Identification and authentication of drugs

Abstract

In some embodiments, a device may receive prescription information associated with a medication in a container. When the medication is in the container and the container is positioned on a receptacle, the device may cause a camera to capture first image data associated with the medication. The device may cause an adjustment device to reposition the container on the receptacle. When the medication is in the container, the device may cause a camera to capture second image data associated with the medication. The device may process the first and second image data via a neural network to identify the medication based on descriptions of individual units of the medication included in the first and second image data. The device may verify the medication based on the prescription information and an identifier of the medication provided by the neural network.

Description

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] This application is a continuation-in-part of U.S. Patent Application No. 16 / 718,519, filed on December 18, 2019, entitled “IDENTIFICATION AND VERIFICATION OF MEDICATION,” which is a divisional application of U.S. Patent Application No. 16 / 276,059, filed on February 14, 2019, entitled “IDENTIFICATION AND VERIFICATION OF MEDICATION,” which claims priority to U.S. Provisional Patent Application No. 62 / 769,132, filed on November 19, 2018. This application also claims priority to U.S. Provisional Patent Application No. 63 / 092,735, filed on October 16, 2020, entitled “SYSTEM FOR IDENTIFICATION AND VERIFICATION OF MEDICATION.” The disclosures of these prior applications are considered a part of and incorporated by reference into this application. Technical Field

[0003] The present application relates to the identification and verification of drugs, and more particularly, to a method, device, and drug analysis system for identifying and verifying drugs. Background Art

[0004] Common medication forms include pills, capsules, tablets, and the like. The medication may be contained in a container. In some cases, a pharmacist, a medication filling device, and / or a pharmacist assisted by a medication filling device may fill the container with medication according to a prescription. The medication may then be administered to the person for whom the medication was prescribed (e.g., the person, a caregiver, a parent, a physician, etc.). Summary of the Invention

[0005] In some embodiments, a method includes receiving, by a device, prescription information associated with a medication in a container; causing, by the device, a camera device to capture first image data associated with the medication while the medication is in the container and the container is positioned on the container; causing, by the device, an adjustment device to reposition the container on a receiver; causing, by the device, a camera device to capture second image data associated with the medication while the medication is in the container; processing, by the device and via a neural network, the first image data and the second image data to identify the medication based on descriptions of individual units of the medication included in the first image data and the second image data; verifying, by the device, the medication based on the prescription information and an identifier of the medication provided by the neural network; and performing, by the device, an action associated with indicating that the medication is verified according to the prescription information.

[0006] In some embodiments, a device includes one or more memories and one or more processors communicatively connected to the one or more memories and configured to receive prescription information associated with a medication in a container, wherein the container is positioned on a receiver of the device; iteratively obtain multiple images of the medication by: adjusting the container on the container via an adjustment device to attempt to reposition individual units of the medication within the container, and capturing image data associated with the medication while the medication is within the container via a camera device; processing the multiple images via a neural network to identify the medication based on one or more descriptions of the units in the individual units; verifying the medication based on the prescription information and a medication identifier on the unit; and performing an action, the action associated with indicating that the medication is verified according to the prescription information.

[0007] In some embodiments, a drug analysis system includes: a receiver configured to support a container on a receiver window; a camera device positioned below the receiver window and configured to have the receiver window within a field of view of the camera; an adjustment device configured to move the receiver to adjust a position of a drug in the container; and a control device configured to identify the drug in the container by causing the adjustment device to reposition the container on the receiver and causing the camera device to capture image data associated with the drug; and processing the image data through a neural network to identify the drug; and performing an action associated with identifying the drug.

[0008] According to a first aspect of the present disclosure, a method is provided, comprising: receiving, by a device, prescription information associated with a drug in a container; causing, by the device, a camera device to capture first image data associated with the drug while the drug is in the container and the container is positioned on a receiver; causing, by the device, an adjustment device to reposition the container on the receiver; causing, by the device, a camera device to capture second image data associated with the drug while the drug is in the container; processing, by the device, the first image data and the second image data via a neural network to identify the drug based on descriptions of individual units of the drug included in the first image data and the second image data; verifying, by the device, the drug based on the prescription information and an identifier of the drug provided by the neural network; and performing, by the device, an action associated with indicating that the drug is verified according to the prescription information.

[0009] According to some embodiments, the prescription information includes at least one of: an identifier of the medication; information identifying a dosage of the medication; or information identifying a quantity of the medication.

[0010] According to some embodiments, wherein the adjustment device comprises a vibration mechanism, the vibration mechanism is configured to move the container on the receiver.

[0011] According to some embodiments, further comprising causing a weighing device to obtain weight data associated with the medication while the medication is within the container, wherein the medication is authenticated based on the prescription information, the identifier, and the weight data.

[0012] According to some embodiments, wherein the neural network comprises a convolutional neural network, the neural network is configured to at least one of: segment the first image data and the second image data into descriptions of individual units; determine a classification score of the description associated with identifying a drug based on corresponding ones of the individual units; and identify the drug based on the classification score.

[0013] According to some embodiments, the method further includes: adjusting at least one of the following before causing the camera device to capture the second image data: a polarization of a lens of the camera device; a filter of the lens of the camera device; a zoom setting of the camera device; or a wavelength of a light emitter associated with the camera device.

[0014] According to some embodiments, wherein performing the action includes: indicating via a display that the medication is verified; or providing a notification to the medication management system that the medication is verified in association with the prescription information.

[0015] According to a second aspect of the present disclosure, a device is provided, comprising: one or more memories; and one or more processors, the one or more processors being communicatively coupled to the one or more memories, the one or more processors being configured to: receive prescription information associated with a drug in a container, wherein the container is positioned on a receiver of the device; acquire multiple images of the drug by iteratively performing the following processes: adjusting the container on the receiver via an adjustment device to attempt to reposition individual units of the drug within the container, and capturing image data associated with the drug via a camera device while the drug is in the container; processing the multiple images via a neural network to identify the drug based on one or more descriptions of the unit in the individual unit; verifying the drug based on the prescription information and an identifier of the drug on the unit; and performing an action, the action being associated with indicating that the drug is verified according to the prescription information.

[0016] According to some embodiments, the prescription information includes at least one of: an identifier of the medication; information identifying a dosage of the medication; or information identifying a quantity of the medication.

[0017] According to some embodiments, the receiver includes a receiver window configured to support the container while the camera device captures image data, wherein the camera device is positioned below the receiver window and the receiver window is within a field of view of the camera device.

[0018] In accordance with some embodiments, after corresponding image data is captured via a camera device, images in a plurality of images are iteratively processed, wherein images of the plurality of images are acquired, until at least one of the following: a drug is identified in an image in the plurality of images, or a predetermined number of images are acquired.

[0019] According to some embodiments, images of the plurality of images are iteratively acquired until a predetermined number of the plurality of images are acquired, wherein the predetermined number is associated with a configuration of the neural network.

[0020] According to some embodiments, wherein the one or more processors, when performing actions, are configured to: indicate via a display that the medication is verified; or provide a notification to the medication management system that the medication is verified in association with the prescription information.

[0021] According to a third aspect of the present disclosure, there is provided a drug analysis system, comprising: a receiver configured to support a container on a receiver window; a camera device located below the receiver window and configured to have the receiver window within a field of view of the camera; an adjustment device configured to move the receiver to adjust a position of a drug in the container; and a control device configured to: identify the drug in the container by causing the adjustment device to reposition the container on the receiver, causing the camera device to capture image data associated with the drug, processing the image data via a neural network to identify the drug; and performing an action associated with identifying the drug.

[0022] According to some embodiments, the receiver window includes one or more adjustable filters.

[0023] According to some embodiments, wherein the adjustment device comprises a vibration mechanism, the vibration mechanism is configured to move the container on the receiver.

[0024] According to some embodiments, wherein the neural network comprises a convolutional neural network, the convolutional neural network is configured to at least one of: segment the image data into descriptions of individual units of a drug; determine a classification score of the description associated with the identified drug based on corresponding ones of the individual units; and determine the drug based on the classification score.

[0025] According to some embodiments, at least one of the following is further included:

[0026] a polarizing lens configured to reduce reflected light depicted in an image associated with the image data; a filter configured to filter light of a particular wavelength from an image associated with the image data; a lens configured to adjust the size of a field of view; or a light emitter configured to adjust characteristics of light in an image associated with the image data.

[0027] In accordance with some embodiments, wherein when an action is performed, the control device is configured to: obtain prescription information associated with a medication; verify the medication based on the prescription information and an identifier of the medication identified in the image data by the neural network; and provide a notification via a display or to a medication management system that the medication is verified to be associated with the prescription information.

[0028] According to some embodiments, the device further includes: a weighing device associated with the receiver, the weighing device being configured to obtain weight data associated with the drug, wherein the control device is further configured to: cause the weighing device to obtain weight data associated with the drug when the drug is in the container, wherein the drug is verified based on the prescription information, the identifier and the weight data. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 is a schematic diagram of an example implementation described herein.

[0030] Figures 2A-2B is a schematic diagram of an exemplary medical device described herein.

[0031] Figure 3 is an example diagram illustrating training and using a machine learning model in connection with identifying and validating drugs.

[0032] Figure 4 is a schematic diagram of an example environment in which the systems and / or methods described herein may be implemented.

[0033] Figure 5 yes Figure 4 A diagram of example components of one or more devices.

[0034] Figure 6 is a flow chart of an exemplary process associated with identification and authentication of a medication. DETAILED DESCRIPTION

[0035] The following detailed description of example implementations refers to the accompanying drawings, in which the same reference numerals in different drawings may represent the same or similar elements.

[0036] In some cases, a pharmacist, a medication-filling device, and / or a pharmacist assisted by a medication-filling device, etc., can fill a container with medication (e.g., pills, capsules, tablets, etc.) according to one or more instructions (e.g., a prescription). In some cases, it is necessary to identify and / or verify the medication in the container (e.g., to ensure that the prescription was correctly issued). In some cases, the medication can be removed from the container, and the device can analyze the medication (e.g., perform a chemical analysis) to identify and / or verify the medication. In other cases, different devices can analyze the medication while it is in the container by illuminating the container with a specific type of light to identify and / or verify the medication. However, these devices are complex and require complex components to perform complex operations, such as opening the container, generating a chemical reaction, generating and focusing a specific type of light, and detecting characteristics of the medication. In addition, the devices require significant on-board processing resources to identify and / or verify the medication. Furthermore, these devices are limited to analyzing the medication, not the container and / or container components, such as the container seal.

[0037] Some embodiments described herein relate to a medication management system for identifying and authenticating medications. For example, the medication management system may receive prescription information associated with a medication in a container. When the medication is in the container and the container is positioned on the container, the medication management system may cause a camera device to capture first image data associated with the medication.

[0038] The medication management system can cause an adjustment device to reposition the container on the receiver. For example, the adjustment device can push, shake, and / or vibrate the container to reposition the medication within the container. By repositioning the medication within the container, the medication management system increases the number of unique images captured of individual units of medication (e.g., tablets, pills, capsules, vials, etc.), thereby reducing the likelihood of medication accumulation (e.g., positioning of individual medication units such that multiple medication units appear as a single medication unit in a captured image).

[0039] When the medication is in the container, the medication management system may cause the camera device to capture second image data associated with the medication. The medication management system may process the first and second image data through a neural network to identify the medication based on descriptions of individual medication units included in the first and second image data. The medication management system may verify the medication based on the prescription information and the medication identifier provided by the neural network.

[0040] In this way, the medication management system provides a simple device for identifying and / or verifying medications (e.g., using simple components, such as a camera device). Furthermore, the medication management system provides similar accuracy in identifying and / or verifying medications as the complex devices described above. This reduces the need for complex components to facilitate identification and / or verification of medications.

[0041] In addition, the medication management system can obtain weight data associated with the medication and use the weight data to determine the amount of medication in the container. The medication management system can provide information identifying the amount of medication in the container to a pharmacist (e.g., to verify the amount of medication in the container, enable the pharmacist to refill the prescription, etc.), the individual receiving the medication, the primary caregiver (e.g., a family member), medical personnel, etc. In this way, the medication management system can implement bedside tracking capabilities for use in medical facilities (e.g., medical rooms that allow patients to self-administer medication), the ability to track medication consumption for caregivers (e.g., family members), etc.

[0042] Figure 1 FIG. 1 is a schematic diagram of an example implementation 100 associated with identifying and verifying a drug. Figure 1 As shown, an example implementation 100 includes a medication device and a medication management system. The medication device can be a communication and / or computing device and can include one or more containers (e.g., for holding a container), one or more camera devices (e.g., for obtaining image data regarding medication in the container), one or more container windows (e.g., for allowing one or more camera devices to observe the medication in the container and obtain image data), one or more weighing devices (e.g., for obtaining weight data regarding the medication in the container), one or more adjustment devices (e.g., for repositioning the medication in the container), and / or the like.

[0043] The medication management system can be a computing device, a server, a cloud computing device, etc. In some embodiments, the medication device and the medication management system can be connected via a network, such as a wired network (e.g., the Internet or other data network), a wireless network (e.g., a wireless local area network, a wireless wide area network, a cellular network, etc.), and / or the like.

[0044] Some example embodiments described herein relate to a single medication device in communication with a single medication management system. In some embodiments, multiple medication devices may communicate with one or more medication management systems. In some embodiments, one or more functions of a medication management system may be performed by the medication device instead of, or by, the medication management system. In some embodiments, one or more functions of a medication device may be performed by, or by, the medication management system instead of, or by the medication device.

[0045] In some embodiments, a pharmacist, a drug filling device, a pharmacist assisted by a drug filling device, etc. can fill the container with the drug according to the prescription. The container can be a tablet container, a capsule container, a tablet container, a bottle, a bottle and / or similar containers. The container can be transparent or translucent (e.g., allowing the drug to be seen from the outside of the container). The container can be filled with the drug and / or additional materials, such as a liner (e.g., cotton), a desiccant and / or similar materials. The prescription can be a written instruction for the doctor to prepare and administer the drug. The prescription may include information such as identifying the drug to be filled in the container, the drug dosage, the amount of drug to be filled in the container, at least one instruction for use of the drug, etc.

[0046] In some embodiments, after filling the container with the prescription, the pharmacist, drug filling device, and / or the like may apply a closure (e.g., a lid, cap, cork, and / or the like), a seal (e.g., a tamper-evident seal, an airtight seal, a sanitary seal, a safety seal, and / or the like), and / or the like to the container. Furthermore, the pharmacist, drug filling device, and / or the like may affix a label to the container that includes information, such as the information contained in the prescription, information about the pharmacy responsible for filling the prescription (e.g., the name, address, telephone number, email address, etc. of the pharmacy), information about the manufacturer of the drug (e.g., the name, address, telephone number, email address, etc. of the manufacturer), information about the patient for whom the drug was prescribed (e.g., the patient's name, address, telephone number, email address, etc.), an identifier associated with the prescription (e.g., an identification string, a barcode, a quick response (QR), etc.), information about the drug (e.g., a description of one or more characteristics of the drug), and / or the like.

[0047] In some embodiments, a user of a medical device, such as a pharmacist, patient, and / or the like, may wish to identify and / or verify the medication in a container and / or verify the integrity of the container seal. In some embodiments, a user may place a container within a container of a medical device to facilitate identification and / or verification of the medication in the container and / or verification of the integrity of the container seal.

[0048] As shown at 110, the medication device receives prescription information related to the medication in the container. The prescription information may include information included on the container label and / or information included in the prescription. For example, the prescription information may include a medication identifier, information identifying the medication dosage, information identifying the medication quantity, etc. The information identifying the medication quantity may include information identifying the medication quantity in the container, the weight of the medication unit (e.g., pill, capsule, tablet, etc.), the total weight of the medication excluding the container weight, the total weight of the medication including the container weight, etc.

[0049] In some embodiments, a user of a medical device can interact with the medical device to cause the medical device to retrieve prescription information. For example, the user can input information (e.g., an identification string associated with a prescription) into the medical device through a user interface of the medical device. The medical device can then perform a lookup in a data structure based on the identification string to obtain the prescription information.

[0050] As another example, a user can present a label of a container to a pharmaceutical device, such as by placing the label in the field of view of a camera device of one or more camera devices, and the pharmaceutical device can cause the camera device to obtain image data of the label. The pharmaceutical device can include one or more components that facilitate positioning the label within the field of view of the camera device (e.g., an arm that rotates the container so that the label points to the camera device, a guide device that positions the container in front of the camera device, etc.). The pharmaceutical device can process the image data using image processing techniques to determine a barcode and / or a QR code of the label. The pharmaceutical device can perform a search in a data structure based on the barcode and / or QR code to obtain prescription information.

[0051] As shown in the figure numeral 120, the medication management system obtains image data and weight data related to the medication. When the medication is in the container, the medication device can obtain image data related to the medication. The image data may include image data about the size, shape, color, pattern, shading, texture, label, brightness, etc. of at least one individual unit of the medication. In some embodiments, the medication device causes at least one camera device of the one or more camera devices to obtain image data. For example, the medication device can determine that the container has been placed in a container of one or more containers (e.g., based on receiving weight data from a weighing device of one or more weighing devices, as described in more detail below). Based on determining that the container has been placed in the container, the medication treatment device can cause at least one camera device to obtain image data.

[0052] The at least one camera device may obtain image data through at least one receptor window of one or more receptor windows (e.g., at least one receptor window associated with the receptor). The at least one container window may be configured to support the container while the at least one camera device acquires image data. The at least one container window may allow the at least one camera device to point to the bottom of the container, at least one side of the container, the top of the container, etc. to obtain image data. For example, the at least one camera device may be located below the receptor window, and the receptor window may be located within the field of view of the at least one camera device. As another example, when causing the at least one camera device to obtain image data, the medication device may cause the at least one camera device to determine when the container is within the field of view of the at least one camera device (e.g., when the at least one camera device captures preview image data, the camera device may identify the container using object identification software) and focus on the medication in the container (e.g., adjust the focus of the at least one camera device to focus on the medication).

[0053] In some embodiments, the medical device causes light to illuminate the container. For example, the medical device can be designed to allow ambient light to illuminate the container (e.g., through one or more container windows). As another example, the medical device can include one or more light sources that generate light (e.g., one or more light-emitting diodes, one or more incandescent light bulbs, one or more fluorescent lamps, etc.). The light can be associated with one or more colors (e.g., "white" light, "red" light, "blue" light, "yellow" light, etc.). When the container is illuminated by the light, the medical device can cause at least one camera device to obtain image data.

[0054] In some embodiments, the camera device includes a configuration component. The configuration component can be configured to control the amount of light illuminating the container, the color of the light illuminating the container, filter settings of the camera device, capture settings of the camera device, zoom settings of the camera device, and the like. Based on a message sent to the configuration component, the medical device can cause a light to illuminate the container. The message can include information identifying the amount of light to be emitted by one or more light sources, the color or wavelength of the light, filter settings, capture settings, zoom settings, and the like. The configuration component can cause the one or more light sources to illuminate the container and / or can cause the camera device to obtain image data based on the information contained in the message.

[0055] In some embodiments, a medical device captures a corresponding image of each of a plurality of containers placed in a plurality of containers of the medical device. In some embodiments, the medical device includes multiple camera devices. Each camera device in the plurality of cameras can be associated with a corresponding container in the plurality of containers. The medical device can cause each camera device to capture an image of the corresponding container placed in the corresponding container associated with each camera device in a manner similar to that described above. Alternatively and / or additionally, the medical device can cause a single camera device to capture a corresponding image of each container in the plurality of containers.

[0056] When the medication is in the container, the medication device can obtain weight data associated with the medication. The weight data can include weight data regarding the container, medication, container label, closure, seal, etc. In some embodiments, the medication device causes at least one of one or more weighing devices to obtain weight data. In some embodiments, at least one weighing device obtains weight information regarding the combined weight of the medication, container, container label, closure, seal, etc. The medication device can process the weight information (e.g., using a tare function) to determine weight data (e.g., to determine only the weight of the medication).

[0057] In some embodiments, the pharmaceutical device obtains corresponding weight data for a plurality of pharmaceutical containers. In some embodiments, the pharmaceutical device utilizes multiple weighing devices to obtain corresponding weight data for the plurality of pharmaceutical containers. Alternatively and / or additionally, the pharmaceutical device obtains combined weight data for the plurality of pharmaceutical containers. For example, the pharmaceutical device may utilize a single weighing device to obtain combined weight data associated with one or more containers, pharmaceutical contents, and optional container labels, closures, seals, etc., for each of the plurality of pharmaceutical containers.

[0058] In some embodiments, the medication device verifies the fill weight of the medication. The fill weight may correspond to the total weight of the medication, container, container label, closure, etc. The medication device may verify the fill weight based on a comparison between the fill weight determined from the weight data and the calculated fill weight. The medication device may determine the calculated fill weight based on the weight of the empty container and the weight of a single medication unit.

[0059] The medication device can determine the weight of an empty container. For example, the medication device can determine the weight of an empty container based on information input by a user through a user interface associated with the medication device, based on accessing a data structure (e.g., a database, table, list, etc.) storing weight information for containers of different types and / or sizes, based on a user placing an empty container into the container and obtaining weight data from one or more weighing devices, etc. The medication device can determine the weight of a single medication unit based on prescription information and / or based on accessing a data structure storing weight data for a single medication unit. The medication device can determine the number of units of medication contained in the container based on the prescription information. The medication device can calculate the total weight of the medication based on the number of units and the weight of the single medication unit (e.g., multiplying the weight of the single unit by the number of units). The medication device can determine a calculated fill weight based on the weight of the empty container and the total weight of the medication (e.g., adding the weight of the empty container to the total weight of the medication). The medication device can compare the calculated fill weight with the actual fill weight.

[0060] The medication device can verify the medication's fill weight based on a comparison of a calculated fill weight and an actual fill weight. For example, the medication device can verify the fill weight based on the calculated fill weight being the same as the actual fill weight, based on a difference between the calculated fill weight and the actual fill weight meeting a threshold amount, or the like. In some embodiments, the medication device provides a notification related to verifying the medication's fill weight. For example, the medication device can cause a message indicating that the medication's fill weight has been verified to be displayed via a user interface associated with the medication device. As indicated by reference numeral 130, the medication device repositions the container to obtain additional image data related to the medication. The medication device can include an adjustment device for repositioning the container on the container. For example, the adjustment device can vibrate, shake, and / or push the container to rearrange and / or reposition the medication within the container. In some embodiments, the adjustment device includes a vibration mechanism configured to move the container on the container. For example, the adjustment device can include one or more load cells positioned around the perimeter of the container window and configured to vibrate the container on the container. In some embodiments, the one or more load cells are connected to the medication device via corresponding load cell mounting members that provide a cantilever effect.

[0061] Based on obtaining initial image data and / or weight data related to the medication, the medication device may cause the adjustment device to reposition the container to rearrange and / or reposition the medication within the container. The medication device may cause the camera device to obtain additional image data based on the adjustment device repositioning the container.

[0062] In some embodiments, the medication device modifies a configuration setting of the at least one camera device before causing the at least one camera device to capture additional image data. For example, the medication device can adjust the polarization of the lens of the at least one camera device, the optical filter of the lens of the at least one camera device, the zoom setting of the at least one camera device, the wavelength of a light emitter associated with the at least one camera device, and the like. The medication device can adjust the polarization of the lens to reduce reflected light depicted in an image associated with the image data. The medication device can adjust the optical filter of the lens to filter a particular wavelength of light from an image associated with the image data. The medication device can adjust the zoom setting to adjust the field of view size of the at least one camera device. The medication device can adjust the wavelength of the light emitter to adjust a characteristic (e.g., color) of light in an image associated with the image data.

[0063] Alternatively, and / or additionally, the container window can include one or more adjustable filters. The pharmaceutical device can adjust the polarization lens, filter, lens, light emitter, and / or one or more adjustable filters before causing the at least one camera device to capture additional image data.

[0064] In some embodiments, while the medication is in the container, the medication device causes at least one camera device to capture a plurality of additional image data corresponding to a plurality of images of the medication. After the corresponding additional image data is captured by the at least one camera device, the medication device may iteratively process images from the plurality of images. Images may be acquired until the medication is identified in one of the plurality of images and / or until a predetermined number of images are acquired. As described in more detail below, the predetermined number may be associated with the configuration of a neural network used to process the image data.

[0065] In some embodiments, the medication device determines information about the medication based on the image data and / or weight data. For example, the medication device can process the image data and / or weight data to identify the medication, the dosage of the medication, the amount of medication in the container, etc.

[0066] As shown in the figure numeral 140, the medication device can process the image data to identify units of the medication. In some embodiments, the medication device processes the image data (e.g., the image data and the additional image data) using a machine learning model to identify units of the medication. For example, the medication device can process the image data and the additional image data using a neural network of a machine learning model to identify the medication based on descriptions of individual units of the medication contained in the image data and the additional image data. The neural network can include a convolutional neural network configured to segment the image data and the additional image data into descriptions of the individual units, determine a classification score for the description associated with identifying the medication based on corresponding individual units in the individual units, and identify the medication based on the classification score.

[0067] In some embodiments, the machine learning model includes an object detection model. The object detection model can process the image data and the additional image data to determine a plurality of bounding boxes corresponding to the locations of individual units within the image included in the image data and / or the additional image data. The medication device can segment the image to generate descriptions of the individual units based on the plurality of bounding boxes. The machine learning model can process one or more descriptions of the individual units to determine a classification score. For example, the medication device can select one or more descriptions of the individual units based on one or more features associated with the depiction of the individual units (e.g., the size of the individual units in the image, the number of individual units visible in the image, the location of the individual units in the image, etc.). The medication device can process the selected descriptions of the individual units to determine a classification score associated with the selected descriptions. The classification score can indicate a likelihood that the individual unit corresponds to an individual unit of a particular type of medication. The medication device can identify the medication as a particular type of medication based on the classification score. For example, the medication device can identify the medication as a particular type of medication based on a classification score that satisfies a classification score threshold.

[0068] Alternatively, and / or additionally, the medication management system can process the image data to identify units of medication. For example, the medication management system can process the image data using a machine learning model to identify units of medication in a manner similar to that described above. In some embodiments, the medication device and / or medication management system can process the image data in a manner similar to that described above to identify units of medication for each of the plurality of medication containers.

[0069] In some embodiments, the medication device generates and / or trains a machine learning model. For example, the medication device may obtain historical information about medication treatment, historical image data, and / or historical weight data (hereinafter collectively referred to as "historical information") to generate and / or train a machine learning model. In some embodiments, the medication device may process the historical information to train a machine learning model to identify medications, medication dosages, and medication amounts based on the image data and weight data, and / or in a manner similar to that described below with respect to Figure 3 The identification confidence level may be determined in a manner that is consistent with the method of FIG. The identification confidence level may indicate a level of prediction accuracy regarding the drug identity, drug dosage, drug quantity, etc. For example, a low identification confidence level may indicate a low level of prediction accuracy (e.g., less than a certain percentage of accuracy), a high identification confidence level may indicate a high level of prediction accuracy (e.g., greater than or equal to a certain percentage of accuracy), etc.

[0070] In some embodiments, a different device (e.g., a medication management system, a server device, etc.) generates and / or trains a machine learning model. The medication device can obtain the machine learning model from the different device. For example, the different device can send the machine learning model to the medication device (e.g., on a scheduled basis, on demand, based on a trigger, etc.).

[0071] As shown in the figure numeral 150, the medication device verifies the prescription based on the weight data and the image data. In some embodiments, the medication device verifies the medication based on the prescription information and the information about the medication. For example, if the identification, dosage, amount of medication, etc. of the medication contained in the information about the medication corresponds to the prescription information (e.g., matches, matches within a threshold, etc.), the medication device can determine that the medication has been verified. In addition, if the identification confidence level meets a threshold (e.g., is equal to or greater than a threshold), the medication device can confirm the verification of the medication. In addition, or alternatively, if the identification, dosage, amount of water of the medication, etc. contained in the information about the medication is inconsistent with the prescription information (e.g., does not match, is not within a threshold match, etc.), the medication device can determine that the medication has not been verified. In addition, if the identification confidence level does not meet a threshold (e.g., is less than a threshold), the medication device can determine that the medication has not been verified.

[0072] As another example, a medication device may verify a medication by determining that an identifier of the medication included in the prescription information matches an identifier of the medication included in the information about the medication, determining that a dosage of the medication identified in the prescription information matches a dosage of the medication identified in the information about the medication, and / or determining that a quantity of the medication identified in the prescription information corresponds within a threshold to a quantity of the medication identified in the information about the medication.

[0073] In some embodiments, the medication device may include information about the medication to determine whether the medication has been verified. In some embodiments, after determining whether the medication has been verified, the medication device may cause the machine learning model to be updated. For example, the medication device may cause the machine learning model to be updated (e.g., cause the machine learning model to be retrained) based on image data, weight data, prescription information, information about the medication, etc.

[0074] In some embodiments, the pharmaceutical device verifies the integrity of the seal of the container based on the verified drug. For example, the pharmaceutical device can obtain additional image data related to the seal of the container. In some embodiments, the pharmaceutical device can cause at least one camera device to obtain additional image data in a manner similar to the pharmaceutical device described above regarding obtaining image data. For example, the pharmaceutical device can determine that the container has been placed in the container and can cause at least one camera device to obtain additional image data. In some embodiments, the user can place the container upside down in the container to allow a specific camera device in one or more camera devices to obtain additional image data (for example, when the container is placed upside down, allowing a specific camera device to point upward through a container window at the bottom of the container). In some embodiments, the pharmaceutical device may include one or more components to facilitate positioning the sealing condition within the field of view of a specific camera device (for example, rotating the container so that the sealing condition points to the arm of the camera device, a guide device that positions the sealing condition in front of the camera device, etc.).

[0075] The medication device may determine information about the seal to verify the integrity of the seal. The medication device may determine information about the seal based on the additional image data. For example, the medication device may process the additional image data to determine information about the seal, which may include information about the integrity of the seal (e.g., whether the seal is intact, has one or more breaks, has one or more holes, shows signs of seal tampering, shows signs of seal failure, etc.).

[0076] In some implementations, the medical device may use a second machine learning model to determine information about the seal. In some implementations, the medical device may determine information about the seal in a manner similar to that described above and / or in a manner similar to that described below regarding Figure 3 A second machine learning model is received, generated, and / or trained in a similar manner. In some implementations, the medical device processes the additional image data to determine integrity issues with the seal and / or to determine an integrity confidence level. The integrity confidence level can indicate a level of predicted accuracy for the determination of the integrity issue. For example, a low integrity confidence level can indicate a low level of predicted accuracy (e.g., less than a certain percentage of accuracy), a high integrity confidence level can indicate a high level of predicted accuracy (e.g., greater than or equal to a certain percentage of accuracy), and so on.

[0077] The medical device may use a second machine learning model to determine whether the seal has an integrity issue based on the additional image data. In some implementations, after determining whether the seal has an integrity issue, the medical device may cause the second machine learning model to be updated. For example, the medical device may cause the second machine learning model to be updated (e.g., retrained) based on the additional image data, information about the seal, etc.

[0078] As shown in reference numeral 160, the medication device indicates whether the medication and / or seal have been verified. The medication device can generate a message about the medication and the seal. In some implementations, the medication device generates a message based on information about the medication and information about the seal. The message may include information, such as information indicating whether the medication has been verified, whether the integrity of the seal has been verified, etc. Alternatively and / or additionally, the message may include one or more instructions, such as instructions associated with how much medication the user of the medication device is to take, instructions associated with notifying the medication manufacturer of possible tampering with the medication and / or seal, etc. In some implementations, the message includes one or more warnings, such as a warning that the medication may be counterfeit, a warning that the integrity of the seal has been compromised, etc.; etc.

[0079] The medication device may cause the message to be presented (e.g., causing a display to present the message, causing a speaker to present the message, etc.). The medication device may present the message via a display of the medication device, a speaker device of the medication device, etc. For example, the medication device may generate voice data based on the message using text-to-speech technology, and cause the speaker of the medication device to emit the voice data.

[0080] In some implementations, the medication device causes different devices to present a message (e.g., causing a display of the different device to present a message, causing a speaker of the different device to present a message, etc.). For example, the medication device may determine an identifier (e.g., a phone number, an Internet Protocol (IP) address, etc.) of a different device (e.g., a user device of the patient, a client device of a pharmacy and / or manufacturer, etc.) based on the prescription information. The medication device may send a message to the different device based on the identifier of the different device. Based on the received message, the different device may display the message on a display of the different device and / or send the message via a speaker of the different device.

[0081] In some implementations, a user can use the medication device to facilitate the user removing an appropriate amount of medication from a container. For example, the user of the medication device can remove an amount of medication from a container after seeing and / or hearing a message, and place the container in a receptacle of the medication device to verify that the amount of medication is correct.

[0082] Thus, the pharmaceutical device may acquire further image data related to the pharmaceutical.For example, the pharmaceutical device may cause at least one camera device to acquire further image data in a similar manner as described above with respect to the pharmaceutical device acquiring image data and additional image data.

[0083] The medication device can obtain further weight data associated with the medication. In some implementations, the medication device causes at least one weighing device to obtain further weight data in a manner similar to that described above with respect to obtaining weight data associated with the medication device. For example, after a user places the container in a receptacle of the medication device, the medication device can cause at least one weighing device to obtain further weight data.

[0084] The medication device can determine the amount of medication removed from the container. In some implementations, the medication device processes further image data and further weight data in a manner similar to that described above to determine additional information about the medication to facilitate determining the amount of medication removed from the container. For example, the medication device can use a machine learning model to process the further image data and further weight data to identify the medication (e.g., to verify that the same medication is being analyzed) and the new amount of medication. The medication identification and verification platform can compare the new amount of medication with the amount of medication included in the information about the medication (e.g., the initial amount of medication before the user removed the medication from the container) to determine the amount of medication removed from the container. The medication device can include in the additional information about the medication information identifying the amount of medication removed from the container, information identifying the new amount of medication, information identifying the amount of medication, etc.

[0085] The medication device may generate an additional message about the medication based on the additional message about the medication. The additional message may include information such as whether the amount of medication removed from the container is correct, information about the amount of medication remaining in the container, and the like.

[0086] The medication device may cause presentation of additional messages (eg, cause a display to present the additional messages, cause a speaker to present the additional messages, etc.). In some implementations, the medication device causes the medication device and / or a different device to present the additional messages in a manner similar to that described above.

[0087] In some implementations, a user can use a medication device to facilitate the user removing an appropriate dose of medication from a plurality of containers. The user can place the plurality of containers into corresponding container receptacles of a plurality of container receptacles of the medication device. The medication device can verify that the user is removing an appropriate dose of medication from each of the plurality of containers in a manner similar to that described above.

[0088] In some implementations, the medication device is used to monitor the consumption of the medication. For example, the medication device may be located in a person's home and / or a medical facility (e.g., a medical facility and / or another type of facility that allows patients to self-administer medication), and the medication device may monitor the consumption of the medication to track the consumption of the medication, determine when to refill a prescription for the medication, automatically refill the prescription, etc.

[0089] In some implementations, the medication device monitors medication consumption based on determining the number of medication units contained in the container. In some implementations, the medication device can use the calculated fill weight to determine the number of medication units contained in the container. For example, the medication device can determine the number of medication units contained in the container by dividing the calculated fill weight by the weight of the individual medication units.

[0090] In some implementations, the medication device periodically monitors the consumption of the medication to determine whether the person is taking and / or being administered the medication according to the prescription. For example, the medication device can determine, based on prescription information, how often the person for whom the prescription is written takes and / or administers a certain amount of medication (e.g., every hour, every four hours, every day, twice a day, etc.). The medication device can periodically determine the number of units in the container based on how often the person takes and / or administers the medication. The medication device can compare the number of units with a previously determined number of units to determine whether the medication is being taken and / or administered to the person. The medication device can provide information indicating whether the medication is being taken and / or administered to the person to a client device (e.g., a client device associated with the person, a caregiver, a medical professional, a family member, etc.). In this way, the medication device can enable medical professionals, family members, caregivers, etc. to track the consumption of a person's medication.

[0091] In some implementations, the medication device determines that the medication is to be refilled based on the number of units in the container. For example, the medication device can determine that the number of units in the container meets a threshold number (e.g., a threshold number set by a pharmacist, a physician, a person, etc.). The medication device can determine that the medication is to be refilled based on the number of units meeting the threshold number.

[0092] In some implementations, the medication device can determine whether there are any refills remaining based on the prescription information. The medication device can provide information to a client device (e.g., a client device associated with a person, a client device associated with a pharmacist, etc.) indicating that the medication will be refilled when there are refills remaining.

[0093] In some implementations, the medication device automatically requests that the prescription be refilled when no refills remain. For example, the medication device may provide information requesting that the prescription be refilled, information identifying the number of units of medication remaining, information identifying the person for whom the prescription was written, information identifying a pharmacy to refill the prescription, etc. to a client device associated with a medical professional identified in the prescription information.

[0094] The medication management system records the verification of the medication and / or seal, as shown at 170. For example, the medication device may provide information as described herein to the medication management system. The medication management system may store information in a memory associated with the medication management system based on the information received from the medication device.

[0095] In some implementations, the information described herein can be obtained from and / or stored in a blockchain. A blockchain is a distributed database that maintains a continuously growing list of records, called blocks, that can be linked together to form a chain. Each block in a blockchain can contain information (e.g., timestamp, link, etc.) linking it to previous blocks and / or transactions in the blockchain. Blocks can be protected from tampering and modification. Furthermore, a blockchain can comprise a secure transaction ledger database shared by all parties participating in an established distributed computer network. A blockchain can record transactions (e.g., information exchanges or transmissions) occurring within the network, thereby reducing or eliminating the need for a trusted / centralized third party. Exemplary embodiments can employ either private (e.g., closed) or public (e.g., open) blockchain environments. In some cases, parties involved in a transaction may not know the identities of any other parties involved in the transaction, but can nonetheless securely exchange information. Furthermore, the distributed ledger can correspond to a record consistent with a cryptographic audit trail, maintained and verified by a set of independent computers.

[0096] For example, prescription information can be stored on a blockchain, and a medication device and / or medication management system can retrieve the prescription information from the blockchain. As another example, a medication device and / or medication management system can store prescription information, information about the medication, information about the seal, additional information about the medication, etc. on a blockchain. The blockchain can be accessed by one or more devices associated with manufacturing, filling, or dispensing medication. In this way, records regarding the integrity of the medication, seal, container, etc. can be updated by each entity that handles the medication, seal, container, etc.

[0097] Some example implementations described herein relate to medication devices that perform one or more functions (e.g., identifying and authenticating medication, verifying the integrity of a seal, determining the amount of medication removed from a container, etc.), although some implementations include medication management systems that perform one or more functions. For example, in some implementations, a medication device provides image data and additional image data to a medication management system, and the medication management system performs the full functionality of the one or more functions. Additionally or alternatively, some example implementations described herein relate to medication devices that generate and / or cause presentation of a message, although some implementations include a medication management system that generates and / or causes presentation of a message.

[0098] In this way, the drug device provides a simple device for identifying and / or verifying medicine (for example, utilizing uncomplicated components, such as camera equipment and weighing equipment). In addition, the drug device provides the accuracy for identifying and / or verifying medicine similar to the complex equipment discussed above. This reduces the demand for the complex assembly that is used to promote identification and / or verification of medicine. In addition, the drug device can send data to the drug management system for drug identification and verification platform to analyze data, which reduces the demand for a large amount of processing resources to be positioned at the position where medicine and / or container are analyzed, to promote identification and / or verification of medicine. In addition, the drug device uses the same, uncomplicated components that are used to promote identification and / or verification of medicine to promote the sealing integrity of container.

[0099] As indicated above, provide Figure 1 As an example. Other examples may differ from the Figure 1 Examples described. Figure 1 The number and arrangement of devices shown are provided as examples. Figure 1 There may be additional devices, fewer devices, different devices, or devices arranged differently than those shown. Figure 1 Two or more of the devices shown may be implemented in a single device, or Figure 1 The single device shown may be implemented as multiple distributed devices. Additionally, or alternatively, Figure 1 The illustrated set of devices (e.g., one or more devices) may perform the operations described as being performed by Figure 1 One or more functions performed by another set of devices are shown.

[0100] Figures 2A to 2B is a diagram of an exemplary medical device 200 as described herein. Figure 2A As shown, the medication device 200 can be a communication and / or computing device and can include one or more container receivers 210 (e.g., to accommodate one or more containers), one or more camera devices 220 (e.g., to acquire image data regarding medication in the container and / or the seal of the container), one or more receiver windows 230 (e.g., to facilitate the one or more camera devices 220 to acquire image data), a weighing device 240, an adjustment device 250, and / or an execution function (such as described above in conjunction with Figure 1 similar devices with the functions described).

[0101] like Figure 2BAs shown, the container receiver 210 of the one or more container receivers 210 may include a receiver window 230 of one or more receiver windows 230 in and / or on the container receiver 210. A camera device 220 of the one or more camera devices 220 may be included in the medication device 200 and directed toward the receiver window 230 to acquire image data of the medication in the container contained in the container receiver 210. The container receiver 210 and / or the receiver window 230 may be connected to and / or disposed on a scale device 240 of one or more weighing devices 240 of the medication device 200, which may acquire weight data regarding the medication in the container.

[0102] Likewise Figure 2B As shown, the medication device includes a window adjustment device 260 configured to modify configuration settings of at least one camera device 220 and / or a configuration of the receiver window 230. For example, the window adjustment device 260 can be configured to adjust the polarization of the lens of the at least one camera device 220, the optical filter of the lens of the at least one camera device 220, the zoom setting of the at least one camera device 220, the wavelength of the light emitter associated with the at least one camera device 220, etc. Alternatively and / or additionally, the receiver window 230 can include one or more adjustable filters, and the window adjustment device 260 can be configured to adjust the one or more adjustable filters.

[0103] As indicated above, provide Figures 2A to 2B As an example. Other examples may differ from the Figures 2A to 2B The example described. Figures 2A to 2B The number and arrangement of the devices shown are examples. Figures 2A to 2B There may be additional devices, fewer devices, different devices, or devices arranged differently than those shown. Figures 2A to 2B Two or more of the devices shown may be implemented in a single device, or Figures 2A to 2B The single device shown in may be implemented as multiple distributed devices. Additionally, or alternatively, Figures 2A to 2B The illustrated set of devices (e.g., one or more devices) may perform the operations described as being performed by Figures 2A to 2B One or more functions performed by another set of devices is shown.

[0104] Figure 3 3 is a diagram illustrating an example 300 of training and using a machine learning model for identifying and verifying medications. The machine learning model training and use described herein can be performed using a machine learning system. The machine learning system can include or be included in a computing device, server, cloud computing environment, etc., such as a medication management system described in more detail elsewhere herein.

[0105] As shown at reference numeral 305, a machine learning model can be trained using an observation set. The observation set can be obtained from training data (e.g., historical data), such as data collected during one or more processes described herein. In some implementations, the machine learning system can receive the observation set (e.g., as input) from a medication management system, as described elsewhere herein.

[0106] As shown in the reference numeral 310, the observation set includes a feature set. A feature set may include a set of variables, and the variables may be referred to as features. A particular observation may include a set of variable values (or feature values) corresponding to the variable set. In some implementations, the machine learning system may determine the variables for the observation set and / or the variable values for a particular observation based on input received from the medication management system. For example, the machine learning system may identify the feature set (e.g., one or more features and / or feature values) by extracting the feature set from structured data, by performing natural language processing to extract the feature set from unstructured data, and / or by receiving input from an operator.

[0107] As an example, a feature set for an observation set may include a first feature of a first image configuration (e.g., Figure 3 The image configuration 1 shown), the second feature of the second image configuration (e.g., Figure 3 The image configuration 2 shown), the third feature of the third image configuration (for example, Figure 3 Different image configurations may be associated with repositioning the container, repositioning the camera device, adjusting the amount of light shining on the container, adjusting camera device settings (e.g., filter settings, focus settings, etc.), etc. As shown, for a first observation, a first feature may have a value of a first image configuration identifier (e.g., Figure 3 Img1.1 shown), the second feature may have a value of a second image configuration identifier (e.g., Figure 3 Img1.2 shown), the third feature may have a value of a third image configuration identifier (e.g., Figure 3 Img1.3 shown), etc. These features and feature values are provided as examples and may be different in other examples.

[0108] As shown in reference numeral 315, the set of observations can be associated with a target variable. The target variable can represent a variable having a numeric value, can represent a variable having a numeric value that falls within a range of values or has some discrete possible values, can represent a variable that is selectable from one of a plurality of options (e.g., one of a plurality of categories, classifications, or labels), and / or can represent a variable having a Boolean value. The target variable can be associated with a target variable value, and the target variable value can be specific to the observation. In example 300, the target variable is a confidence score (e.g., a confidence score, such as Figure 3 ), which has a value of 0.8 (eg, 80%) for the first observation. Alternatively and / or additionally, the target variable may be an identity of a drug associated with the observation.

[0109] The target variable can represent the value that the machine learning model is being trained to predict, and the feature set can represent the variables that are input to the trained machine learning model to predict the value for the target variable. The observation set can also include target variable values, so that the machine learning model can be trained to identify patterns in the feature set that lead to target variable values. A machine learning model trained to predict target variable values can be referred to as a supervised learning model.

[0110] In some implementations, a machine learning model can be trained on an observation set that does not include a target variable. This can be referred to as an unsupervised learning model. In this case, the machine learning model can learn patterns from the observation set without labeling or supervision and can provide output that indicates such patterns, such as by using clusters and / or associations to identify groups of related items within the observation set.

[0111] As shown at 320, the machine learning system can use the set of observations and train a machine learning model using one or more machine learning algorithms, such as a regression algorithm, a decision tree algorithm, a neural network algorithm, a k-nearest neighbor algorithm, a support vector machine algorithm, etc. After training, the machine learning system can store the machine learning model as a trained machine learning model 325, which is used to analyze new observations.

[0112] As shown at reference numeral 330, the machine learning system can apply the trained machine learning model 325 to a new observation, such as by receiving the new observation and inputting the new observation into the trained machine learning model 325. As shown, as an example, the new observation can include a first feature of a first image configuration (e.g., Figure 3 The image configuration 1 shown), the second feature of the second image configuration (e.g., Figure 3 The image configuration 2 shown), the third feature of the third image configuration (for example, Figure 3The machine learning system can apply the trained machine learning model 325 to the new observation to generate an output (e.g., a result). The type of output can depend on the type of machine learning model and / or the type of machine learning task being performed. For example, the output can include a predicted value of a target variable, such as when supervised learning is employed. Additionally, or alternatively, the output can include information identifying the cluster to which the new observation belongs and / or information indicating the similarity between the new observation and one or more other observations, such as when unsupervised learning is employed.

[0113] As an example, the trained machine learning model 325 may predict a value of 0.9 for the target variable for a confidence score for the new observation, as shown at 335. Based on the prediction, the machine learning system may provide a first recommendation, may provide a determined output for the first recommendation, may perform a first automatic action, and / or may cause the first automatic action to be performed (e.g., by instructing another device to perform the automatic action), among other examples.

[0114] In some implementations, the trained machine learning model 325 can classify new observations in clusters (e.g., clusters), as shown in reference numeral 340. The observations within the clusters can have a threshold similarity. As an example, if the machine learning system classifies the new observation in a first cluster (e.g., a high confidence score cluster), the machine learning system can provide a first recommendation. Additionally, or alternatively, the machine learning system can perform a first automatic action based on classifying the new observation in the first cluster and / or can cause the first automatic action to be performed (e.g., by instructing another device to perform the automatic action).

[0115] As another example, if the machine learning system classifies the new observation in a second cluster (e.g., a low confidence score cluster), the machine learning system can provide a second (e.g., different) recommendation and / or can perform or cause the performance of a second (e.g., different) automatic action.

[0116] In some implementations, recommendations and / or automatic actions associated with a new observation can be based on a target variable value having a particular label (e.g., a classification or categorization), can be based on whether the target variable value satisfies one or more thresholds (e.g., whether the target variable value is greater than a threshold, less than a threshold, equal to a threshold, falls within a threshold range, etc.), and / or can be based on the cluster into which the new observation is classified.

[0117] In this way, the machine learning system can apply a rigorous and automated process to identify and verify drugs. The machine learning system enables the recognition and / or identification of tens, hundreds, thousands, or millions of features and / or tens, hundreds, thousands, or millions of observed feature values, thereby improving accuracy and consistency and reducing delays associated with identifying and verifying drugs relative to the need to allocate computing resources to tens, hundreds, or thousands of operators to manually identify and verify drugs using the features or feature values.

[0118] As mentioned above, providing Figure 3 As an example. Other examples may be different from combining Figure 3 Examples described.

[0119] Figure 4 is a diagram of an example environment 400 in which the systems and / or methods described herein may be implemented. Figure 4 As shown, environment 400 may include a healthcare management system 401, which may include one or more elements within a cloud computing system 402 and / or one or more elements that may be executed within the cloud computing system 402. The cloud computing system 402 may include one or more elements 403 to 413, as described in more detail below. Figure 4 As further shown, environment 400 may include network 420 and medication device 430. The devices and / or elements of environment 400 may be interconnected via wired and / or wireless connections.

[0120] Cloud computing system 402 includes computing hardware 403, a resource management component 404, a host operating system (OS) 405, and / or one or more virtual computing systems 406. Resource management component 404 can perform virtualization (e.g., abstraction) of computing hardware 403 to create one or more virtual computing systems 406. Using virtualization, resource management component 404 enables a single computing device (e.g., a computer, server, etc.) to operate as multiple computing devices, such as by creating multiple isolated virtual computing systems 406 from the computing hardware 403 of a single computing device. In this manner, computing hardware 403 can operate more efficiently than using separate computing devices, with lower power consumption, higher reliability, higher availability, higher utilization, greater flexibility, and lower cost.

[0121] Computing hardware 403 includes hardware and corresponding resources from one or more computing devices. For example, computing hardware 403 may include hardware from a single computing device (e.g., a single server) or from multiple computing devices (e.g., multiple servers), such as multiple computing devices in one or more data centers. As shown, computing hardware 403 may include one or more processors 407, one or more memories 408, one or more storage components 409, and / or one or more networking components 410. Examples of processors, memories, storage components, and networking components (e.g., communication components) are described elsewhere herein.

[0122] Resource management component 404 includes a virtualization application (e.g., executed on hardware such as computing hardware 403) capable of virtualizing computing hardware 403 to start, stop, and / or manage one or more virtual computing systems 406. For example, resource management component 404 may include a hypervisor (e.g., a bare metal or first-class hypervisor, a hosted or second-class hypervisor, etc.) or a virtual machine monitor, such as when virtual computing system 406 is a virtual machine 411. Additionally or alternatively, resource management component 404 may include a container manager, such as when virtual computing system 406 is a container 412. In some implementations, resource management component 404 executes within and / or in coordination with host operating system 405.

[0123] The virtual computing system 406 includes a virtual environment that uses computing hardware 403 to enable the execution of cloud-based operations and / or the processes described herein. As shown, the virtual computing system 406 may include virtual machines 411, containers 412, a hybrid environment 413 including virtual machines and containers, etc. The virtual computing system 406 can execute one or more applications using a file system including binary files, software libraries, and / or other resources required to execute applications on a guest operating system (e.g., within the virtual computing system 406) or a host operating system 405.

[0124] Although the healthcare management system 401 may include one or more elements 403 to 413 of the cloud computing system 402, may be executed within the cloud computing system 402, and / or may be hosted within the cloud computing system 402, in some implementations, the healthcare management system 401 may not be cloud-based (e.g., may be implemented outside of the cloud computing system), or may be partially cloud-based. For example, the healthcare management system 401 may include one or more devices that are not part of the cloud computing system 402, such as Figure 5 The device 500 may include a standalone server or another type of computing device. The healthcare management system 401 may perform one or more operations and / or processes described in more detail elsewhere herein.

[0125] The network 420 includes one or more wired and / or wireless networks. For example, the network 420 may include a cellular network, a public land mobile network (PLMN), a local area network (LAN), a wide area network (WAN), a private network, the Internet, etc., and / or a combination of these or other types of networks. The network 420 enables communication between devices in the environment 400.

[0126] The medication device 430 includes one or more devices capable of receiving, generating, storing, processing, and / or providing information (such as the information described herein). For example, the medication device 430 may include a computer (e.g., a desktop computer, a laptop computer, a tablet computer, a handheld computer, a server device, etc.), a mobile phone (e.g., a smartphone, a wireless phone, etc.), an Internet of Things (IoT) device or smart application, or the like. In some implementations, the medication device 430 may include one or more components, such as one or more receivers for holding a container filled with medication, one or more camera devices for capturing image data related to the medication and / or the container's seal, one or more receiver windows for facilitating the one or more camera devices to capture image data, one or more scales for capturing weight data related to the medication, etc. In some implementations, the medication device 430 may receive information from and / or transmit information to the medication management system 401, etc.

[0127] Figure 4 The number and arrangement of devices and networks shown are provided as examples. Figure 4 There may be additional devices and / or networks, fewer devices and / or networks, different devices and / or networks, or differently arranged devices and / or networks than those shown. Figure 4 Two or more of the devices shown may be implemented in a single device, or Figure 4 The single device shown may be implemented as multiple distributed devices. Additionally or alternatively, a set of devices (eg, one or more devices) of environment 400 may perform one or more functions described as being performed by another set of devices of environment 400.

[0128] Figure 5 is a diagram of example components of a device 500, which may correspond to medication management system 401 and / or medication device 430. In some implementations, medication management system 401 and / or medication device 430 may include one or more devices 500 and / or one or more components of device 500. Figure 5 As shown, device 500 may include a bus 510 , a processor 520 , a memory 530 , a storage component 540 , an input component 550 , an output component 560 , and a communication component 570 .

[0129] The bus 510 includes components that enable wired and / or wireless communication between components of the device 500. The processor 520 includes a central processing unit, a graphics processing unit, a microprocessor, a controller, a microcontroller, a digital signal processor, a field programmable gate array, an application-specific integrated circuit, and / or other types of processing components. The processor 520 is implemented in hardware, firmware, or a combination of hardware and software. In some implementations, the processor 520 includes one or more processors that can be programmed to perform functions. The memory 530 includes random access memory, read-only memory, and / or other types of memory (e.g., flash memory, magnetic memory, and / or optical memory).

[0130] The storage component 540 stores information and / or software related to the operation of the device 500. For example, the storage component 540 may include a hard disk drive, a magnetic disk drive, an optical disk drive, a solid-state disk drive, an optical disk, a digital versatile disk, and / or other types of non-transitory computer-readable media. The input component 550 enables the device 500 to receive input, such as user input and / or sensed input. For example, the input component 550 may include a touch screen, a keyboard, a keypad, a mouse, buttons, a microphone, a switch, a sensor, a global positioning system component, an accelerometer, a gyroscope, and / or an actuator. The output component 560 enables the device 500 to provide outputs, such as via a display, a speaker, and / or one or more light-emitting diodes. The communication component 570 enables the device 500 to communicate with other devices, such as via a wired connection and / or a wireless connection. For example, the communication component 570 may include a receiver, a transmitter, a transceiver, a modem, a network interface card, and / or an antenna.

[0131] The device 500 can perform one or more processes described herein. For example, a non-transitory computer-readable medium (e.g., memory 530 and / or storage component 540) can store an instruction set (e.g., one or more instructions, codes, software codes, and / or program codes) for execution by the processor 520. The processor 520 can execute the instruction set to perform one or more processes described herein. In some implementations, the instruction set executed by the one or more processors 520 causes the one or more processors 520 and / or the device 500 to perform one or more processes described herein. In some implementations, hard-wired circuitry can be used in place of instructions or in combination with instructions to perform one or more processes described herein. Therefore, the implementations described herein are not limited to any particular combination of hardware circuitry and software.

[0132] Figure 5 The number and arrangement of components shown are provided as examples. Figure 5, device 500 may include additional components, fewer components, different components, or components arranged differently than those shown in FIG. Additionally or alternatively, a set of components (e.g., one or more components) of device 500 may perform one or more functions described as being performed by another set of components of device 500.

[0133] Figure 6 is a flow chart of an example process 600 associated with identification and verification of a medication. In some implementations, Figure 6 One or more process blocks of can be performed by a device (e.g., medication management system 401). In some implementations, Figure 6 One or more process blocks of may be performed by another device or device group (e.g., medication device 430) that is separate from or includes the device. Additionally or alternatively, Figure 6 One or more processing blocks of may be performed by one or more components of device 500 , such as processor 520 , memory 530 , storage component 540 , input component 550 , output component 560 , and / or communication component 570 .

[0134] like Figure 6 As shown, process 600 may include receiving prescription information associated with the medication in the container (block 610). For example, as described above, the device may receive prescription information associated with the medication in the container. The prescription information may include an identifier for the medication, information identifying a dosage of the medication, and / or information identifying an amount of the medication. The information identifying the amount of the medication may include information identifying the amount of medication in the container, the weight of a unit of medication (e.g., a pill, capsule, tablet, etc.), the total weight of the medication excluding the weight of the container, the total weight of the medication including the weight of the container, and the like.

[0135] As in Figure 6 As further shown in FIG6 , process 600 may include causing a camera device to capture first image data associated with the medication while the medication is in the container and the container is positioned on the receiver (block 620). For example, as described above, the device may cause the camera device to capture first image data associated with the medication while the medication is in the container and the container is positioned on the receiver. The receiver may include a receiver window configured to support the container while the camera device captures the image data. The camera device may be positioned below the receiver window, and the receiver window may be within a field of view of the camera device.

[0136] like Figure 6 As further shown, process 600 may include causing the adjustment device to reposition the container on the receiver (block 630). For example, as described above, the device may cause the adjustment device to reposition the container on the receiver. In some implementations, the adjustment device includes a vibration mechanism configured to move the container on the receiver.

[0137] As in Figure 6 As further shown in FIG6 , process 600 may include causing a camera device to capture second image data associated with the medication while the medication is in the container (block 640). For example, as described above, the device may cause the camera device to capture second image data associated with the medication while the medication is in the container. In some implementations, before causing the camera device to capture the second image data, the device may adjust the polarization of a lens of the camera device, an optical filter of the lens of the camera device, a zoom setting of the camera device, and / or a wavelength of a light emitter associated with the camera device. For example, the device may include a polarizing lens configured to reduce reflected light depicted in an image associated with the image data, an optical filter configured to filter specific wavelengths of light from the image associated with the image data, a lens configured to adjust a field of view size, and / or a light emitter configured to adjust light characteristics in the image associated with the image data. Alternatively and / or additionally, the receiver window may include one or more adjustable filters. Before causing the camera device to capture the second image data, the device may adjust the polarizing lens, the optical filter, the lens, the light emitter, and / or the one or more adjustable filters.

[0138] In some implementations, when the medication is in the container, the device may cause the camera device to capture a plurality of second image data corresponding to a plurality of images associated with the medication. After the corresponding second image data is captured by the camera device, the device may iteratively process images from the plurality of images. The plurality of images may be acquired until the medication is identified in the plurality of images and / or until a predetermined number of the plurality of images is acquired. The predetermined number may be associated with the configuration of the neural network.

[0139] As in Figure 6 As further shown in FIG6 , process 600 may include processing the first image data and the second image data via a neural network to identify a medication based on descriptions of individual medication units contained in the first image data and the second image data (block 650). For example, as described above, the device may process the first image data and the second image data via a neural network to identify a medication based on descriptions of individual medication units contained in the first image data and the second image data. The neural network may include a convolutional neural network configured to segment the first image data and the second image data into descriptions of individual units, determine a classification score for the description associated with identifying the medication based on corresponding units in the individual units, and / or identify the medication based on the classification score.

[0140] like Figure 6As further shown, process 600 may include verifying the medication based on the prescription information and the identifier of the medication provided by the neural network (block 660). For example, as described above, the device may verify the medication based on the prescription information and the identifier of the medication provided by the neural network. In some implementations, the device causes a weighing device to obtain weight data associated with the medication while the medication is within the container. The device may verify the medication based on the prescription information, the identifier, and the weight data.

[0141] As in Figure 6 As further shown in FIG6 , process 600 may include performing an action associated with indicating that the medication is verified according to the prescription information (block 670). For example, as described above, the device may perform an action associated with indicating that the medication is verified according to the prescription information. In some implementations, performing the action may include the device indicating via a display that the medication has been verified and / or providing a notification to the medication management system that the medication associated with the prescription information has been verified.

[0142] although Figure 6 Example blocks of process 600 are shown, but in some implementations, Figure 6 Process 600 may include additional blocks, fewer blocks, different blocks, or blocks in a different arrangement than those described in

[0066] Additionally, or alternatively, two or more blocks of process 600 may be performed in parallel.

[0143] The foregoing disclosure provides illustration and description, but is not intended to be exhaustive or to limit the embodiments to the precise form disclosed. Modifications may be made in light of the above disclosure or may be acquired from practice of implementation.

[0144] As used herein, the term "component" is intended to be broadly interpreted as hardware, firmware, or a combination of hardware and software. Obviously, the systems and / or methods described herein can be implemented in different forms of hardware, firmware, and / or a combination of hardware and software. The actual dedicated control hardware or software code used to implement these systems and / or methods does not limit the implementation. Therefore, the operation and behavior of the systems and / or methods described herein are described without reference to specific software code. It should be understood that, based on the description herein, software and hardware can be used to implement the systems and / or methods.

[0145] As used herein, satisfying a threshold may refer to a value that is greater than a threshold, greater than or equal to a threshold, less than or equal to a threshold, equal to a threshold, not equal to a threshold, etc., depending on the context.

[0146] Although particular combinations of features are listed in the claims and / or disclosed in the specification, these combinations are not intended to limit the disclosure of the various embodiments. In fact, many of these features may be combined in ways not specifically listed in the claims and / or disclosed in the specification. Although each dependent claim listed below may directly depend on only one claim, the disclosure of the various embodiments includes the combination of each dependent claim with every other claim in the claim set. As used herein, a phrase referring to "at least one" of a list of items refers to any combination of those items, including single members. As an example, "at least one of a, b, or c" is intended to cover a, b, c, ab, ac, bc, and abc, as well as any combination with multiples of the same item.

[0147] Unless expressly stated otherwise, no element, action, or instruction used in this Agreement should be construed as critical or essential. In addition, as used herein, “a” and “an” are intended to include one or more items and can be used interchangeably with “one or more”. In addition, as used herein, the term “the” is intended to include one or more items related to the term “the” and can be used interchangeably with “the one or more items”. In addition, the term “set” as used herein is intended to include one or more items (e.g., related items, unrelated items, or a combination of related and unrelated items) and can be used interchangeably with “one or more”. If only one item is intended to be used, the phrase “only one” or similar language is used. In addition, the terms “having,” “having,” “having,” etc. used herein are intended to be open-ended terms. In addition, the term “based on” is intended to mean “based at least in part on,” unless otherwise expressly stated. In addition, unless otherwise expressly stated (e.g., if used in conjunction with “any one” or “only one of them”), the term “or” used herein should be inclusive when used in a series and can be used interchangeably with “and / or.”

Claims

1. A method for identifying and authenticating a drug, comprising: receiving, by the device, prescription information associated with the medication in the container; causing, by the device, a camera device to capture first image data associated with the medication while the medication is in the container and the container is positioned on a receiver; causing, by the device, an adjustment device to reposition the container on the receiver, wherein the adjustment device pushes, shakes, and / or vibrates the container to reposition the medication within the container to increase the number of unique images captured for the individual unit; while the medication is in the container, causing the camera device to capture, by the device, second image data associated with the medication; processing, by the device, the first image data and the second image data via a neural network to identify the medication based on descriptions of individual units of the medication included in the first image data and the second image data; verifying, by the device, the medication based on the prescription information and an identifier of the medication provided by the neural network; as well as An action is performed by the device, the action associated with indicating that the medication is authenticated according to the prescription information.

2. The method according to claim 1, wherein the prescription information includes at least one of the following: an identifier for the medication; Information identifying the dosage of the medication; or Information identifying the quantity of the medication.

3. The method according to claim 1, wherein The adjustment device includes a vibration mechanism configured to move the container on the receptacle.

4. The method according to claim 1, further comprising: causing a weighing device to obtain weight data associated with the medication while the medication is within the container, Wherein the medication is authenticated based on the prescription information, the identifier and the weight data.

5. The method of claim 1 , wherein the neural network comprises a convolutional neural network, the neural network configured to at least one of: segmenting the first image data and the second image data into said description of said individual units; determining a classification score for the description associated with identifying the drug based on corresponding ones of the individual units; and The drug is identified based on the classification score.

6. The method according to claim 1, further comprising: Before causing the camera device to capture the second image data, adjusting at least one of the following: polarization of a lens of the camera device; a filter for a lens of the camera device; the zoom setting of the camera device; or The wavelength of the light emitter associated with the camera device.

7. The method of claim 1 , wherein performing the action comprises: indicating via a display that the medication is authenticated; or A notification is provided to the medication management system that the medication is verified in association with the prescription information.

8. A device for identifying and authenticating a drug, comprising: one or more memories; as well as one or more processors communicatively coupled to the one or more memories, the one or more processors configured to: receiving prescription information associated with a medication in a container, wherein the container is positioned on a receiver of the device; Multiple images of the drug are acquired by iteratively performing the following process: adjusting the container on the receiver via an adjustment device to attempt to reposition individual units of the medication within the container, wherein the adjustment device pushes, shakes, and / or vibrates the container to reposition the medication within the container to increase the number of unique images captured for the individual units, and capturing, via a camera device, image data associated with the medication while the medication is in the container; processing the plurality of images via a neural network to identify the medication based on one or more descriptions of cells in the individual cells; verifying the medication based on the prescription information and an identifier of the medication on the unit; as well as An action is performed, the action associated with indicating that the medication is verified according to the prescription information.

9. The apparatus according to claim 8, wherein The prescription information includes at least one of the following: said identifier of said medication; Information identifying the dosage of the medication; or Information identifying the quantity of the medication.

10. The apparatus according to claim 8, wherein the receiver comprising a receiver window configured to support the container while the camera device captures the image data, Wherein the camera device is positioned below the receiver window and the receiver window is within the field of view of the camera device.

11. The apparatus according to claim 8, wherein images of the plurality of images are iteratively processed after corresponding image data is captured via the camera device, wherein the image of the plurality of images is acquired until at least one of: The drug is identified in an image in the plurality of images, or A predetermined number of the plurality of images are acquired.

12. The apparatus of claim 8, wherein images of the plurality of images are iteratively acquired until a predetermined amount of the plurality of images are acquired, in, The predetermined amount is associated with a configuration of the neural network.

13. The apparatus according to claim 8, wherein The one or more processors, when performing the actions, are configured to: indicating via a display that the medication is authenticated; or A notification is provided to the medication management system that the medication is verified in association with the prescription information.

14. A drug analysis system for identifying and verifying drugs, comprising: a receiver configured to support a container on the receiver window; a camera device positioned below the receiver window and configured with the receiver window within a field of view of the camera; an adjustment device configured to move the receiver to adjust the position of the medication in the container, wherein the adjustment device pushes, shakes, and / or vibrates the container to reposition the medication within the container to increase the number of unique images captured for an individual unit; and A control device, the control device being configured to: The medication in the container is identified by the following process: causing the adjustment device to reposition the container on the receiver, causing the camera device to capture image data associated with the medication processing the image data via a neural network to identify the drug; as well as An action associated with identifying the medication is performed.

15. The pharmaceutical analysis system of claim 14, wherein the receiver window comprises one or more adjustable filters.

16. The drug analysis system according to claim 14, wherein: The adjustment device includes a vibration mechanism configured to move the container on the receptacle.

17. The drug analysis system according to claim 14, wherein: The neural network includes a convolutional neural network configured to: segmenting the image data into individual units of description of the drug; determining a classification score for the description associated with identifying the drug based on corresponding ones of the individual units; and The drug is determined based on the classification score.

18. The drug analysis system according to claim 14, further comprising at least one of the following: a polarizing lens configured to reduce reflected light depicted in an image associated with the image data; a filter configured to filter light of a particular wavelength from an image associated with the image data; a lens configured to adjust the size of the field of view; or A light emitter is configured to adjust characteristics of light in an image associated with the image data.

19. The drug analysis system according to claim 14, wherein: When performing the actions, the control device is configured to: obtaining prescription information associated with the drug; verifying the medication based on the prescription information and an identifier of the medication identified by the neural network in the image data; as well as A notification is provided via a display or to a medication management system that the medication is verified in association with the prescription information.

20. The drug analysis system according to claim 19, further comprising: a weighing device associated with the receiver, the weighing device being configured to obtain weight data associated with the medication, Wherein, the control device is further configured to: causing the weighing device to obtain weight data associated with the medication while the medication is within the container, Wherein the medication is authenticated based on the prescription information, the identifier and the weight data.

Images