Intensive analysis model for medical inventory management

Abstract

The invention provides a method, device and system for determining an immediate item. Historical item data is received. In one embodiment, an immediacy analysis model is trained with training data to generate a trained immediacy analysis model configured to receive item data related to an item, and generate an immediacy prediction of one or more items related to the item data. The fence includes a platform at a distal edge of the fence. The platform is configured to contact an article placed in the housing. The sensor is configured to generate a signal indicative of a fill level of the housing based on contact of the platform with an article placed in the housing. An operation is performed to prevent the item from being still unused after the target date.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application claims priority to U.S. Provisional Application No. 63 / 354,915, filed on June 23, 2022, entitled “Soon-To-Expire Analysis Models For Medical Inventory Management,” the entire contents of which are incorporated herein by reference. Technical Field

[0003] The subject matter described herein relates generally to data processing and, more particularly, to dynamic analytical models for STE analysis and medical inventory management. Background Art

[0004] Modern medical inventory management software applications provide a variety of solutions for monitoring the supply and use of stored medications. These types of software applications are sometimes integrated with utilization management software applications and are present in comprehensive pharmacy management software suites that can be deployed in a variety of medical environments (e.g., pharmacies, clinical trial laboratories, and medical facilities) to track the storage, distribution, consumption, and disposal of various drugs, equipment, and other supplies. In many cases, the operation of medical inventory management software applications can reduce operating costs and reduce waste. For example, many medical inventory management software applications are configured to track the shipment, delivery, storage, prescription, distribution, management, and waste of individual medications while generating one or more corresponding electronic records (e.g., cost, batch number, expiration date, patient name). Summary of the invention

[0005] Systems, methods, computer program products, and apparatus for medical inventory management with a near-expiration (STE) analysis are provided. In some exemplary embodiments, a stock controller may apply a near-expiration (STE) analysis model to identify that one or more items may not be used after their expiration date at their current storage location. Therefore, the stock controller may perform one or more corrective actions to prevent one or more items from not being used after their expiration date. For example, one or more items (or a specific number of one or more items) may be reallocated to a different location that may be consumed before its expiration date. Alternatively and / or additionally, the stock controller may preferentially allocate one or more items from a first location where one or more items are more likely to be unused after their expiration date, rather than allocating one or more items from a second location where one or more items are less likely to be unused after their expiration date.

[0006] The embodiments of the current theme may include methods consistent with the description provided herein, and articles including embodied machine-readable media, operable to enable one or more machines (e.g., computers, etc.) to implement operations that implement one or more described features. Similarly, the present invention also describes a computer system, which may include one or more processors and one or more memories connected to one or more processors. The memory may include a non-transitory computer-readable medium or a machine-readable storage medium, which may include one or more programs such as encoding, storage, etc., which enable one or more processors to perform one or more operations described herein. The computer-implemented method consistent with one or more embodiments of the current theme may be implemented by one or more data processors residing in a single computing system or multiple computing systems. Such multiple computing systems may be connected, and data and / or commands or other instructions may be exchanged via one or more connections or via direct connections between one or more of the multiple computing systems, etc., including, for example, connections through a network (e.g., the Internet, a wireless wide area network, a local area network, a wide area network, a personal area network, a peer-to-peer network, a mesh network, a wired network, etc.).

[0007] Details of one or more variations of the subject matter described herein are set forth in the accompanying drawings and the following description. Other features and advantages of the subject matter described herein will be apparent from the description and drawings, and from the claims. Although certain features of the presently disclosed subject matter are described for purposes of illustration related to medical inventories including medicines, equipment, and supplies, it should be readily understood that these features are not intended for purposes of limitation. The claims that follow this disclosure are intended to define the scope of the protected subject matter. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate certain aspects of the subject matter disclosed herein, and together with the description, help explain some principles associated with the disclosed embodiments. In the drawings:

[0009] Figure 1 depicts a system diagram illustrating an example of a medical inventory management system according to some exemplary embodiments;

[0010] Figure 2A depicts a schematic diagram illustrating an example of a STE analysis model according to some exemplary embodiments;

[0011] Figure 2B depicts a schematic diagram illustrating another example of a STE analysis model according to some exemplary embodiments;

[0012] Figure 3depicts a flow chart illustrating an example of a process for medical inventory management with time-to-expiration (STE) analysis according to some exemplary embodiments;

[0013] Figure 4A depicts a schematic diagram showing a logical flow of an example of a STE analysis model according to some exemplary embodiments;

[0014] Figure 4B depicts a schematic diagram showing the logic flow of another example of a STE analysis model according to some exemplary embodiments; and

[0015] Figure 5 Depicted is a block diagram illustrating an example of a computing system in accordance with some exemplary embodiments.

[0016] Whenever practicable, similar reference numerals refer to similar structures, features, or elements. DETAILED DESCRIPTION

[0017] A major goal of medical inventory management software applications is to reduce operating costs and reduce waste by storing, distributing, consuming and processing various medicines, equipment and other supplies. For example, a medical inventory management software application deployed in a medical facility can perform analysis to predict the supplies that may expire or move to another location for use in the inventory of the current medical supplies at the location within a certain period of time. In some embodiments, once the article is moved or identified as to be moved, the location or article will be excluded from further near-expiry analysis. This exclusion can have a time limit (e.g., 10 days after moving) or an event limit (e.g., until an inventory update event, such as a restock). Medical supplies identified as near-expiry (STE) refer to those medical supplies that are expected to expire within a given period of time. These near-expiry items are usually removed from the warehouse before being destroyed or reduced in stock (destocked) from their current location. In the latter case, the medical supplies that reduce stock can be replenished in stock at different locations, or at least a partial refund is returned.

[0018] As used herein, articles will expire (and be assigned an expiration date) based on the time that the articles are expected to remain effective and / or safe to use. It should be understood that the expiration timeframe will be different according to the articles. Some articles, such as some drugs prepared and / or repackaged locally (for example, in hospitals, pharmacies or other licensed facilities) may be "short-acting", which means that these articles have a very short expiration timeframe (for example, a few hours, a few days or a few weeks, rather than a few months or a few years), during which time, these articles are considered to be near the expiration date. In other cases, articles may be very expensive, in which case, the articles may need to be moved and stored in the position with the greatest possibility of being used before their expiration date. On the contrary, for articles with lower costs, the cost of transferring and replenishing in different locations may exceed the cost of the articles themselves, in which case, the timeframe for articles to be considered to be near the expiration date and to be moved to a new location may be shortened, and closer to the expiration date of the articles. For articles in short supply, the need to avoid waste due to expiration may exceed the cost of articles. Therefore, the timeframe for articles in short supply to be considered to be near the expiration date and to be transferred to a new location may be shorter than the timeframe for articles with more sufficient supply.

[0019] However, traditional medical inventory management software applications are imperfect for a variety of reasons. For example, traditional medical inventory management software applications perform a STE analysis based on the earliest expiration date of the current inventory at a specific location, even though this value is often incorrect because clinicians are not obligated to remove the inventory with the earliest expiration date, and the expiration date of the current inventory is not always confirmed and updated as part of the restocking workflow. In addition, the results of the STE analysis trigger reactive measures, such as the destruction of expired medical supplies and medical supplies that are too close to their expiration date to be restocked at other locations, which hinders efforts to reduce operating costs and waste.

[0020] In some exemplary embodiments, the inventory controller can perform a near-expiration (STE) analysis by applying a trained near-expiration (STE) analysis model to identify one or more items (e.g., medicines, equipment, and other supplies) that are unlikely to be used in their current location. The inventory controller can apply various embodiments of the near-expiration (STE) analysis model, including a hybrid model based on a heuristic model and a combination of one or more heuristic models and a machine learning model. In some cases, the near-expiration (STE) analysis model can be trained based on historical data points related to a medical facility and / or one or more similar medical facilities. The historical data points ingested by the near-expiration (STE) analysis model can be related to one or more distribution events, locations, and inventory levels of various items stored in the medical facility. For specific items stored in a medical facility, examples of such data points may include the number of items removed in the current time period, the inventory level of items in the current time period (e.g., measured in numerical values), the number of items consumed in the previous time period, the distance to the earliest expiration date associated with the item in the current time period, etc.

[0021] In some exemplary embodiments, a stock controller applying a STE analysis model may pre-identify that one or more items are unlikely to be used at their current location. Therefore, when it is determined that an item is unlikely to be used at its current location, the stock controller may perform various corrective actions to prevent the item from expiring at its current location. For example, the stock controller may apply a STE analysis model to determine that a particular item is more likely to remain unused after its expiration date at a first location than at a second location, in which case the stock controller may reallocate the item from the first location to the second location. Alternatively and / or additionally, the stock controller may prioritize allocating items from a first location that is likely to remain unused after its expiration date, rather than allocating items from a second location where the item is unlikely to remain unused. In some cases, if there are more items at the first location that are likely to remain unused after their expiration date than at the second location, the first location may be prioritized as the allocation location. Additionally, in some cases, the inventory controller can apply a time-to-expiration (STE) model to determine the quantity of items that may remain unused and adjust the quantity of the item ordered to replenish inventory accordingly, and may also adjust the reorder point and the maximum (or minimum) quantity of the item at that location for future replenishment, or even recommend removing the item from the inventory location entirely.

[0022] In some exemplary embodiments, a STE analysis model can be trained to identify the relationship between a single item and different storage locations. In particular, the item and the location where the item is stored will show a certain combination of features that will affect the possibility that the item is still not used at the location after its expiration date. Therefore, a STE analysis model can be trained to identify a combination of such features so as to identify items and their quantities that are likely to be unused at a specific storage location after its expiration date. Throughout the text, the term "location" can be used interchangeably with the term "storage location" and can refer to a medical environment at any granularity level. For example, the location where an item is stored can be a specific device for storing items (e.g., a distribution cabinet, a shelf, etc.), a building (or a part of a building) where the device is located, a department, a room within a department, a unit, or a care area of ​​a facility related to the item, the facility itself, the geographical area of ​​the facility, a network including facilities and one or more other facilities, etc.

[0023] The likelihood that an item remains unused after its expiration date at its current storage location may change over time due to changes in various factors, such as the speed at which items are used at that location, the types of items stored at that location, the cost of items, the expiration pattern of items, the movement pattern of items, etc. Therefore, in some exemplary embodiments, the inventory controller may periodically update the STE analysis model to adapt to changes in factors that affect the STE analysis of items stored at a particular medical facility. For example, in some cases, when the STE analysis model is trained at a first time t0, the STE analysis model may be updated at one or more consecutive time points thereafter. For example, at a second time t1, the STE analysis model may be trained based on data points between the first time t0 and the second time t1, thereby updating it.

[0024] Figure 1 A system diagram illustrating an example of a medical inventory management system 100 according to some exemplary embodiments is depicted. Figure 1 , the medical inventory management system 100 may include an inventory controller 110, a client device 120, and one or more medical locations 130. Figure 1As shown, the inventory controller 110, the client device 120, and one or more medical locations 130 can be communicatively connected via a network 140. The client device 120 can be a specially configured processor-based device, such as a point of care unit (PCU), a smart phone, a tablet, a wearable device, a desktop computer, a laptop computer, a workstation, etc. Meanwhile, the network 140 can be a wired and / or wireless network, such as a public land mobile network (PLMN), a local area network (LAN), a virtual local area network (VLAN), a wide area network (WAN), the Internet, etc.

[0025] In some exemplary embodiments, the inventory controller 110 may apply a near-expiration (STE) analysis model 115 to perform a near-expiration (STE) analysis on the items 135 stored at one or more locations 130. For example, the inventory controller 110 may apply the near-expiration (STE) analysis model 115 to determine the likelihood that the items 135 stored at one or more locations 130 will remain unused after their expiration date. Alternatively and / or additionally, the inventory controller 110 may apply the near-expiration (STE) analysis model 115 to determine the number of items 135 stored at one or more locations 130 that will remain unused after their expiration date.

[0026] In some exemplary embodiments, the inventory controller 110 may apply a near-expiration (STE) analysis model to predetermine that an item 135 is likely to remain unused at its current location and trigger various corrective actions to prevent the item 135 from expiring at its current location, or in some cases, to ensure that the item 135 is destocked early enough before it expires so that it can be replenished elsewhere. For example, when the inventory controller 110 determines that an item 135 is likely to remain unused at a first location 130a after its expiration date, but will be used at a second location 130b before its expiration date, the inventory controller 110 may reallocate the item 135 from the first location 130a to the second location 130b. In some cases, reallocating the item 135 from the first location 130a to the second location 130b may include transferring the item 135 from one distributed distribution location (e.g., a first distribution cabinet) to another distributed distribution location (e.g., a second distribution cabinet located in the same or a different facility or portion of a facility). In other cases, reallocating item 135 from first location 130a to second location 130b may include transferring item 135 from a distributed distribution location (e.g., a first distribution cabinet) to a central distribution location (e.g., a central pharmacy, a warehouse, etc.).

[0027] In some exemplary embodiments, the inventory controller 110 may generate one or more electronic records associated with the item being reallocated from the first location 130a to the second location 130b. For example, reallocating the item 135 from the first location 130a to the second location 130b may include transferring custody of the item 135 from a first user associated with the first location 130a to a second user associated with the second location 130b. Thus, the inventory controller 110 may generate one or more electronic records to document the chain of custody associated with the item 135. In some cases, the item 135 may be subject to certain regulatory requirements that require a certain chain of custody. Thus, the reallocation from the first location 130a to the second location 130b may further include an intermediate location (e.g., a pharmacy).

[0028] In the case where the item 135 is stored at multiple locations, if the item 135 is more likely to remain unused after its expiration date at the first location 130a than at the second location 130b, and / or if there are more items 135 that are likely to remain unused after their expiration date at the first location 130a than at the second location 130b, the inventory controller 110 may cause the item 135 to be dispensed from the first location 130a. For example, the first location 130a is the first drawer of an automated dispensing cabinet and the second location 130b is the second drawer of an automated dispensing cabinet. Instances of the item 135 may be stored at both locations. When a clinician requests the item 135 to be dispensed, the inventory controller 110 may apply the STE model (or view information generated by the STE model) to determine which location is released to dispense the item 135. The inventory controller 110 may authorize the dispense from the location identified as being most likely to expire closest to the current date. In some cases, inventory controller 110 may apply a time-to-expiration (STE) analysis model 115 to determine the quantity of items 135 that may remain unused and accordingly adjust the quantity of items 135 ordered at first location 130a and / or second location 130b to replenish inventory.

[0029] In some exemplary embodiments, upon identifying that an item 135 is likely to remain unused at one or more locations 130 beyond its expiration date, the inventory controller 110 may send one or more corresponding notifications 125 to the client devices 120 associated with the one or more locations 130. For example, the inventory controller 110 may send a notification 125 to a first location 130a with instructions to check the expiration date of the item 135 stored at the first location 130a, destock the item 135 from the first location 130a, and / or remove the item 135 from the first location 130a. In some cases, the instructions may further specify a certain number of items 135 for destocking and removal from the first location 130a and for transfer and storage at the second location 130b. In some cases, the inventory controller 110 may send the notification 125 at a specific time to ensure that the item 135 is destocked and removed from the first location 130a early enough to be restocked and consumed at the second location 130b before its expiration date. For example, if item 135 is a high cost item due to expire in a short period of time, but is stored at first location 130a with a history of infrequent dispensing activity, inventory controller 110 may send notifications 125 at an earlier time and / or with a higher frequency.

[0030] In some exemplary embodiments, the near expiration (STE) analysis model 115 can be trained to identify the relationship between a single item (e.g., item 135) and different storage locations 130. In particular, the item 135 and one or more locations 130 where the item 135 is stored may exhibit a combination of certain characteristics that affect the likelihood that the item 135 remains unused after its expiration date. For example, an item 135 stored at a first location 130a may exhibit a different set of characteristics from an item 135 stored at a second location 130b. Examples of these characteristics include the speed at which the item 135 is used at each location 130, the cost of the item 135, the expiration pattern of the item 135, the movement pattern of the item 135, and the like. When trained, the near expiration (STE) analysis model 115 is able to recognize that the item 135 may expire at the first location 130a, and that there is, for example, sufficient time to reduce the inventory of the item 135 from the first location 130a and transfer it to the second location 130b where the item 135 can be consumed before its expiration date, thereby achieving a significant reduction in operating costs and reducing waste.

[0031] In some exemplary embodiments, the inventory controller 110 may periodically update the STE analysis model 115, at least because the likelihood that an item 135 remains unused after its expiration date at its current storage location may change over time due to changes in various factors, such as the rate at which the item is used at the location, changes in the types of items stored at the location, the cost of the item, the expiration pattern of the item, the movement pattern of the item, etc. For example, when the STE analysis model 115 is trained at a first time t0, the inventory controller 110 may subsequently train the STE analysis model 115 based on data points between the first time t0 and the second time t1, thereby updating the STE analysis model 115 at the second time t1.

[0032] Changes in one or more of the foregoing factors may be attributed to simple reasons, such as changes in the packaging, manufacturing, storage requirements, and / or other characteristics of the item, and therefore, may be common. For example, if item 135 is a composite item, a repackaged item, and / or an item that requires special storage (e.g., refrigeration, etc.), item 135 may be associated with a shorter expiration date. By periodically retraining the STE analysis model 115 to update the STE analysis model 115, the STE analysis model 115 can be made responsive to the foregoing changes and maintain the accuracy of its STE analysis.

[0033] In some exemplary embodiments, the STE analysis model 115 may be trained to perform STE analysis on the items 135 based on various data points, including, for example, the cost of the item 135, the velocity or usage rate of the item 135, the number of removals of the item 135, the current inventory level of the item 135, the number of items 135 consumed in a previous time period, the distance to the earliest expiration date associated with the current inventory of the item 135, etc. Other data points that may be incorporated into the STE analysis of the item 135 may include its packaging, storage requirements, whether the item is a custom compound, etc.

[0034] At least some of the aforementioned data points may be represented as categorical values. For example, the cost of item 135 may be represented as a first binary value indicating whether item 135 is a high-cost item or a low-cost item, the current inventory level of item 135 may be represented as a second binary value indicating whether item 135 is associated with a low inventory value or a high inventory value, and the usage rate of item 135 may be represented as a third binary value indicating whether item 135 has a low usage rate or a high usage rate. At the same time, the number of items 135 removed, for example due to expiration or reduced inventory, may be represented as a category selected from a plurality of categories of removal percentages (e.g., a ratio of a first number of items 135 removed to a second number of items 135 in inventory at the beginning of the time period).

[0035] The percentiles representing the classification values ​​of the aforementioned data points (e.g., thresholds for low or high unit cost, low or high inventory dollar value, and low or high usage) and the categories for different removal percentages can be determined based on corresponding errors (e.g., mean absolute error (MAE) or a different error metric). For example, in some cases, as part of the training-to-expiration (STE) analysis model 115, the inventory controller 110 can determine thresholds for distinguishing high-value categories from low-value categories based on corresponding historical data from each of one or more locations 130. Thus, for example, high and low thresholds can be identified as percentiles (e.g., the 75th, 80th, or 85th percentiles) of an existing data set associated with a minimum error (e.g., mean absolute error (MAE) or a different error metric).

[0036] In some embodiments, when the system identifies an article 135 or position 130a, 130b as containing an article 135 of near expiration for reallocation or reduction of inventory, the system can ensure the safety of the position before reallocation or reduction of inventory occurs. For example, if the first position (e.g., drawer, pocket or box) of the automatic distribution cabinet includes an article that is considered to be about to expire (e.g., within a predetermined number of days of the predicted near expiration date; within a predetermined expiration confidence range, etc.), the automatic distribution cabinet can be configured to prevent any further distribution from the first position unless the clinician who performs the reduction of inventory or reallocation makes an access request. The access request can be identified based on the credentials or other user identification information provided by the clinician who accesses the automatic distribution cabinet. The access request can be based on the operation selected on the automatic distribution cabinet. For example, the clinician can activate the control element on the user interface to activate the reduction of inventory or reallocation mode. In this mode, the request to unlock or lock the position can be distinguished from the allocation request of a specific patient.

[0037] In some exemplary embodiments, the sickness-to-term (STE) analysis model 115 may be implemented as a heuristic model or a hybrid model combining one or more heuristic models and a machine learning model. Figure 2A depicts a schematic diagram showing an example of a STE analysis model 115 implemented as a hybrid model 200, Figure 2BAnother example of a STE analysis model 115 implemented as a heuristic model 250 is depicted. In some cases, the inventory controller 110 can select an implementation of the STE analysis model 115 that is more suitable for one or more locations 130, such as by being associated with a lower prediction error (e.g., mean absolute error (MAE) or a different error metric). For example, where the STE analysis model 115 is implemented as a heuristic model, the inventory controller 110 can identify one with the lowest prediction error from a selection of heuristic models that include different combinations of data points and classification values. Table 1 below depicts some examples of heuristic models and corresponding data points.

[0038] Table 1

[0039] Model Data Points Model 1 Item unit value (low / high) + item usage rate Model 2 Item value (low / high) + item usage rate Model 3 Item unit value (low / high) + distance to earliest expiration date Model 4 Item value (low / medium / high) + item usage rate

[0040] Inventory controller 110 may evaluate the models by providing each model with data for a group of controlled items, comparing the model predictions to the actual or expected output for each item, and based on the comparison, selecting the model that has the highest success rate in predicting the actual or expected output.

[0041] Figure 4A A schematic diagram illustrating an example of a logic flow 400 of a near-expiration (STE) analysis model 115 implemented as a heuristic model to determine a percentage of current inventory of items 135 at one or more locations 130 that are likely to remain unused past their expiration dates is depicted. Figure 4A In the example shown, the logic flow 400 may include a combination of factors such as current inventory levels, unit costs, inventory values, and earliest expiration dates to determine the percentage of the current inventory of items 135 that are likely to remain unused past their expiration dates. As described above, such a combination of factors may be selected as part of the training near expiration (STE) analysis model 115 based on the combination of factors being associated with a minimum error (e.g., as measured by mean absolute error (MAE) or a different error metric). In addition, as described above, Figure 4A As shown, the STE analysis model 115 may apply one or more of the aforementioned classification values ​​associated with the items 135. It should be understood that the inventory controller 110 may perform one or more corrective actions based on the percentage of items 135 that may remain unused, such as reducing inventory and / or reallocating the corresponding number of items 135.

[0042] exist Figure 4AIn the example of the logic flow 400 shown, at block 402, the STE analysis model 115 may first determine whether any number of items 135 remain at one or more locations 130. If some number of items 135 remain at one or more locations 130, then at block 404, the STE analysis model 115 may next determine whether the items 135 are high-cost items or low-cost items. As previously described, the threshold for whether an item 135 is classified as a high-unit-cost item or a low-unit-cost item may be determined as part of training the STE analysis model 115.

[0043] In addition, Figure 4A In the example shown, if item 135 is determined to be a high unit cost item, the STE analysis model 115 can determine that 100% of the current inventory of item 135 may remain unused after its expiration date. Alternatively, if item 135 is determined to be a low unit cost item, then at box 406, the STE analysis can use the STE analysis model 115 to continue to determine whether item 135 is associated with a high inventory value (e.g., the unit cost of the item multiplied by the number of items at a certain location in the inventory; the holding cost (e.g., hazardous, high-risk, or transferable drugs) multiplied by the number of items at a certain location in the inventory; the cost of replenishing or replacing an item (e.g., the time to re-compound or order) multiplied by the number of items at a certain location in the inventory). In the case where item 135 is associated with a high inventory value, the STE analysis model 115 can determine that 45% of the current inventory of item 135 may remain unused after its expiration date. However, if item 135 is not associated with a high inventory value, then at block 408, when the current inventory of item 135 is associated with an earliest expiration date, the STE analysis model 115 may determine that 45% of the current inventory of item 135 may remain unused after its expiration date. Conversely, if item 135 is not associated with a high inventory value and does not have an earliest expiration date, the STE analysis model 115 may determine that 0% of the current inventory of item 135 may remain unused after its expiration date, indicating that no inventory adjustment is required.

[0044] Figure 4B Depicted is a schematic diagram illustrating a logic flow 450 of another example of a STE analysis model 115 in accordance with some exemplary embodiments. Figure 4BThe example of the near expiration (STE) analysis model 115 shown in is configured to determine the removal percentage of items 135 stored in one or more locations 130 based on a combination of factors including the unit cost of the item 135 and the speed of the item 135. In some cases, the inventory controller 110 can perform one or more corrective actions based on the removal percentage, and the corrective action includes, for example, reducing inventory and / or reallocation of the corresponding number of items 135. Similarly, it should be understood that this combination of factors can be selected based on corresponding errors (e.g., mean absolute error (MAE) or different error metrics) during the training of the near expiration (STE) analysis model 115. In addition, each factor can be evaluated as a classification value, and the threshold of the classification value (e.g., high unit value and low unit value, fast movement and slow movement, etc.) is selected as part of the training near expiration (STE) analysis model 115 based on the corresponding error (e.g., mean absolute error (MAE) or different error metrics).

[0045] Refer again Figure 4B , the STE analysis model 115 implementing the logic flow 450 may first determine whether the item 135 is a high unit cost item or a low unit cost item before determining whether the item is a fast moving item or a slow moving item. Figure 4B As shown, if item 135 is determined to be a high unit cost item and is also a fast moving item, the near expiration (STE) analysis model 115 may identify 0% of the current inventory of item 135 for removal. Conversely, if item 135 is determined to be a slow moving, high unit cost item, the near expiration (STE) analysis model 115 may identify 60% of the current inventory of item 135 for removal. In the case where item 135 is a fast moving, low unit cost item, the near expiration (STE) analysis model 115 may identify 25% of the current inventory of item 135 for removal, and if item 135 is determined to be a slow moving, low unit cost item, 56% of the current inventory of item 135 may be identified for removal.

[0046] In the case where the near expiration (STE) analysis model 115 is implemented as a hybrid model combining one or more heuristic models and machine learning models, the inventory controller 110 can train and deploy one or more heuristic models and machine learning models based on the amount of data available for training the near expiration (STE) analysis model 115. In some cases, the training data used to train the near expiration (STE) analysis model 115 can be location-specific. For example, the near expiration (STE) analysis model 115 can be trained based on training data including historical data from the first location 130a. Therefore, the near expiration (STE) analysis model 115 can be trained to identify a combination of features that affect the possibility that the item 135 is still unused at the first location 130a after its expiration date. In addition, once trained, the near expiration (STE) analysis model 115 can be applied to current data from the first location 130a to determine whether the current inventory of the item 135 at the first location 130a is likely to be still unused after its expiration date. Where the second location 130b is sufficiently similar to the first location 130a, a near-expiration (STE) analysis model 115 trained on data from the first location 130a may also be applied to determine whether the current inventory of item 135 at the second location 130b is likely to remain unused past its expiration date.

[0047] In some embodiments, the system can determine that the evaluation of slow-moving and fast-moving items is more effective or more accurate in determining the clinical status of the item based on the type of item or other local clinical allocation factors. In this case, the system can evaluate not only different models, but also different modeling pipelines to identify the best accurate configuration for the site. This optimization can take into account not only accuracy, but also the time and other resources required to generate the clinical status. For example, if the pipeline considers the speed of the item (fast and slow moving items) and then considers the unit cost, the clinical status of the test item will be generated at a rate of n (e.g., 1 second) or using x amount of resources (e.g., network communications, processing cycles, memory, etc.). If a different configuration requires less time or uses a smaller amount of resources, the system will choose an alternative configuration.

[0048] To further illustrate, Figure 2AThe example of the hybrid model 200 shown in includes a machine learning model 210, a first heuristic model 220, and a second heuristic model 230, each of which has different requirements for the amount of training data. Therefore, in the case where the amount of available training data meets the first threshold (for example, more than 6 months of historical data are available), the hybrid model 200 can be trained by training the machine learning model 210 based on the training data. In the case where the amount of training data does not meet the first threshold but meets the second threshold (for example, less than 6 months but more than 2 months of data are available), the hybrid model 200 can be trained by training the first heuristic model 220 based on the training data. In the case where the amount of training data does not meet the second threshold (for example, less than 2 months of data are available), the hybrid model 200 can be trained by training the second heuristic model 230 based on the training data.

[0049] Figure 3 A flow chart illustrating an example of a process 300 for medical inventory management with time-to-expiration (STE) analysis according to some exemplary embodiments is depicted. Figures 1 to 3 , process 300 may be performed by inventory controller 110 applying a time-to-expiration (STE) analysis model 115 to determine, for example, whether an item 135 stored at one or more locations 130 is likely to remain unused at its current location past its expiration date.

[0050] At 302, the inventory controller 110 may train a near-expiration (STE) analysis model to perform near-expiration (STE) analysis on one or more locations. In some exemplary embodiments, the inventory controller 110 may train a near-expiration (STE) analysis model 115 to perform near-expiration (STE) analysis on one or more locations 130. The near-expiration (STE) analysis model 115 may be implemented as a heuristic model (e.g., heuristic model 250) or a hybrid model (e.g., hybrid model 200) combining one or more machine learning models and heuristic models. In addition, the near-expiration (STE) analysis model 115 may be trained based on historical data points associated with one or more locations 130. For each item (e.g., item 135) stored at one or more locations 130, examples of such data points include: the number of items removed in the current time period, the inventory level of the item in the current time period (e.g., measured in numerical terms), the number of items consumed in the previous time period, the distance to the earliest expiration date associated with the item in the current time period, etc. Through training, the near-expiration (STE) analysis model 115 can identify a combination of features that affect the likelihood that an item 135 remains unused after its expiration date at each of one or more locations. Examples of these features include the rate at which the item 135 is used at each location 130, the cost of the item 135, the expiration pattern of the item 135, the movement pattern of the item 135, etc.

[0051] As described above, the STE analysis model 115 can be implemented as one or more heuristic models and / or machine learning models. Therefore, it should be understood that one or more aspects of the artificial intelligence described can be implemented in whole or in part by a model (including a machine learning model). The training performed on the model can be supervised, unsupervised, reinforced, or a hybrid method using multiple learning techniques to generate the model. Training the model can include obtaining a set of training data and adjusting the features of the model to obtain the desired model output. For example, three features can be related to the desired device state. In this case, training can include receiving three features as the input of the model and adjusting the features of the model so that for each set of three features, the output device state matches the desired device state associated with the training data. In some cases, training can be dynamic, which means that the system can update the model using a set of events with detectable characteristics of events for adjusting the model.

[0052] In some cases, the STE analysis model 115 can be an equation, an artificial neural network, a recurrent neural network, a convolutional neural network, a decision tree and / or another machine-readable artificial intelligence structure. The features of the structure that can be used to adjust during training will be different based on the selected model. For example, if a neural network is the selected model, the features may include input elements, network layers, node density, node activation thresholds, weights between nodes, input or output value weights, etc. If the model is implemented as an equation (e.g., a regression equation), the features may include weights of input parameters, thresholds or limits for evaluating output values, or criteria selected from a set of equations.

[0053] Once the STE analysis model 115 is trained, it can be retrained to improve or update the model to reflect additional data or specific operating conditions. For example, as described above, the inventory controller 110 can periodically update the STE analysis model to adapt to changes in factors that affect the STE analysis of items stored in a particular medical facility. Retraining can be based on one or more signals detected by the device described herein, or as part of the method described herein. After detecting a specified signal, the system can initiate a training process to adjust the STE analysis model 115.

[0054] Further examples of machine learning and modeling features that may be included in the embodiments discussed above are described in “A survey of machine learning for big data processing” by Qiu et al., published in EURASIP Journal on Advances in Signal Processing (2016), the entire contents of which are incorporated herein by reference.

[0055] At 304, the inventory controller 110 may apply a trained near-expiration (STE) analysis model to identify items stored at one or more locations that may not be used after their expiration date. The trained model can view the unit cost of the item, the inventory quantity, the number of days from its earliest expiration date, and its usage rate, and provide the near-expiration amount of the item. For example, the inventory controller 110 may apply a trained near-expiration (STE) analysis model 115 to identify that item 135 may not be used after its expiration date at one or more locations 130. The inventory controller 110 may apply the near-expiration (STE) analysis model 115 periodically or when a change in the inventory of one or more items (such as item 135) is detected. In addition, the inventory controller 110 may apply the near-expiration (STE) analysis model 115 to identify items that may not be used after their expiration date at a single location or a group of locations (such as facilities, locations in the same geographic area, and locations within the same network). In order to apply the near-expiration (STE) analysis model 115, the inventory controller 110 can provide information related to at least a portion of the items currently in stock at one or more locations 130 (e.g., current inventory levels, unit costs, inventory values, and earliest expiration dates) for ingestion by the near-expiration (STE) analysis model 115. The logic of the near-expiration (STE) analysis model 115 can be applied to process the current inventory information and generate outputs that identify items that may not be used at their current locations after their expiration dates. In some cases, the output of the near-expiration (STE) analysis model 115 may include a list of items sorted by the likelihood that each item will expire at the current location, so that one or more corrective actions to prevent the items from expiring can be performed based on the list.

[0056] At 306, the inventory controller 110 may perform one or more corrective actions to prevent the item from remaining unused after its expiration date. When trained, the near expiration (STE) analysis model 115 may be applied to identify that the item 135 is likely to expire, for example, at the first location 130a, and has sufficient time to take corrective actions, such as reducing inventory of the item 135 from the first location 130a and transferring it to the second location 130b to ensure that the item 135 can be consumed before its expiration date. For example, when it is identified that the item 135 is more likely to remain unused after its expiration date at the first location 130a than at the second location 130b, the inventory controller 110 may reallocate the item 135 from the first location 130a to the second location 130b. Alternatively and / or additionally, if the item 135 is more likely to remain unused after its expiration date at the first location 130a than at the second location 130b, the inventory controller 110 may prioritize allocating the item 135 from the first location 130a rather than from the second location 130b. In some cases, the inventory controller 110 may apply the trained near-expiration (STE) analysis model 115 to determine the quantity of each of the items 135 that may still be unused at the first location 130a and the second location 130b. In the event that there are more items 135 that may still be unused at the first location 130a than at the second location 130b, the inventory controller 110 may trigger reallocation and / or prioritize a certain number of items 135 from the first location 130a. In some cases, the inventory controller 110 may also adjust the quantity of items 135 ordered at the first location 130a and / or the second location 130b to replenish inventory based on the quantity of each of the items 135 that may still be unused at the first location 130a and the second location 130b. Alternatively and / or additionally, the inventory controller 110 may adjust the reorder plan for the items 135 stored at the first location 130a and / or the second location 130b and / or the maximum (or minimum) quantity of the items 135 based on the quantity of each of the items 135 that may remain unused at the first location 130a and the second location 130b. In some cases, the inventory controller 110 may even recommend that the items 150 be completely removed from the inventory at the first location 130a and / or the second location 130b.

[0057] Figure 5 A block diagram illustrating a computing system 500 consistent with an embodiment of the current subject matter is depicted. Figure 1 and Figure 5 , computing system 500 may be used to implement inventory controller 110 and / or any components therein.

[0058] like Figure 5As shown, the computing system 500 may include a processor 510, a memory 520, a storage device 530, and an input / output device 540. The processor 510, the memory 520, the storage device 530, and the input / output device 540 may be interconnected via a system bus 550. The processor 510 is capable of processing instructions executed within the computing system 500. The instructions so executed may implement, for example, one or more components of the inventory controller 110. In some exemplary embodiments, the processor 510 may be a single-threaded processor. Alternatively, the processor 510 may be a multi-threaded processor. The processor 510 is capable of processing instructions stored in the memory 520 and / or the storage device 530 to display graphical information of a user interface provided via the input / output device 540.

[0059] Memory 520 is a computer-readable medium, such as a volatile or non-volatile medium, that stores information within computing system 500. Memory 520 may store, for example, a data structure representing a configuration object database. Storage device 530 is capable of providing persistent storage for computing system 500. Storage device 530 may be a floppy disk device, a hard disk device, an optical disk device, a tape device, a solid-state device, and / or any other suitable persistent storage device. Input / output device 540 provides input / output operations for computing system 500. In some exemplary embodiments, input / output device 540 includes a keyboard and / or a pointing device. In various embodiments, input / output device 540 includes a display unit for displaying a graphical user interface.

[0060] According to some exemplary embodiments, the input / output device 540 can provide input / output operations for the network device. For example, the input / output device 540 can include an Ethernet port or other network port that communicates with one or more wired and / or wireless networks (e.g., a local area network (LAN), a wide area network (WAN), the Internet).

[0061] In some exemplary embodiments, computing system 500 can be used to execute various interactive computer software applications, which can be used to organize, analyze and / or store data in various formats. Alternatively, computing system 500 can be used to execute any type of software application. These applications can be used to perform various functions, such as planning functions (e.g., generating, managing, editing electronic spreadsheet documents, word processing documents and / or any other objects, etc.), computing functions, communication functions, etc. The application can include various additional functions, or can be an independent computing product and / or function. After activation in the application, these functions can be used to generate a user interface provided via input / output device 540. The user interface can be generated by computing system 500 and presented to the user (e.g., on a computer screen monitor, etc.).

[0062] One or more aspects or features of the subject matter described herein can be implemented by digital electronic circuits, integrated circuits, specially designed ASICs, field programmable gate arrays (FPGAs), computer hardware, firmware, software, and / or combinations thereof. These various aspects or features can include implementations in one or more computer programs, which can be executed and / or compiled in a programmable system, which includes at least one programmable processor, which can be a special-purpose processor or a general-purpose processor, which is connected to a storage system, at least one input device, and at least one output device to receive data and instructions, and sends data and instructions to the storage system, at least one input device, and at least one output device. A programmable system or computing system can include a client and a server. Clients and servers are usually far away from each other, and generally interact through a communication network. The relationship between a client and a server is generated by a computer program that runs on each computer and has a client-server relationship between each other.

[0063] These computer programs (also referred to as programs, software, software applications, applications, components or codes) include machine instructions for programmable processors and can be implemented by high-level programming languages, and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the term "machine-readable medium" refers to any computer program product, device and / or device for providing machine instructions and / or data to a programmable processor, such as a disk, an optical disk, a memory and a programmable logic device (PLD), including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor. A machine-readable medium can store such machine instructions non-temporarily, for example, a non-transient solid-state memory or a magnetic hard drive or any equivalent storage medium. A machine-readable medium can alternatively or additionally store such machine instructions in a transient manner, for example, a processor's cache memory or other random access memory associated with one or more physical processor cores.

[0064] In order to provide interaction with a user, one or more aspects or features of the subject matter described herein may be implemented on a computer having a display device, such as a cathode ray tube (CRT) or a liquid crystal display (LCD) or a light emitting diode (LED) display screen for displaying information to the user, and a keyboard and pointing device, such as a mouse or a trackball, through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user. For example, the feedback provided to the user may be any form of sensory feedback, such as visual feedback, auditory feedback, or tactile feedback; and input from the user may be received in any form, including sound, voice, or tactile input. Other possible input devices include touch screens or other touch sensing devices, such as single-point or multi-point resistive or capacitive trackpads, voice recognition hardware and software, optical scanners, optical pointers, digital image acquisition devices, and related interpretation software, etc.

[0065] In the above description and claims, phrases such as "at least one" or "one or more" may appear after a connected list of elements or features. The term "and / or" may also appear in a list of two or more elements or features. Unless there is an implicit or explicit contradiction in the context in which the phrase is used, such phrases mean any element or feature listed separately, or any listed element or feature combined with any other listed element or feature. For example, the phrases "at least one of A and B", "one or more of A and B", and "A and / or B" each mean "single A, single B, or A and B". Similar explanations also apply to lists including three or more items. For example, the phrases "at least one of A, B, and C", "one or more of A, B, and C", and "A, B, and / or C" each mean "single A, single B, single C, A and B, A and C, B and C, or A, B and C". The term "based on" used above and in the claims means "based at least in part on", and unrecorded features or elements are also allowed.

[0066] As used herein, a "user interface" (also referred to as an interactive user interface, graphical user interface, or UI) may refer to a web-based interface including data fields and / or other control elements for receiving input signals or providing electronic information and / or providing information to a user in response to any received input signals. Control elements may include dials, buttons, icons, selectable areas, or other perceptible indicia presented via the UI that, when interacted with (e.g., clicked, touched, selected, etc.), initiate data exchange with the device presenting the UI. The UI may be presented in whole or in part using a web-based interface such as Hypertext Markup Language (HTML), FLASH, or the like. TM , JAVA TM , NETTM , C, C++, web services, rich site summary (RSS) technology. In some embodiments, the UI can be included in an independent client (e.g., a fat client) that is configured to communicate (e.g., send or receive data) according to one or more aspects of the description. The communication can be communication with the medical device or a server communicating with it.

[0067] Further non-limiting aspects or embodiments are set forth in the following numbered examples:

[0068] Example 1: A method includes: under the control of one or more processors, receiving training data including historical data related to an item; training an expiration analysis model using the training data to generate a trained expiration analysis model, wherein the trained expiration analysis model is configured to receive item data related to the item and generate expiration predictions for one or more items related to the item data; receiving inventory information of the item; processing at least a portion of the inventory information using the trained expiration analysis model to determine that items stored at one or more locations may remain unused after a target date; and providing an output to an inventory controller to perform operations to prevent items from remaining unused after the target date.

[0069] Example 2: The method of Example 1, wherein preventing the item from remaining unused after an expiration date comprises moving, by the inventory controller, at least a portion of the item from the one or more locations to a use location.

[0070] Example 3: The method of any of the preceding examples, wherein determining that items stored at one or more locations may have remained unused past an expiration date comprises comparing the classification value to a threshold value.

[0071] Example 4: The method of any of the preceding examples, wherein the classification value comprises one or more of a unit cost, a usage speed, and a movement speed of the item.

[0072] Example 5: The method of any of the preceding examples, wherein the historical data includes inventory changes from multiple locations.

[0073] Example 6: The method of any of the preceding examples, wherein the near-term analysis model comprises a machine learning model and one or more heuristic models.

[0074] Example 7: The method of any of the foregoing examples, wherein training the near-expiration analysis model comprises: determining whether the historical data satisfies a first threshold; and in response to determining that the historical data satisfies the first threshold, performing training using a machine learning model.

[0075] Example 8: The method of any of the foregoing examples, wherein training the near-expiration analysis model comprises: determining whether the historical data satisfies a first threshold; in response to determining that the historical data does not satisfy the first threshold, determining whether the historical data satisfies a second threshold; and in response to determining that the historical data satisfies the second threshold, performing training using one of the one or more heuristic models.

[0076] Example 9: The method of any of the preceding examples, wherein the one or more heuristic models include a model defining an association between item unit value and item usage rate, item value and item usage rate, or item unit value and distance to earliest expiration date.

[0077] Example 10: The method of any of the preceding examples, wherein the training comprises any one of supervised training, unsupervised training, reinforcement training, dynamic training or hybrid training.

[0078] Example 11: The method of any of the foregoing examples, wherein training a clinical expiration analysis model comprises: acquiring training item data; generating a first clinical expiration analysis model comprising a first processing pipeline, wherein the machine learning model receives the training item data, and wherein the heuristic model receives at least a portion of a first output from the machine learning model as a first input; generating a second clinical expiration analysis model comprising a second processing pipeline, wherein the heuristic model receives the training item data, and wherein the machine learning model receives at least a portion of a second output from the heuristic model as a second input; measuring resource usage for processing at least a portion of the training item data using the first clinical expiration analysis model and the second clinical expiration analysis model; and selecting one of the first clinical expiration analysis model and the second clinical expiration analysis model as the clinical expiration analysis model based on the resource usage.

[0079] Example 12: The method of any of the preceding examples, wherein the target data is one of an expiration date of an item, a predetermined amount of time from a current date, or a planned inventory renewal date.

[0080] Example 13: A method of any of the preceding examples, wherein a first instance of the item is available at a first location managed by an inventory controller, and a second instance of the item is available at a second location managed by an inventory controller, and wherein preventing the first instance of the item from remaining unused after a target date includes configuring the inventory controller to allocate the item from the first location upon receiving a request to allocate the item.

[0081] Example 14: A system includes: at least one data processor; and at least one memory storing instructions that, when executed by the at least one data processor, produce operations including the following operations: receiving training data including historical data related to an item; training an expiration analysis model using the training data to generate a trained expiration analysis model; applying the trained expiration analysis model to determine that items stored at one or more locations may not have been used after an expiration date; and providing an output to perform operations to prevent the item from not being used after the expiration date.

[0082] Example 15: The system of Example 14, wherein the operation of preventing the item from remaining unused after the expiration date includes: moving at least a portion of the item from the one or more locations to a use location by the inventory controller, and wherein the historical data includes inventory changes from multiple locations.

[0083] Example 16: The system of any of the preceding examples, wherein determining that an item stored at one or more locations may remain unused after an expiration date comprises comparing a classification value to a threshold, wherein the classification value comprises one or more of a unit cost, a usage rate, and a movement rate of the item.

[0084] Example 17: A system of any of the preceding examples, wherein the expiration analysis model comprises a machine learning model and one or more heuristic models, wherein the one or more heuristic models comprises a model defining an association between an item unit value and an item usage rate, an item value and an item usage rate, or an item unit value and a distance to the earliest expiration date.

[0085] Example 18: A system of any of the foregoing examples, wherein training the near-expiration analysis model includes: determining whether the historical data meets a first threshold; and in response to determining that the historical data meets the first threshold, performing training using a machine learning model; or in response to determining that the historical data does not meet the first threshold, determining whether the historical data meets a second threshold; and in response to determining that the historical data meets the second threshold, performing training using one of the one or more heuristic models.

[0086] Example 19: The system of any of the preceding examples, wherein the training comprises any of supervised training, unsupervised training, reinforcement training, dynamic training, or hybrid training.

[0087] Example 20: A non-transitory computer-readable medium storing instructions that, when executed by at least one data processor, produce operations comprising: receiving training data comprising historical data related to an item; training an expiration analysis model using the training data to generate a trained expiration analysis model; applying the trained expiration analysis model to determine that items stored at one or more locations may have remained unused after an expiration date; and providing an output to perform operations to prevent the item from remaining unused after the expiration date.

[0088] Depending on the desired configuration, the subject matter described herein can be implemented as a system, device, method and / or article. The embodiments set forth in the foregoing description do not represent all embodiments consistent with the subject matter described herein. On the contrary, they are merely some examples consistent with the aspects related to the described subject matter. Although some changes are described in detail above, other modifications or additions are also possible. In particular, further features and / or changes can be provided in addition to those set forth herein. For example, the embodiments described above can be directed to various combinations and sub-combinations of the disclosed features and / or combinations and sub-combinations of several further features disclosed above. In addition, the logic flows depicted in the accompanying drawings and / or the logic flows described herein do not necessarily require the specific order or sequential order shown to obtain the desired results. Other embodiments may fall within the scope of the appended claims.

Claims

1. A method, comprising: Under the control of one or more processors, receiving training data including historical data associated with an item; Training an expiration analysis model using the training data to generate a trained expiration analysis model, wherein the trained expiration analysis model is configured to receive item data related to an item and generate an expiration prediction of one or more items related to the item data; receiving inventory information of the item; Processing at least a portion of the inventory information using the trained near-expiration analysis model to determine that items stored at one or more locations are likely to remain unused after a target date; Provides output to the inventory controller to perform actions that prevent items from remaining unused after the target date.

2. The method according to claim 1, wherein: Preventing the items from remaining unused after their expiration dates includes moving, by the inventory controller, at least a portion of the items from the one or more locations to a usage location.

3. The method according to claim 1, wherein: Determining that items stored at one or more locations may have remained unused past an expiration date includes comparing a classification value to a threshold value.

4. The method according to claim 3, wherein: The classification value includes one or more of a unit cost, a usage speed, and a movement speed of the item.

5. The method according to claim 1, wherein: The historical data includes inventory changes from multiple locations.

6. The method according to claim 1, wherein: The clinical analysis model includes a machine learning model and one or more heuristic models.

7. The method according to claim 6, wherein: Training the model for period analysis includes: Determining whether the historical data meets a first threshold; In response to determining that the historical data satisfies the first threshold, training is performed using the machine learning model.

8. The method according to claim 7, wherein: Training the model for period analysis includes: Determining whether the historical data meets a first threshold; In response to determining that the historical data does not satisfy the first threshold, determining whether the historical data satisfies a second threshold; In response to determining that the historical data satisfies the second threshold, training is performed using one of the one or more heuristic models.

9. The method according to claim 6, wherein: The one or more heuristic models include a model that defines a correlation between item unit value and item usage rate, item value and item usage rate, or item unit value and distance to earliest expiration date.

10. The method according to claim 1, wherein: The training includes any of supervised training, unsupervised training, reinforcement training, dynamic training or hybrid training.

11. The method according to claim 6, wherein: Training the model for period analysis includes: Get training item data; generating a first expiration analysis model comprising a first processing pipeline, wherein the machine learning model receives training item data, and wherein the heuristic model receives at least a portion of a first output from the machine learning model as a first input; generating a second expiration analysis model comprising a second processing pipeline, wherein the heuristic model receives the training item data, and wherein the machine learning model receives at least a portion of a second output from the heuristic model as a second input; measuring resource usage for processing at least a portion of the training item data using the first expiration analysis model and the second expiration analysis model; One of the first and second critical analysis models is selected as the critical analysis model based on the resource usage.

12. The method according to claim 1, wherein: The target data is one of an item's expiration date, a predetermined amount of time from the current date, or a planned inventory renewal date.

13. The method according to claim 1, wherein: a first instance of the item is available at a first location managed by the inventory controller, and a second instance of the item is available at a second location managed by the inventory controller, The operation of preventing the first instance of the item from remaining unused after the target date includes: configuring the inventory controller to allocate the item from the first location when a request to allocate the item is received.

14. A system comprising: at least one data processor; as well as at least one memory storing instructions that, when executed by the at least one data processor, result in operations including: receiving training data including historical data associated with an item; Training the clinical analysis model using the training data to generate a trained clinical analysis model; Applying the trained near-expiration analysis model to determine items stored at one or more locations that may have remained unused past their expiration dates; Provides output to perform actions that prevent items from being left unused past their expiration date.

15. The system of claim 14, wherein: Preventing items from remaining unused after an expiration date includes moving, by an inventory controller, at least a portion of the items from the one or more locations to a usage location, and wherein the historical data includes inventory changes from the plurality of locations.

16. The system of claim 14, wherein: Determining that items stored at one or more locations may remain unused past an expiration date includes comparing a classification value to a threshold, wherein the classification value includes one or more of a unit cost, a usage rate, and a movement rate of the item.

17. The system of claim 14, wherein: The expiration analysis model includes a machine learning model and one or more heuristic models, wherein the one or more heuristic models include a model that defines the association between the unit value of an item and the item usage rate, the item value and the item usage rate, or the unit value of an item and the distance to the earliest expiration date.

18. The system of claim 14, wherein: Training the model for period analysis includes: Determining whether the historical data meets a first threshold; In response to determining that the historical data satisfies the first threshold, performing training using the machine learning model; In response to determining that the historical data does not satisfy the first threshold, determining whether the historical data satisfies a second threshold; In response to determining that the historical data satisfies the second threshold, training is performed using one of the one or more heuristic models.

19. The system of claim 14, wherein: The training includes any of supervised training, unsupervised training, reinforcement training, dynamic training or hybrid training.

20. A non-transitory computer readable medium storing instructions which, when executed by at least one data processor, result in operations comprising: receiving training data including historical data associated with an item; Training the clinical analysis model using the training data to generate a trained clinical analysis model; Applying the trained near-expiration analysis model to determine items stored at one or more locations that may have remained unused past their expiration dates; Provides output to perform actions that prevent items from being left unused past their expiration date.

Images