US-20260127898-A1 - APPARATUS FOR ACQUIRING STOCK INFORMATION OF MEDICINES AND METHOD THEREOF

US20260127898A1US 20260127898 A1US20260127898 A1US 20260127898A1US-20260127898-A1

Abstract

According to the present disclosure, disclosed is a method of acquiring information by an electronic apparatus, which includes acquiring a target image, identifying one or more medicines included in the target image, and acquiring, based on a result obtained by identifying the one or more medicines, stock information for each medicine type included in the target image.

Inventors

Sung An Byun

Assignees

Sung An Byun

Dates

Publication Date: 20260507
Application Date: 20251103
Priority Date: 20241106

Claims (20)

1 . A method of acquiring information from an electronic apparatus, the method comprising: acquiring a target image; identifying one or more medicines included in the target image; and acquiring, based on a result obtained by identifying the one or more medicines, stock information for each medicine type included in the target image.
2 . The method of claim 1 , wherein the identifying of the one or more medicines comprises: identifying one or more feature components included in the target image; and acquiring type information of a medicine related to a first feature component included in the one or more feature components.
3 . The method of claim 2 , wherein the acquiring of the type information of the medicine related to the first feature component comprises comparing the first feature component with one or more comparative images.
4 . The method of claim 3 , wherein the comparing of the first feature component with the one or more comparative images comprises: inputting the first feature component and the one or more comparative images to a pre-trained machine learning model; and acquiring an output of the machine learning model, and wherein the machine learning model is pre-trained based on a plurality of medicine images.
5 . The method of claim 3 , wherein the comparing of the first feature component with the one or more comparative images comprises: determining one or more attributes related to the first feature component; and selecting, based on the one or more attributes, the one or more comparative images from a plurality of images included in a medicine image group.
6 . The method of claim 5 , wherein the determining of the one or more attributes comprises identifying logo information included in the first feature component.
7 . The method of claim 2 , wherein the acquiring of the type information of the medicine related to the first feature component comprises: acquiring gradient information related to the first feature component; and rotating the first feature component based on the gradient information.
8 . The method of claim 2 , wherein the acquiring of the type information of the medicine related to the first feature component comprises: acquiring distortion information related to the first feature component; and correcting the first feature component based on the distortion information, and wherein the correcting of the first feature component comprises performing warping for the first feature component.
9 . The method of claim 1 , further comprising acquiring photographing environment information of the target image, wherein the identifying of the one or more medicines comprises transforming the target image based on the photographing environment information.
10 . The method of claim 9 , wherein the photographing environment information includes one or more pieces of: product information of a camera for photographing the target image, setting information of the camera when the target image is photographed, distance information between the camera and a target to be photographed when the target image is photographed, and angle information between the camera and the target to be photographed when the target image is photographed.
11 . The method of claim 1 , wherein the acquiring of the stock information comprises: determining types of the plurality of medicines existing in a space corresponding to the target image; and acquiring position information of the plurality of medicines.
12 . The method of claim 1 , further comprising acquiring, based on the stock information, three-dimensional (3D) modeling information corresponding to the target image.
13 . The method of claim 12 , wherein the acquiring of the 3D modeling information comprises: generating one or more geometric models corresponding to at least a portion of the plurality of medicines existing in a space corresponding to the target image; and performing a texture mapping process for the one or more geometric models.
14 . The method of claim 1 , further comprising acquiring storage environment information of the one or more medicines, and wherein the electronic apparatus acquires the stock information based on the storage environment information.
15 . The method of claim 14 , wherein the storage environment information includes one or more pieces of attribute information related to a storage part for storing the one or more medicines, and wherein the one or more pieces of attribute information include one or more pieces of: information for product identification of the storage part, shape information of the storage part, size information of the storage part, and volume information of the storage part.
16 . The method of claim 14 , further comprising acquiring, based on the storage environment information and the stock information, suggestion information related to a storage method of the one or more medicines.
17 . The method of claim 1 , further comprising comparing the stock information with pre-existing computerized stock information.
18 . The method of claim 17 , further comprising notifying a discrepancy when there is the discrepancy between the stock information and the pre-existing computerized stock information.
19 . A non-transitory computer-readable recording medium recording a program for executing the method of claim 1 in a computer.
20 . An electronic apparatus acquiring information, the electronic apparatus comprising: a memory configured to store an instruction and a processor, wherein the processor, which is connected to the memory, is configured to: acquire a target image; identify one or more medicines included in the target image; and acquire, based on a result obtained by identifying the one or more medicines, stock information for each medicine type included in the target image.

Description

CROSS-REFERENCE TO RELATED APPLICATION(S) This application claims the benefit of Korean Patent Application No. 10-2024-0156007, filed on Nov. 6, 2024, in the Korean Intellectual Property Office, the disclosure of which is incorporated herein by reference. BACKGROUND 1. Field of the Invention The present disclosure relates to an apparatus for acquiring stock information of medicines and a method thereof. More specifically, the present disclosure relates to an electronic apparatus, which identifies one or more medicines included in an acquired target image and acquires, based on a result of the identification, stock information for each medicine type included in the target image, and a method thereof. 2. Description of the Related Art In the case of medicines, it is particularly required to manage stock thoroughly due to their characteristics, such as a point in which customers may experience great inconvenience when a medicine is not provided in time, a point in which health damage may be caused when a wrong medicine is provided, and a point in which some medicines may be used for undesirable behavior like abuse when the medicines are wrongly released. Meanwhile, as types and quantities of medicines that are required to be stored and managed in a pharmacy continue to grow due to development of medical treatment technology and pharmaceutical technology, considerable costs and effort are consumed to manage stock of medicines. In relation to this, prior documents such as KR101674195B1 and KR102245345B1 may be referred to. SUMMARY A task to be solved by an example embodiment is, for solving the above-mentioned issue, to provide an electronic apparatus, which acquires a target image, identifies one or more medicines included in the target image, and acquires, based on a result obtained by identifying the one or more medicines, stock information for each medicine type included in the target image, and a method thereof. A technical task to be achieved by an example embodiment of the present disclosure is not limited to the technical task described above, and other technical tasks may be derived from example embodiments described below. A method of acquiring information according to an example embodiment includes acquiring a target image, identifying one or more medicines included in the target image, and acquiring, based on a result obtained by identifying the one or more medicines, stock information for each medicine type included in the target image. According to an example embodiment, the identifying of the one or more medicines may include identifying one or more feature components included in the target image and acquiring type information of a medicine related to a first feature component included in the one or more feature components. According to an example embodiment, the acquiring of the type information of the medicine related to the first feature component may include comparing the first feature component with one or more comparative images. According to an example embodiment, the comparing of the first feature component with the one or more comparative images may include inputting the first feature component and the one or more comparative images to a pre-trained machine learning model and acquiring an output of the machine learning model. The machine learning model may be pre-trained based on a plurality of medicine images. According to an example embodiment, the comparing of the first feature component with the one or more comparative images may include determining one or more attributes related to the first feature component and selecting, based on the one or more attributes, the one or more comparative images from a plurality of images included in a medicine image group. According to an example embodiment, the determining of the one or more attributes may include identifying logo information included in the first feature component. According to an example embodiment, the acquiring of the type information of the medicine related to the first feature component may include acquiring gradient information related to the first feature component and rotating the first feature component based on the gradient information. According to an example embodiment, the acquiring of the type information of the medicine related to the first feature component may include acquiring distortion information related to the first feature component and correcting the first feature component based on the distortion information. The correcting of the first feature component may include performing warping for the first feature component. According to an example embodiment, the method of acquiring information may further include acquiring photographing environment information of the target image. The identifying of the one or more medicines may include transforming the target image based on the photographing environment information. According to an example embodiment, the photographing environment information may include one or