 will causealarm344 to generate an alert that the loaded items are either missing a container or have a container that should not be present. The containers may be identified by scanning as they are loaded and removed, or in place, with RFID tags that can ascertain which containers are within proximity of an RFID transponder. As data is generated regarding which containers are loaded or removed, when doors are opened to grant access, and perhaps the geographical coordinates which loading or loading occurs, it may be combined with sensor measurements and other data to produce blockchain records. The blockchain record data is transmitted to aremote data store360 overcommunication link362, which may be wireless, and which may usewireless communication module350 or some other communication connectivity.
• FIG. 4 illustrates two functionallysimilar items402aand402b, having differing susceptibility to adverse environmental conditions due to differing internal components. For example,item402aincludes an incandescentlight bulb404, aspeaker406, and alogic module408 that included integrated circuits, whereasitem402bincludes a light emitting diode (LED)410, aspeaker406, and alogic module408. Typically, incandescent lightbulbs are more prone to failure from vibration and shock, due to the fragility of the filament. Thus, ifitems402aand402bare both subject to the same shock and vibration forces that are sufficient to damageincandescent bulb404, but not damage LED410,item402amay be inoperable whileitem402bmay be fully operable.
• Long exposure to high humidity can cause the paper in some audio speaker cones to saturate and weaken, whereas speaker cones made from other materials may be less susceptible to humidity. Thus,items402aand402bhave susceptibilities that affect mortality due to the specific components. It may be that the manufacturer ofitems402aand402bsells them as the same model device, but has switched from using incandescent bulbs to using LEDs for certain illumination needs. The consumers may not notice the difference betweenitems402aand402b, saving the manufacturer the expense of changing packaging and preserving the investment in advertising the earlier-design product. However, the manufacturer may wish to keep its component list confidential, and thus does not wish to disclose the change from incandescent bulbs to LEDs or the use of inexpensive paper in the speakers.
• Therefore, the manufacturer may effectively anonymize the component data, and merely report the environmental conditions to avoid, such as by specifying thresholds at which damage is expected to occur. Thus, for example,threshold106 ingraph100 ofFIG. 1 may be set for temperature (based on tolerances of logic module408), or humidity (based on speaker406), or shack or vibration forces (based onincandescent bulb404 or LED410). The manufacturer may disclose these problem thresholds, based on the different internal components, without actually specifying which components drove the thresholds or what the components are, specifically. This then permits others, later in the supply chain, up through the consumer, to identify thatitem402ais more likely to become degraded from shock and vibration than isitem402b, but without necessarily knowing why. Alternatively, the manufacturer may anonymize the components, identifying that two internal components in each ofitems402aand402bhave the same part numbers, while one component is different. If the manufacturer provides information tying the different part numbers to the different damage or degradation thresholds, the others can identify that a different internal component is being used, but may not be able to easily ascertain that the components are.
• In a scenario such as this, in which an item with multiple components that each have their own unique degradation in response to adverse environmental conditions and unique effects on life expectancy, a tiered mortality analysis may be used: predicting mortality for each component, and then flowing the results upward into the overall or composite item mortality.
• FIG. 5 illustrates adata distribution arrangement500 that uses ablockchain502 to increase confidence in sensor measurement data.Blockchain502 is distributed among a plurality of interconnected nodes, includingdata store360 andnodes504aand504b. A full copy ofblockchain502 is available from any ofdata store360 andnodes504aand504b, within the constraints of network latency.
• Inarrangement500,transport container302, ontransport vehicle506 transmits blockchain record data todata store360 overcommunication link362, as described above forFIG. 3. Once entered into the blockchain, network connectivity amongdata store360 andnodes504aand504b. As illustrated, a terminal508 polls blockchain502 to retrieve sensor data. This data may be used by aretailer510 that will be selling the goods to consumers; asubsequent shipper512 that is planning to take delivery and move the goods closer toretailer510; a customs agent orimporter514; aninsurer516 that is insuring the goods in transit or will be insuring warranty claims; themanufacturer518; or anyone else with an interest in learning the condition of the goods in transit. In addition toretailer510 determining disposition regarding inventory delivered to the retailer's facility, a consumer may use the disclosure herein to determine whether to accept delivery of items delivered to aconsumer residence520.
• Retailer510 may be interested in ascertaining whether the goods will be in salable condition, andshipper512 may be interesting in ascertaining whether the goods had already been damaged, prior toshipper512 taking possession. A smart contract may be in place betweenshipper512, and the shipper who currently has possession, and sensor measurements indicating damage may be trigger an action or obligation under the smart contract. A smart contract may also exist that includes any ofinsurer516,retailer510,manufacturer518, or another party, and involves obligations or actions that trigger upon damaging conditions being sensed. Container manifests, possibly including tariff codes, may be required for tariff systems at ports of entry, and by placing product and environmental exposure data in a blockchain, the product and its supply chain can be verified by customs agent orimporter514. Data may be provided in an advance shipping notification and an electronic bill of lading, and copied into theblockchain502.
• Blockchain502 permits verification of information associated with items; some data may not be shareable with everyone in the supply chain.Blockchain502 can provide a level of confidence that the items being received are the correct items, and that improper access has not been granted to anyone during transit. Each transaction from the manufacturer, to the shipper, to the freight forwarder, to the shipping line, to the longshoremen, to the trucking company, and eventually to the distribution center can be tracked.Blockchain502 can record transaction data, including location and other sensor measurements, at each turnover event for a container. In some scenarios, video data covering the loading of a secure container by the source and unloading of the container at the destination, may be placed intoblockchain502.
• FIG. 6 illustrates an itemmortality prediction scheme600 that can advantageously use data obtained fromarrangement500 ofFIG. 5 to determine item mortality based on tracked environmental conditions during transit. In the illustrated embodiment,historical sensor data602 is collected and paired with historical mortality data604 (including failure rates ad descriptions, repair rates and descriptions, warranty claims, etc.) to create a neural net training data set, and then provided to a mortalitymodel training module608. Mortalitymodel training module608 generates amortality model610 using a neural net trained withhistorical sensor data602 andhistorical mortality data604. This enables generatingmortality model610 based on real-world failure and lifespan data; alternatively,mortality model610 may be trained at least partially on human-specified or synthetically-generated data. Mortalitymodel training module608 may generatemortality model610 as a tiered mortality model, using data for a first component of the item and data for a second component of the item. That is a tiered mortality model may predict failure rates and expected remaining lifespan of individual components, so that, based on those predictions, the failure rate and expected remaining lifespan of the entire item may be predicted.
• Information about the components within an item may often be learned from the manufacturer of the item or the manufacturer of a particular component. Suppliers may be required to provide mortality model data and component limitations, such as relationship between environmental conditions and mortality, when bringing in a new product or on-boarding, in addition to disclosing the presence or use of hazardous material. For example, the manufacturer may identify the components that are relevant for determining mortality data, and the environmental conditions that cause degradation. In some situations, however, the manufacturer may be reluctant to identify specific components in complex items, or manufacturing processes used, as these may constitute trade secrets. For example, the manufacturer may have found a new lamination process that saves money by cutting down on defects. However, the manufacturer does not wish to disclose details of the process, and so merely identifies the affected component with an anonymized identifier, along with humidity conditions that cause delamination. The use of mortality models generated with anonymized component or process data may enable manufacturers to protect trade secrets, even while leveraging the manufacturer's knowledge of the specific components or processes used in complex items to enhance precision of the mortality models.
• In some scenarios, the manufacturer may be located remotely from there themortality model610 is being created or improved, and so sends the relevant information, the manufacturer knowledge ofitem606, to mortalitymodel training module608 securely, perhaps encrypted. Manufacturer knowledge ofitem606 will contain data for the first component of the item and data for the second component of the item (as well as other relevant components), to use in the generation ofmortality model610. Manufacturer knowledge ofitem606 may also comprise an earlier version of a mortality model. In some embodiments, though,mortality model610 may be constructed and improved without using manufacturer knowledge ofitem606.
• Mortality prediction module614 receives sensor data for environmental conditions experienced by an item during transit from transitsensor data module612. Transitsensor data module612 may also have other data, that is also sent tomortality prediction module614, to use for generating morality data for the item. Transitsensor data module612 may receive sensor data, such as sensor measurement date, and perhaps even sensor failure data, fromblockchain502. As described above forFIG. 3, the sensor data comprises measurements from at least one sensor, perhaps two or more, selected from the list consisting of: temperature, humidity, air pressure, condensation, salinity, CO2 level, time, shock, and vibration.
• Based at least on the received sensor data,mortality prediction module614 determines mortality data for the first component of the item. Based at least on the received sensor data,mortality prediction module614 also determines mortality data for the second component of the item, which is a different component than the first component.Mortality prediction module614 then combines these, so that based at least on mortality data for the first component and mortality data for the second component,mortality prediction module614 determines mortality data for the item. To accomplish this,mortality prediction module614 may comparing the received sensor data against a damage threshold to generate the mortality data. This mortality data may include predictions regarding failure rate and/or expected remaining lifespan. In some situations, damage may not be a binary determination, but may be probabilistic, such as altering a failure rate from a first percentage to a second, higher percentage. Thus, mortality data may also be probabilistic.
• Mortality prediction module614 may compare the received sensor data against more than just one threshold, and may compare against a plurality of thresholds. The thresholds may be specific to different internal components, so that the failure of a specific component can be predicted, leading to a prediction of a failure of the entire item. In some embodiments, rather than merely using a single threshold for damage determination, the duration of exposure to certain conditions, or frequency of repeated exposures may be determined. For example, a component may be able to endure a single shock event of a given g-force, but receiving multiple shock events at the same g-force level may cause damage. Similarly for humidity, a component may be able to survive short-term exposure to humidity above some level (for example, perhaps less than an hour), but long-term exposure (for example, perhaps days), may cause adverse effects, such as de-lamination, warping, or weakening. In conjunction with comparing the received sensor data against a damage threshold or thresholds, or alternatively,mortality prediction module614 use with the received sensor data inmortality model610 to generate the mortality data for the item.
• Based at least on the mortality data for the item and disposition rules, adisposition determination module616 generates a disposition recommendation for the item. The disposition rules may specify exposure conditions or mortality data that leads to acceptance, acceptance, but at a reduced price, deferral to a secondary inventory market, or rejection. Items that are degraded and are to be sold on an “as-is” basis for a reduced price may be accepted from the supplier or transporter at a reduced price. Deferral to a secondary market may include sending to an outlet facility where consumers may be expecting items to contain flaws, such as perhaps an affiliate of the retailer or an independent entity. Another secondary market option may be a refurbishing center that will carefully inspect the item and make necessary repairs. Additionally, aninsurer622 may have input to the disposition rules indisposition determination module616, learn of the disposition from disposition determination module616 (possibly through a claim automatically generated by disposition determination module616), and/or receive a secure copy of mortality data frommortality prediction module614.
• Sensor data from transitsensor data module612 may also be sent to an ongoingtraining data module620 that may be used to further train the neural net trained with the received sensor data. Ongoingtraining data module620 receives data from transitsensor data module612 and alsocurrent mortality data618, possibly including warranty claim and other repair and failure data. This data may be combined into training data sets and sent to mortalitymodel training module608 for use in training the next version ofmortality model610.
• Ongoingtraining data module620 may also send data from transitsensor data module612 andcurrent mortality data618 to the manufacturer, to include in the next version of manufacturer knowledge ofitem606 and/or to be used to improve the item or components of the item to reduce susceptibility to damage. Ongoingtraining data module620 may send this information securely, such as encrypted, when the manufacturer is located remotely. Optionally, the manufacturer may securely obtain a copy of thecurrent mortality model610, if another entity is requesting to use it for generating an independent mortality model.
• FIG. 7 shows aflow chart700 illustrating exemplary operations involved in determining item mortality based on tracked environmental conditions during transit. More specifically,flow chart700 illustrates an exemplary operation of determining item mortality based on tracked environmental conditions during transit.Flow chart700 may be used by retailers, consumers, insurers, shippers, and other entities. The operations illustrated inflow chart700 may be performed by any processing unit or computing node, such as the computing device ofFIG. 9.Operation702 includes receiving sensor data for environmental conditions experienced by an item during transit.Operation704 includes, based at least on the received sensor data, determining mortality data for a first component of the item.Operation706 includes, based at least on the received sensor data, determining mortality data for a second component of the item, different from the first component.Operation708 includes, based at least on mortality data for the first component and mortality data for the second component, determining mortality data for the item.Operation710 includes, based at least on the mortality data for the item and disposition rules, generating a disposition recommendation for the item. For a retailer, generating a disposition recommendation may involve generating a recommendation regarding inventory delivered to the retailer's facility, whereas for a consumer, generating a disposition recommendation may involve generating a recommendation regarding acceptance of items delivered to an end consumer. In addition to retailers and consumers, generating a disposition recommendation may involve generating a recommendation that is tailored to the specific needs of a subsequent shipper, a customs agent, an importer, in insurer, a manufacturer, or another entity with a need to learn the condition of the goods in transit.
• FIG. 8 shows anotherflow chart800 illustrating exemplary operations involved in determining item mortality based on tracked environmental conditions during transit. The operations illustrated inflow chart800 may be performed by any processing unit or computing node, such as the computing device ofFIG. 9. Indecision operation802, a neural net or simpler threshold comparison is chosen. It a simpler threshold is to be used, thenoperation804 identifies thresholds of sensor measurements that are associated with damage or degradation. This may include both simple threshold comparisons, which determine whether damage thresholds have been exceeded, and more complicated analysis that take into account exposure times and the number of occurrences. If, however, a neural net or artificial intelligence (AI) is to be used, thenoperation806 will collect training data. Training data may include historical sensor data, historical mortality data, manufacturer information, and prior mortality models.Operation808 will then train the neural net.
• Operation810 will generate mortality models, perhaps including a tiered mortality model that has sub-models for individual components included within a larger item. Inoperation810, this may include generating the mortality model using a neural net trained with historical sensor data and historical mortality data. In some embodiments, for items having a first component and second component included within the item, generating the mortality model further comprises generating the mortality model using data for the first component and data for the second component.
• As the item is in transit or storage, or preparing for transit or storage,operation812 involves receiving sensor data for environmental conditions experienced by the item during transit, and possibly, also environmental conditions experienced by the item during storage. Receiving sensor data comprises receiving sensor data from a blockchain, as described above inFIG. 5. The sensor data comprises measurements from at least one sensor selected from the list consisting of temperature, humidity, air pressure, condensation, salinity, CO2 level, time, shock, and vibration. In some embodiments, the sensor data comprises measurements from at least two sensors selected from the list consisting of temperature, humidity, air pressure, condensation, salinity, CO2 level, time, shock, and vibration. Other sensors may be used, including moisture pooling, corrosive conditions, other gasses, time, and location (including altitude and latitude/longitude), including duplicates of any sensor type.
• Operation814 includes, based at least on the received sensor data, determining mortality data for a first component of the item, andoperation816 includes, based at least on the received sensor data, determining mortality data for a second component of the item, different from the first component. For example, the first component may be an incandescent light bulb that is susceptible to damage from shock or vibration, and the second item may be a laminated portion of a housing that is susceptible to damage from high humidity levels. In some embodiments, determining mortality data for a component of the item comprises comparing the received sensor data against a damage threshold to generate the mortality data. In some embodiments, determining mortality data for a component of the item comprises using the received sensor data in a mortality model to generate the mortality data. Some embodiments, however, may use a combination of threshold exposure analysis and a mortality model derived from a neural net.
• Operation818 involves, based at least on mortality data for the first component and mortality data for the second component, determining mortality data for the item. That is, the mortality model may be tiered, such that the mortality of the larger item is determined by the mortality data for the individual components. For example, perhaps the first component has not entirely failed, but has degraded, and similarly the second component has not entirely failed, but has also degraded. The combination of the degradation of the first component with the degradation of the second component, however, may result in a determination of a failure of the item. As a further example, the mortality data may be probabilistic, such that it is determined that the first component has a 50% chance of failure. If only the first component had this likelihood of failure, and no other components had been damaged, then the entire item would then have a 50% chance of failure. However, perhaps the second component also has a 50% chance of failure, based on a different environmental condition exposure. If the chances of failure are statically independent, and failure of either the first component or the second component can cause failure of the entire item, then the item has a 75% chance of failure and only a 25% chance of operating properly. With such a composite tiered mortality model, the individual chances of failure for different components may be combined to ascertain the total chance of failure. Thus, a chance of failure (for one component) that may not be enough to cause a rejection of an item may combine with other chances of failure for other components to trigger a rejection of the item.
• Operation820 includes, based at least on the mortality data for the item and disposition rules, generating a disposition recommendation for the item. Some embodiments may be used by consumers, rather than retailers; some may be used by shippers (taking in from other shippers); some embodiments may be used by insurers; some embodiments may be used by customs agents or importers; some embodiments may be used by manufacturers; and some embodiments may be used by insurers any other suitable entity. Thus, generating a disposition recommendation may include generating a disposition recommendation that is tailored to the specific type of user. Consumers, for example, may not have the ability to defer incoming goods to secondary markets, but may be presented with a fewer set of options: accept or reject. As indicated above, the disposition for an item may not be merely determined based on a single component's mortality data (although if the single component has failed, then that may be determinative), but instead, the disposition recommendation may be determined by a more complex combination of the mortality data of the individual components. Disposition options for the item may include acceptance, acceptance as a discounted price, diversion to a secondary market, or refusal of delivery. The mortality data may additionally be returned to the manufacturer or an insurance company, to use for ascertaining whether the item warranty has been voided, or a particular shipper was at fault for damage.
• Operation822 will collect ongoing training data and return it tooperation808 for further training the neural net trained with the received sensor data. Other mortality data may also be included in the ongoing training data, such as warranty claim and other repair and failure data. In some embodiments, early use of the sensor data may be with a simpler threshold analysis ofoperation804, but as data is collected, enough may be used for training a neural net to generate a mortality model.
• In some examples, the operations illustrated in the flowcharts may be implemented as software instructions encoded on a computer readable medium, in hardware programmed or designed to perform the operations, or both. For example, aspects of the disclosure may be implemented as a system on a chip or other circuitry including a plurality of interconnected, electrically conductive elements. While the aspects of the disclosure have been described in terms of various examples with their associated operations, a person skilled in the art would appreciate that a combination of operations from any number of different examples or some reordering is also within scope of the aspects of the disclosure.
Exemplary Operating Environment
• FIG. 9 is a block diagram of anexample computing device900 for implementing aspects disclosed herein, and is designated generally ascomputing device900.Computing device900 is one example of a suitable computing environment and is not intended to suggest any limitation as to the scope of use or functionality of the invention. Neither should thecomputing device900 be interpreted as having any dependency or requirement relating to any one or combination of components/modules illustrated.
• The examples and embodiments disclosed herein may be described in the general context of computer code or machine-useable instructions, including computer-executable instructions such as program components, being executed by a computer or other machine, such as a personal data assistant or other handheld device. Generally, program components including routines, programs, objects, components, data structures, and the like, refer to code that performs particular tasks, or implement particular abstract data types. The disclosed examples may be practiced in a variety of system configurations, including personal computers, laptops, smart phones, mobile tablets, hand-held devices, consumer electronics, specialty computing devices, etc. The disclosed examples may also be practiced in distributed computing environments, where tasks are performed by remote-processing devices that are linked through a communications network. For example, a distributed computing environment may host cloud synthetics services. Some embodiments of synthetics services may provide synthetic3D environments as well as rendering a surface in a synthetic scene.
• Computing device900 includes abus910 that directly or indirectly couples the following devices:memory912, one ormore processors914, one ormore presentation components916, input/output (I/O)ports918, I/O components920, apower supply922, and anetwork component924.Computing device900 should not be interpreted as having any dependency or requirement related to any single component or combination of components illustrated therein. Whilecomputing device900 is depicted as a seemingly single device,multiple computing devices900 may work together and share the depicted device resources. For instance,memory912 may be distributed across multiple devices, processor(s)914 may provide housed on different devices, and so on.
• Bus910 represents what may be one or more busses (such as an address bus, data bus, or a combination thereof). Although the various blocks ofFIG. 9 are shown with lines for the sake of clarity, in reality, delineating various components is not so clear, and metaphorically, the lines would more accurately be grey and fuzzy. For example, one may consider a presentation component such as a display device to be an I/O component. Also, processors have memory. Such is the nature of the art, and the diagram ofFIG. 9 is merely illustrative of an exemplary computing device that can be used in connection with one or more embodiments of the present invention. Distinction is not made between such categories as “workstation,” “server,” “laptop,” “hand-held device,” etc., as all are contemplated within the scope ofFIG. 9 and the references herein to a “computing device.”
• Memory912 may include any of the computer-readable media discussed herein.Memory912 may be used to store and access instructions configured to carry out the various operations disclosed herein. In some examples,memory912 includes computer storage media in the form of volatile and/or nonvolatile memory, removable or non-removable memory, data disks in virtual environments, or a combination thereof.
• Processor(s)914 may include any quantity of processing units that read data from various entities, such asmemory912 or I/O components920. Specifically, processor(s)914 are programmed to execute computer-executable instructions for implementing aspects of the disclosure. The instructions may be performed by the processor, by multiple processors within thecomputing device900, or by a processor external to theclient computing device900. In some examples, the processor(s)914 are programmed to execute instructions such as those illustrated in the flowcharts discussed below and depicted in the accompanying drawings. Moreover, in some examples, the processor(s)914 represent an implementation of analog techniques to perform the operations described herein. For example, the operations may be performed by an analogclient computing device900 and/or a digitalclient computing device900.
• Presentation component(s)916 present data indications to a user or other device. Exemplary presentation components include a display device, speaker, printing component, vibrating component, etc. One skilled in the art will understand and appreciate that computer data may be presented in a number of ways, such as visually in a graphical user interface (GUI), audibly through speakers, wirelessly betweencomputing devices900, across a wired connection, or in other ways.
• Ports918 allowcomputing device900 to be logically coupled to other devices including I/O components920, some of which may be built in. Examples I/O components920 include, for example but without limitation, a microphone, keyboard, mouse, joystick, game pad, satellite dish, scanner, printer, wireless device, etc.
• In some examples, thenetwork component924 includes a network interface card and/or computer-executable instructions (e.g., a driver) for operating the network interface card. Communication between thecomputing device900 and other devices may occur using any protocol or mechanism over any wired or wireless connection. In some examples, thenetwork component924 is operable to communicate data over public, private, or hybrid (public and private) using a transfer protocol, between devices wirelessly using short range communication technologies (e.g., near-field communication (NFC), BLUETOOTH® branded communications, or the like), or a combination thereof.
• Although described in connection with anexample computing device900, examples of the disclosure are capable of implementation with numerous other general-purpose or special-purpose computing system environments, configurations, or devices. Examples of well-known computing systems, environments, and/or configurations that may be suitable for use with aspects of the disclosure include, but are not limited to, smart phones, mobile tablets, mobile computing devices, personal computers, server computers, hand-held or laptop devices, multiprocessor systems, gaming consoles, microprocessor-based systems, set top boxes, programmable consumer electronics, mobile telephones, mobile computing and/or communication devices in wearable or accessory form factors (e.g., watches, glasses, headsets, or earphones), network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, virtual reality (VR) devices, holographic device, and the like. Such systems or devices may accept input from the user in any way, including from input devices such as a keyboard or pointing device, via gesture input, proximity input (such as by hovering), and/or via voice input.
• Examples of the disclosure may be described in the general context of computer-executable instructions, such as program modules, executed by one or more computers or other devices in software, firmware, hardware, or a combination thereof. The computer-executable instructions may be organized into one or more computer-executable components or modules. Generally, program modules include, but are not limited to, routines, programs, objects, components, and data structures that perform particular tasks or implement particular abstract data types. Aspects of the disclosure may be implemented with any number and organization of such components or modules. For example, aspects of the disclosure are not limited to the specific computer-executable instructions or the specific components or modules illustrated in the figures and described herein. Other examples of the disclosure may include different computer-executable instructions or components having more or less functionality than illustrated and described herein. In examples involving a general-purpose computer, aspects of the disclosure transform the general-purpose computer into a special-purpose computing device when configured to execute the instructions described herein.
• By way of example and not limitation, computer readable media comprise computer storage media and communication media. Computer storage media include volatile and nonvolatile, removable and non-removable memory implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules, or the like. Computer storage media are tangible and mutually exclusive to communication media. Computer storage media are implemented in hardware and exclude carrier waves and propagated signals. Computer storage media for purposes of this disclosure are not signals per se. Exemplary computer storage media include hard disks, flash drives, solid-state memory, phase change random-access memory (PRAM), static random-access memory (SRAM), dynamic random-access memory (DRAM), other types of random-access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disks (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information for access by a computing device. In contrast, communication media typically embody computer readable instructions, data structures, program modules, or the like in a modulated data signal such as a carrier wave or other transport mechanism and include any information delivery media.
Exemplary Operating Methods and Systems
• An exemplary system for determining item mortality based on tracked environmental conditions during transit implemented on at least one processor comprises: a processor; and a computer-readable medium storing instructions that are operative when executed by the processor to: receive sensor data for environmental conditions experienced by an item during transit; based at least on the received sensor data, determine mortality data for a first component of the item; based at least on the received sensor data, determine mortality data for a second component of the item, different from the first component; based at least on mortality data for the first component and mortality data for the second component, determine mortality data for the item; and based at least on the mortality data for the item and disposition rules, generate a disposition recommendation for the item.
• An exemplary method for determining item mortality based on tracked environmental conditions during transit implemented on at least one processor comprises: receiving sensor data for environmental conditions experienced by an item during transit; based at least on the received sensor data, determining mortality data for a first component of the item; based at least on the received sensor data, determining mortality data for a second component of the item, different from the first component; based at least on mortality data for the first component and mortality data for the second component, determining mortality data for the item; and based at least on the mortality data for the item and disposition rules, generating a disposition recommendation for the item.
• One or more exemplary computer storage devices having a first computer-executable instructions stored thereon for determining item mortality based on tracked environmental conditions during transit, which, on execution by a computer, cause the computer to perform operations which may comprise: receiving, from a blockchain, sensor data for environmental conditions experienced by an item during transit, wherein the sensor data comprises measurements from at least two sensors selected from the list consisting of: temperature, humidity, air pressure, condensation, salinity, CO2 level, time, shock, and vibration; based at least on the received sensor data, determining mortality data for a first component of the item; based at least on the received sensor data, determining mortality data for a second component of the item, different from the first component; based at least on mortality data for the first component and mortality data for the second component, determining mortality data for the item; and based at least on the mortality data for the item and disposition rules, generating a disposition recommendation for the item.
• An exemplary system implemented on at least one processor may comprise: a processor; and a non-transitory computer-readable medium storing instructions that are operative when executed by the processor, the instructions comprising logic for implementing any of the methods or processes disclosed herein.
• Alternatively, or in addition to the other examples described herein, examples include any combination of the following:
• • receiving sensor data comprises receiving sensor data from a blockchain;
  • the sensor data comprises measurements from at least one sensor selected from the list consisting of: temperature, humidity, air pressure, condensation, salinity, CO2 level, time, shock, and vibration;
  • the sensor data comprises measurements from at least two sensors selected from the list consisting of: temperature, humidity, air pressure, condensation, salinity, CO2 level, time, shock, and vibration;
  • determining mortality data for a component of the item comprises comparing the received sensor data against a damage threshold to generate the mortality data;
  • determining mortality data for a component of the item comprises using the received sensor data in a mortality model to generate the mortality data;
  • the instructions are further operative to generate the mortality model using a neural net trained with historical sensor data and historical mortality data; and
  • generating the mortality model further comprises generating the mortality model using data for the first component and data for the second component.
• The order of execution or performance of the operations in examples of the disclosure illustrated and described herein may not be essential, and thus may be performed in different sequential manners in various examples. For example, it is contemplated that executing or performing a particular operation before, contemporaneously with, or after another operation is within the scope of aspects of the disclosure. When introducing elements of aspects of the disclosure or the examples thereof, the articles “a,” “an,” “the,” and “said” are intended to mean that there are one or more of the elements. The terms “comprising,” “including,” and “having” are intended to be inclusive and mean that there may be additional elements other than the listed elements. The term “exemplary” is intended to mean “an example of” The phrase “one or more of the following: A, B, and C” means “at least one of A and/or at least one of B and/or at least one of C.”
• Having described aspects of the disclosure in detail, it will be apparent that modifications and variations are possible without departing from the scope of aspects of the disclosure as defined in the appended claims. As various changes could be made in the above constructions, products, and methods without departing from the scope of aspects of the disclosure, it is intended that all matter contained in the above description and shown in the accompanying drawings shall be interpreted as illustrative and not in a limiting sense. While the disclosure is susceptible to various modifications and alternative constructions, certain illustrated examples thereof are shown in the drawings and have been described above in detail. It should be understood, however, that there is no intention to limit the disclosure to the specific forms disclosed, but on the contrary, the intention is to cover all modifications, alternative constructions, and equivalents falling within the spirit and scope of the disclosure.

Claims (20)

What is claimed is:

1. A system for determining item mortality based on tracked environmental conditions during transit implemented on at least one processor, the system comprising:

a processor; and

a computer-readable medium storing instructions that are operative when executed by the processor to:

receive sensor data for environmental conditions experienced by an item during transit;

based at least on the received sensor data, determine mortality data for a first component of the item;

based at least on the received sensor data, determine mortality data for a second component of the item, different from the first component;

based at least on mortality data for the first component and mortality data for the second component, determine mortality data for the item; and

based at least on the mortality data for the item and disposition rules, generate a disposition recommendation for the item.

2. The system ofclaim 1 wherein receiving sensor data comprises receiving sensor data from a blockchain.

3. The system ofclaim 1 wherein the sensor data comprises measurements from at least one sensor selected from the list consisting of:

temperature, humidity, air pressure, condensation, salinity, CO2 level, time, shock, and vibration.

4. The system ofclaim 1 wherein the sensor data comprises measurements from at least two sensors selected from the list consisting of:

temperature, humidity, air pressure, condensation, salinity, CO2 level, time, shock, and vibration.

5. The system ofclaim 1 wherein determining mortality data for a component of the item comprises:

comparing the received sensor data against a damage threshold to generate the mortality data.

6. The system ofclaim 1 wherein determining mortality data for a component of the item comprises:

using the received sensor data in a mortality model to generate the mortality data.

7. The system ofclaim 6 wherein the instructions are further operative to:

generate the mortality model using a neural net trained with historical sensor data and historical mortality data.

8. The system ofclaim 7 wherein generating the mortality model further comprises generating the mortality model using data for the first component and data for the second component.

9. The system ofclaim 7 wherein the instructions are further operative to:

further train the neural net trained with the received sensor data.

10. A method for determining item mortality based on tracked environmental conditions during transit implemented on at least one processor, the method comprising:

receiving sensor data for environmental conditions experienced by an item during transit;

based at least on the received sensor data, determining mortality data for a first component of the item;

based at least on the received sensor data, determining mortality data for a second component of the item, different from the first component;

based at least on mortality data for the first component and mortality data for the second component, determining mortality data for the item; and

based at least on the mortality data for the item and disposition rules, generating a disposition recommendation for the item.

11. The method ofclaim 10 wherein receiving sensor data comprises receiving sensor data from a blockchain.

12. The method ofclaim 10 wherein the sensor data comprises measurements from at least one sensor selected from the list consisting of:

temperature, humidity, air pressure, condensation, salinity, CO2 level, time, shock, and vibration.

13. The method ofclaim 10 wherein the sensor data comprises measurements from at least two sensors selected from the list consisting of:

temperature, humidity, air pressure, condensation, salinity, CO2 level, time, shock, and vibration.

14. The method ofclaim 10 wherein determining mortality data for a component of the item comprises:

comparing the received sensor data against a damage threshold to generate the mortality data.

15. The method ofclaim 10 wherein determining mortality data for a component of the item comprises:

using the received sensor data in a mortality model to generate the mortality data.

16. The method ofclaim 15 further comprising:

generating the mortality model using a neural net trained with historical sensor data and historical mortality data.

17. The method ofclaim 16 wherein generating the mortality model further comprises generating the mortality model using data for the first component and data for the second component.

18. The method ofclaim 16 further comprising:

further training the neural net trained with the received sensor data.

19. One or more computer storage devices having computer-executable instructions stored thereon for determining item mortality based on tracked environmental conditions during transit, which, on execution by a computer, cause the computer to perform operations comprising:

receiving, from a blockchain, sensor data for environmental conditions experienced by an item during transit,

wherein the sensor data comprises measurements from at least two sensors selected from the list consisting of:

temperature, humidity, air pressure, condensation, salinity, CO₂level, time, shock, and vibration;

based at least on the received sensor data, determining mortality data for a first component of the item;

based at least on the received sensor data, determining mortality data for a second component of the item, different from the first component;

based at least on mortality data for the first component and mortality data for the second component, determining mortality data for the item; and

based at least on the mortality data for the item and disposition rules, generating a disposition recommendation for the item.

20. The one or more computer storage devices ofclaim 19

wherein determining mortality data for a component of the item comprises using the received sensor data in a mortality model to generate the mortality data,

and wherein the instructions further cause the computer to perform operations comprising:

generating the mortality model using a neural net trained with historical sensor data and historical mortality data and using data for the first component and data for the second component; and

further training the neural net trained with the received sensor data.

Images