Automated order processing system based on automatic inventory management and order quantity calculation according to pharmaceutical classification types

Abstract

An automated order processing system based on inventory management according to pharmaceutical classification types and automatic calculation of order quantities is launched. In an order processing automation system based on inventory management according to pharmaceutical classification type and automatic calculation of order quantity according to one embodiment of the present invention, the system comprises: a memory; a communication unit; The electronic device includes a processor connected to the communication unit and memory, wherein the processor receives drug name, drug code, manufacturer, stock quantity, appropriate quantity, sales quantity, dispensing quantity, usage quantity, total purchase unit price, and order data of a drug from a pharmacy's POS (Point of Sale) Safety Stock system, a drug billing program, or an external server, extracts and analyzes string patterns, number patterns, prefixes, suffixes, and symbol patterns for the drug name, and based on the analysis results, applies a preset drug classification standard to classify and determine the drug by mapping it to at least one first to nth code (n is an integer) among over-the-counter drugs (OTC), ethical drugs (ETC), oral preparations, topical preparations, drinks, nutritional supplements, pediatric drugs, patches, herbal granules, veterinary drugs, items stored in storage space, items excluded from discounts, and items excluded from orders, and determines the string of text corresponding to the first to kth symbol (k is an integer) included in the drug name Extracts and calculates the actual quantity, displayable quantity, packaging unit, and discount / surcharge standard quantity; calculates the maximum holding quantity and minimum maintenance quantity by applying the minimum holding factor, maximum holding factor, and standard maximum value as user-configured parameters; calculates the final maximum quantity as the smaller value between the maximum holding quantity and the displayable quantity; calculates the required order quantity based on the difference between the final maximum quantity and the current inventory quantity; performs an order correction operation to convert the required order quantity into an integer by dividing it by the actual quantity to calculate the final reference order quantity; sets the reference order quantity to 0 if the prefix of the drug name corresponds to the order exclusion criteria; determines whether to apply a discount / surcharge based on the total purchase unit price and the standard maximum value; and calculates the final order amount using the reference order quantity and the purchase price.The above final order amounts are summed by manufacturer to calculate the total amount by manufacturer, and the order availability is determined by comparing the total amount by manufacturer with the minimum order amount by manufacturer. At least one condition among immediate order availability, discount / surcharge application availability, manufacturer, storage space classification, and order availability is applied using a logical AND-based intersection filtering method to output the filtering result to the display unit. Based on the filtering result, order request data or message data is generated and transmitted to an external terminal, message transmission server, or order server. The first to nth codes may consist of identifier information already stored in the drug classification database.

Description

Technology Field

[0001] The present invention relates to the field of pharmaceutical inventory management technology, and more specifically, to a pharmaceutical inventory management and order processing automation system that automatically classifies over-the-counter drugs (OTC), prescription drugs and ethical drugs (ETC), medical supplies, drinks, external preparations, and items subject to storage in storage spaces handled in pharmacies according to the type of pharmaceutical, sales volume, dispensing volume, usage volume, packaging unit, displayable quantity, pack multiple, discount / surcharge conditions, and storage space characteristics, automatically calculates the minimum holding quantity, maximum holding quantity, standard appropriate quantity, and required order quantity based on this, and finally automates order processing, transaction document generation, and transaction brokerage between pharmacies.

[0002] In particular, the present invention is configured to automatically analyze pharmaceuticals based on sales volume, dispensing volume, inventory volume, and purchase unit price data extracted from a POS (Point of Sale) system or billing program within a pharmacy, and to execute dynamic inventory management logic that reflects consumption patterns and storage characteristics for each pharmaceutical, in order to solve problems such as pharmaceutical inventory shortages, excess inventory, order delays, insufficient storage space, and complexity of ordering operations occurring in a pharmacy operating environment.

[0003] In addition, the present invention automatically classifies over-the-counter (OTC) drugs and prescription drugs based on different criteria and applies separate order calculation logic to each, thereby enabling order optimization for OTC drugs considering displayable quantity, volume, discounts / surcharges, and packaging units, and for prescription drugs calculating the appropriate standard quantity and determining the order based on prescription deviation, daily dispensing volume, and prescription concentration.

[0004] In addition, the present invention can be configured to automatically recognize the storage location, display characteristics, packaging structure, order unit, and discount conditions of pharmaceuticals using specific symbols and string patterns included in the drug name, thereby improving storage space management efficiency by automatically classifying whether the product is stored in a warehouse, whether it is stored in an upper or lower cabinet, whether it is a drink, and whether it is a large package.

[0005] In addition, the present invention may include an online brokerage function for pharmaceutical transactions between pharmacies and falls under the field of technology that supports the securing of emergency medicines and the improvement of pharmaceutical distribution efficiency by providing functions for registering transaction requests, accepting transactions, transmitting real-time notifications, approving transactions based on electronic signatures, and automatically generating transaction records between pharmacies.

[0006] In other words, the present invention relates to the field of an integrated pharmacy operation automation platform technology that fuses inventory management technology, order automation technology, pharmaceutical classification technology, data-based demand forecasting technology, pharmacy operation support technology, electronic document automatic generation technology, and online transaction brokerage technology. Background Technology

[0008] Generally, pharmacies handle a wide variety of medicines and products simultaneously, including over-the-counter (OTC) drugs, ethical (ETC) drugs, medical supplies, health functional foods, drinks, external preparations, and compounded medicines, and for each item, the sales frequency, prescription frequency, packaging structure, storage conditions, and order units differ.

[0009] In particular, unlike simple merchandise inventory management, pharmaceutical inventory management in pharmacies is directly linked to patient treatment, making the prevention of stockouts and inventory stability critical. However, in reality, pharmacies must simultaneously manage thousands of types of medications with limited storage space and operating funds, leading to recurring problems of stock shortages and excess inventory.

[0010] For example, sales volumes of over-the-counter (OTC) drugs are inconsistent, and demand fluctuates significantly depending on the season, holidays, long weekends, epidemics, and manufacturers' supply schedules. In particular, during holiday periods or summer vacations, delivery delays can occur for extended periods due to the closure of pharmaceutical companies and distributors, requiring a higher level of inventory than usual. However, conventional technology has failed to adequately reflect these periodic fluctuations, leading to frequent problems of inventory shortages or overordering.

[0011] In addition, some over-the-counter drugs have large packaging structures, and when the box is opened, there are multiple small packages inside. For example, a single box of beverages may contain multiple bottle units, and a set of small packages may exist within a large package of nutritional supplements. Conventional inventory management systems failed to account for this concept of pack multiples, resulting in a discrepancy between the actual sales unit and the order unit.

[0012] Furthermore, because pharmacies have very limited display space, it is necessary to separately manage the maximum display quantity for specific medications. However, existing systems calculate order quantities based solely on simple inventory standards, leading to a problem of over-ordering that exceeds the actual display space.

[0013] Meanwhile, inventory management for prescription and compounded medicines is more complex than for over-the-counter medicines. The demand for compounded medicines can fluctuate rapidly depending on the prescribing patterns of specific medical institutions, and even for the same drug, prescription volumes may be concentrated during certain periods. In particular, due to the prescribing characteristics of departments such as family medicine, internal medicine, and otolaryngology, prescriptions for multiple items in small quantities occur frequently; therefore, if inventory is managed based solely on simple average values, shortages of medicine may frequently occur during actual dispensing.

[0014] However, conventionally, pharmacists had to manually check prescription records for a certain period to reflect prescription variations by prescription drug, which resulted in a significant amount of time and workload. In addition, it was difficult to reflect sudden increases in dispensing volume on a daily basis, leading to a problem of a time lag between the actual dispensing situation and inventory assessment.

[0015] Furthermore, the management of storage space within pharmacies was often operated inefficiently. While pharmacies generally utilize multiple storage spaces—such as upper cabinets, lower cabinets, warehouses, and display cases—systems that automatically determine appropriate storage locations based on the size, weight, and turnover rate of medications were virtually non-existent. In particular, despite the critical importance of space efficiency for bulky products like beverages, existing technologies had limitations in that they could not comprehensively assess both storage location and order volume.

[0016] Furthermore, in the case of pharmaceutical transactions between pharmacies, transactions were previously conducted in an unstructured manner using telephones, text messages, or messengers, and transaction records were often prepared manually. However, since the creation of transaction records is mandatory for pharmaceutical transactions under relevant regulations, inefficiencies in the transaction process and the burden of document management have persisted.

[0017] In particular, despite the importance of rapid transaction response for urgently needed medicines, existing systems faced problems where it was difficult to verify the registration status of specific medicines in real time and to immediately determine whether a transaction had been accepted.

[0018] Therefore, there is a continuously being raised need for a new type of automated pharmaceutical inventory management and order processing system capable of automatically classifying over-the-counter and prescription drugs based on different criteria, automatically calculating required order quantities by comprehensively reflecting sales volume, dispensing volume, inventory volume, packaging unit, display capacity, stock volume, storage space characteristics, and discount / surcharge conditions, and automating order processing and transaction document generation. The problem to be solved

[0020] The objective of the present invention is to solve the problems of the aforementioned prior art by providing an automated pharmaceutical inventory management and order processing system capable of automatically classifying general pharmaceuticals, prescription pharmaceuticals, and compounding pharmaceuticals handled in pharmacies by pharmaceutical type, and automatically calculating the required order quantity by comprehensively analyzing sales volume, compounding volume, inventory volume, appropriate quantity, packaging unit, stacking volume, displayable quantity, and storage space characteristics.

[0021] Another objective of the present invention is to provide an order quantity calculation technology that applies the concepts of minimum maintenance amount and maximum retention amount to over-the-counter drugs and considers the stock volume, packaging unit, and displayable quantity to prevent over-ordering while minimizing the risk of stockout.

[0022] Another objective of the present invention is to provide an order automation technology capable of minimizing excess inventory while reducing the risk of prescription drug shortages by providing a primary, non-primary, and manual classification system for prescription drugs and compounded drugs that considers prescription variations, and by providing a technology for calculating a standard appropriate amount that reflects the dispensing volume and daily usage of each drug.

[0023] Another objective of the present invention is to provide a string-based drug attribute analysis technology capable of automatically recognizing specific strings, numbers, and symbols included in a drug name to automatically classify the quantity, packaging unit, discount / surcharge conditions, displayable quantity, and storage location of the drug.

[0024] Another objective of the present invention is to enable the user to customize settings for minimum maintenance quantity, maximum holding quantity, discount / surcharge criteria, classification criteria for main and non-main products, holding days, displayable quantity, and order criteria, so as to respond to operating policies that differ from pharmacy to pharmacy.

[0025] Another objective of the present invention is to provide a storage space management technology that automatically determines the storage location and warehouse availability for each medicine by reflecting the structure and characteristics of the storage space within a pharmacy, and automatically calculates the quantity to be moved from the storage space based on changes in usage over a specific period.

[0026] Another objective of the present invention is to provide an order processing technology capable of automating order tasks by automatically aggregating order items by manufacturer, automatically determining whether the minimum order amount is met, and automatically generating order statements and order messages.

[0027] Another objective of the present invention is to provide an online brokerage platform for pharmaceutical transactions between pharmacies and to improve the speed of emergency pharmaceutical transactions and the efficiency of legal document management by implementing functions such as transaction request registration, transaction acceptance, real-time notification, electronic signature, and automatic generation of transaction records.

[0028] Another objective of the present invention is to provide an integrated pharmaceutical operation automation system that automatically links Point of Sale (POS) data, sales data, dispensing data, and purchasing data to minimize manual input and reduce the workload of pharmacy operators. means of solving the problem

[0030] In an order processing automation system based on inventory management according to pharmaceutical classification type and automatic calculation of order quantity according to one embodiment of the present invention, the system comprises: a memory; a communication unit; The electronic device includes a processor connected to the communication unit and memory, wherein the processor receives drug name, drug code, manufacturer, stock quantity, appropriate quantity, sales quantity, dispensing quantity, usage quantity, total purchase unit price, and order data of a drug from a pharmacy's POS (Point of Sale) Safety Stock system, a drug billing program, or an external server, extracts and analyzes string patterns, number patterns, prefixes, suffixes, and symbol patterns for the drug name, and based on the analysis results, applies a preset drug classification standard to classify and determine the drug by mapping it to at least one first to nth code (n is an integer) among over-the-counter drugs (OTC), ethical drugs (ETC), oral preparations, topical preparations, drinks, nutritional supplements, pediatric drugs, patches, herbal granules, veterinary drugs, items stored in storage space, items excluded from discounts, and items excluded from orders, and determines the string of text corresponding to the first to kth symbol (k is an integer) included in the drug name Extracts and calculates the actual quantity, displayable quantity, packaging unit, and discount / surcharge standard quantity; calculates the maximum holding quantity and minimum maintenance quantity by applying the minimum holding factor, maximum holding factor, and standard maximum value as user-configured parameters; calculates the final maximum quantity as the smaller value between the maximum holding quantity and the displayable quantity; calculates the required order quantity based on the difference between the final maximum quantity and the current inventory quantity; performs an order correction operation to convert the required order quantity into an integer by dividing it by the actual quantity to calculate the final reference order quantity; sets the reference order quantity to 0 if the prefix of the drug name corresponds to the order exclusion criteria; determines whether to apply a discount / surcharge based on the total purchase unit price and the standard maximum value; and calculates the final order amount using the reference order quantity and the purchase price.The above final order amounts are summed by manufacturer to calculate the total amount by manufacturer, and the order availability is determined by comparing the total amount by manufacturer with the minimum order amount by manufacturer. At least one condition among immediate order availability, discount / surcharge application availability, manufacturer, storage space classification, and order availability is applied using a logical AND-based intersection filtering method to output the filtering result to the display unit. Based on the filtering result, order request data or message data is generated and transmitted to an external terminal, message transmission server, or order server. The first to nth codes may consist of identifier information already stored in the drug classification database.

[0031] The processor according to one embodiment of the present invention receives dispensing volume and usage data for a certain period for a prescription drug or a compounding drug, analyzes a string pattern included in the drug name to classify it into oral preparations and topical preparations, classifies oral preparations into at least one of a main group, a non-main group, and a manual review group, classifies topical preparations into at least one of a main group, a non-main group, and a manual review group, calculates a standard appropriate amount by applying a standard retention period stored for each group, calculates a first order value by subtracting the current inventory amount from the standard appropriate amount, calculates a determined usage amount by applying a set multiplier value to the usage amount of the day, calculates a second order value by comparing the determined usage amount with the current inventory amount, determines the larger value between the first order value and the second order value as an order evaluation value, sets the order evaluation value as a reference order amount if it is a number and classifies it as a subject for manual review if it is a character value, and if the reference order amount is less than a standard value, applies a standard retention period to correct it to be greater than or equal to the minimum order standard, and for a specific drug, the appropriate amount multiplier value If set, the appropriate amount is multiplied by the corresponding multiplier value to calculate the corrected appropriate amount; if the holding instruction quantity is set for a specific pharmaceutical product, the larger value between the value obtained by subtracting the current inventory quantity from the holding instruction quantity and the order evaluation value is determined as the final reference order quantity; if the maximum displayable quantity is set for a specific pharmaceutical product, the reference order quantity is limited and corrected so as not to exceed the maximum displayable quantity, and the guidance message set for the specific pharmaceutical product can be displayed on the display unit.

[0032] The processor according to one embodiment of the present invention analyzes the sales volume, dispensing volume, consumption volume, volume, weight, packaging size, storage characteristics, and turnover rate of the pharmaceuticals to automatically classify the pharmaceuticals to be stored in the storage space, analyzes the code and symbol patterns included in the pharmaceutical names to classify them into at least one of store display items, warehouse storage items, upper cabinet storage items, lower cabinet storage items, drink items, nutritional supplement items, and discount exclusion items, calculates the difference between the cumulative usage up to a first point in time designated by the user and the cumulative usage up to a second point in time prior to the first point in time to calculate the replenishment quantity to be moved from the storage space, generates a storage space movement list based on the replenishment quantity, outputs the pharmaceuticals to be moved and the moving quantity to a display unit according to the storage space movement list, receives pharmaceutical transaction request information between pharmacies and sends a notification message to a user terminal when the pharmaceuticals to be traded are posted, automatically generates a transaction statement including transaction counterparty information, pharmaceutical information, transaction quantity information, and transaction date and time information when an acceptance input for the transaction request is received, and applies an electronic signature to the transaction statement when an electronic signature input is received. Reflecting and generating a final transaction document, transmitting the final transaction document to a user terminal, an external server, or a message transmission server, and storing and managing the final transaction document as evidence for face-to-face or non-face-to-face transactions, and the processes of storage space classification, movement list generation, transaction request processing, and transaction statement generation and transmission are performed integrally in conjunction with the order processing automation system, and the storage space classification and movement are performed periodically based on differences in consumption amounts by time interval, and the time interval may include multiple reference points defined by user settings or system settings.

[0033] The processor according to one embodiment of the present invention collects disposal record data, order history data, and inter-pharmacy transaction history data based on the expiration of the expiration date of each pharmaceutical product for each of a plurality of pharmacies; obtains first group classification data reclassified into at least one of a main group, a non-main group, and a manual review group through a first model based on the disposal record data and order history data; corrects the standard appropriate amount based on the first group classification data; calculates a first match rate for each group by comparing the first group classification data with the second group classification data, which is the group classification data prior to reclassification; calculates an Eco Risk Score for each pharmaceutical product for groups where the first match rate is less than a preset standard value; calculates a Trade Feasibility Score for each pharmaceutical product based on at least one of the number of transaction requests, the number of transaction successes, the transaction quantity, and the transaction time included in the inter-pharmacy transaction history data; calculates an Adjusted Eco Risk Score by correcting the disposal risk score using the Trade Feasibility Score; and based on the Adjusted Eco Risk Score, the main group, the non-main group, or Reclassification is performed to at least one of the manual review groups, and at least one of the order evaluation value, the standard appropriate quantity, or the reference order quantity is corrected based on the reclassification result and the standard appropriate quantity, and an Environment Score is periodically calculated for each of the plurality of pharmacies based on the corrected disposal risk score, and Environment Points are awarded to user accounts corresponding to each pharmacy based on the Environment Score, and the first model is an artificial intelligence model trained to output group classification results and disposal risk scores by pharmaceutical using disposal record data, order history data, and group classification data as training data, and the disposal risk score is the frequency of disposal occurrence by pharmaceutical, disposal quantity,It is a value calculated based on at least one of the inventory turnover rate and group classification results, the transaction possibility score is a value quantifying the possibility that the medicine will be transferred to another pharmacy, the environment score is a value calculated based on the amount of waste reduction over a certain period and the amount of medicine moved through transactions between pharmacies, the environment point is a compensation value calculated by applying a weight proportional to the amount of reduction when the amount of waste is reduced through transactions between pharmacies, and may include a value that can be deducted once as a correction value for the order amount when determining whether the minimum order amount is satisfied.

[0034] The processor according to one embodiment of the present invention collects pharmaceutical collection history data for each of the pharmacies among a plurality of pharmacies where pharmaceutical collection boxes are installed, generates regional collection data based on the collection history data and location information of the pharmacies where the collection boxes are installed, groups the plurality of pharmacies into a first group according to the units of Eup, Myeon, Dong, or administrative districts based on the location information, groups pharmacies that are different from the matching first group and whose distance between pharmacies is within a preset threshold distance into a second group, calculates whether there is a need to expand collection boxes at each base through a second model trained to determine whether there is a need to expand collection boxes at each base based on the collection history data, and, according to the output result of the second model, identifies the first pharmacy within the first base group where collection box expansion is needed and the second pharmacies excluding the first pharmacy among the first groups, recommends the installation of a collection box to the user account corresponding to the third pharmacy if there is a third pharmacy among the second pharmacies where the first pharmacy does not exist within a preset standard distance, and if the third pharmacy does not exist In the case, a second base group adjacent to the first base group is additionally identified, a fourth pharmacy with a collection box installed within the second base group and fifth pharmacies excluding the fourth pharmacy are identified, and if there is at least one first pharmacy among the fourth pharmacies and a sixth pharmacy grouped into the second group, a seventh pharmacy located within a reference distance from the sixth pharmacy and the first pharmacy grouped into the second group among the fifth pharmacies is identified, and the installation of a collection box is recommended for the user account corresponding to the seventh pharmacy, and if there is no sixth pharmacy, at least one first pharmacy among the fifth pharmacies and an eighth pharmacy grouped into the second group are identified, and the installation of a collection box is recommended for the user account corresponding to the eighth pharmacy.Based on the sales volume of pharmaceuticals handled within the first base group and the transaction history between pharmacies within the first base group and other base groups, the average primary group, average non-primary group, and average manual review group of the first base group are calculated; a group-specific match rate is calculated by comparing the average group with the group for each pharmacy; first recommendation information, which is a list of replaceable pharmaceuticals, is generated for groups where the calculated match rate is less than a threshold value; and second recommendation information, which is a list of additional replaceable pharmaceuticals, is generated for groups where the match rate calculated by comparing the primary group, non-primary group, and manual review group for each pharmacy within the first base group with the average primary group, average non-primary group, and average manual review group is less than a threshold value; and the second model is an artificial intelligence model trained to output collection demand and collection distribution maps by base using collection history data and pharmacy location data of multiple pharmacies as training data; the first recommendation information is provided to accounts for each pharmacy within the first base group, and the second recommendation information can be provided to user accounts corresponding to matching pharmacies. there is.,

[0035] A device according to one embodiment of the present invention may be combined with hardware and controlled by a computer program stored on a medium to execute any one of the operation methods by the processor of the system described above. Effects of the invention

[0037] According to the present invention, by automatically classifying general medicines and prescription medicines handled in pharmacies according to different inventory management standards and calculating the order quantity, precise inventory management reflecting the characteristics of each medicine type becomes possible.

[0038] In addition, since the present invention calculates the required order quantity by simultaneously considering sales volume, dispensing volume, inventory volume, optimal quantity, quantity, packaging unit, displayable quantity, and storage space characteristics, it has the effect of significantly reducing the possibility of inventory shortages and excess inventory compared to a simple average-based system.

[0039] In addition, the present invention applies the concepts of minimum maintenance amount and maximum retention amount to over-the-counter medicines and automatically adjusts the order quantity by reflecting the limitations of display space, thereby having the effect of efficiently utilizing the limited space within a pharmacy.

[0040] In addition, the present invention applies a primary, non-primary, and manual classification system to prescription drugs and introduces the concept of assessed usage reflecting daily usage, thereby having the effect of reducing the risk of stock shortages for compounded drugs with large prescription variations.

[0041] In addition, the present invention automatically analyzes the quantity, packaging unit, discount / surcharge conditions, and storage location using specific symbols and strings included in the drug name, thereby having the effect of automatically recognizing drug attributes without the need for separate manual data input.

[0042] In addition, the present invention has the effect of contributing to the reduction of pharmaceutical purchasing costs and the improvement of order efficiency in pharmacies by optimizing order strategies through the automatic determination of discount / surcharge conditions and minimum order amounts.

[0043] In addition, the present invention has the effect of streamlining the inventory replenishment work of pharmacy operators by automatically distinguishing between items held in the warehouse and items for store display through a storage space management function, and by calculating the quantity of items to be moved in the warehouse based on changes in usage over a specific time interval.

[0044] In addition, the present invention has the effect of shortening the order processing time for pharmacy operators and reducing work errors by automatically aggregating order items by manufacturer and automatically generating order messages and order records.

[0045] In addition, the present invention enables the rapid execution of emergency drug transactions through a transaction system between pharmacies and provides an automatic generation function for electronic signature-based transaction records, thereby having the effect of improving the legal stability of drug transactions and the efficiency of document management.

[0046] In addition, the present invention is configured to allow users to customize inventory management policies, storage space structures, and ordering strategies that differ from pharmacy to pharmacy, thereby having the effect of being flexibly applicable to various types of pharmacy operating environments.

[0047] Consequently, the present invention has the effect of significantly contributing to improved pharmacy operational efficiency, reduced inventory costs, reduced risk of stockouts, and enhanced levels of business automation by integrally performing functions of pharmaceutical inventory management, order automation, storage space management, and inter-pharmacy transaction management. Brief explanation of the drawing

[0049] FIG. 1 is a block diagram schematically illustrating the basic configuration of a device according to one embodiment. FIG. 2 is a schematic diagram illustrating a system according to one embodiment. FIGS. 3 and 4 are basic operation flowcharts of a method according to one embodiment. Specific details for implementing the invention

[0050] Hereinafter, embodiments are described in detail with reference to the attached drawings. However, various modifications may be made to the embodiments, and thus the scope of the patent application is not limited or restricted by these embodiments. It should be understood that all modifications, equivalents, and substitutions to the embodiments are included within the scope of the rights.

[0051] Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only and may be modified and implemented in various forms. Accordingly, the embodiments are not limited to the specific disclosed forms, and the scope of this specification includes modifications, equivalents, or substitutions that fall within the technical concept.

[0052] Terms such as "first" or "second" may be used to describe various components, but these terms should be interpreted solely for the purpose of distinguishing one component from another. For example, the first component may be named the second component, and similarly, the second component may be named the first component.

[0053] When it is stated that a component is "connected" to another component, it should be understood that it may be directly connected to or joined to that other component, or that there may be other components in between.

[0054] The terms used in the embodiments are for illustrative purposes only and should not be interpreted as intended to be limiting. Singular expressions include plural expressions unless the context clearly indicates otherwise. In this specification, terms such as "comprising" or "having" are intended to indicate the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should be understood as not precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0055] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as generally understood by those skilled in the art to which the embodiments pertain. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an ideal or overly formal sense unless explicitly defined in this application.

[0056] In addition, when describing with reference to the attached drawings, identical components are assigned the same reference numeral regardless of drawing symbols, and redundant descriptions thereof are omitted. In describing the embodiments, if it is determined that a detailed description of related prior art could unnecessarily obscure the essence of the embodiments, such detailed description is omitted.

[0057] The embodiments can be implemented in various forms of products such as personal computers, laptop computers, tablet computers, smartphones, televisions, smart home appliances, intelligent automobiles, kiosks, and wearable devices.

[0058] Artificial Intelligence (AI) systems are computer systems that implement human-level intelligence. Unlike existing rule-based smart systems, they are systems in which machines learn and make decisions autonomously. As AI systems improve in recognition accuracy and gain a more accurate understanding of user preferences with continued use, existing rule-based smart systems are gradually being replaced by deep learning-based AI systems.

[0059] Artificial intelligence technology consists of machine learning and component technologies utilizing machine learning. Machine learning is an algorithmic technology that autonomously classifies and learns the characteristics of input data, while component technologies are technologies that mimic the cognitive and judgmental functions of the human brain by utilizing machine learning algorithms such as deep learning, and are comprised of technological fields such as linguistic understanding, visual understanding, reasoning / prediction, knowledge representation, and motion control.

[0060] The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding refers to technologies that recognize, apply, and process human language and text, including natural language processing, machine translation, dialogue systems, question answering, and speech recognition / synthesis. Visual understanding refers to technologies that perceive and process objects like human vision, including object recognition, object tracking, image search, person recognition, scene understanding, spatial understanding, and image enhancement. Inference and prediction refers to technologies that logically reason and predict by judging information, including knowledge / probability-based inference, optimization prediction, preference-based planning, and recommendation. Knowledge representation refers to technologies that automatically process human experiential information into knowledge data, including knowledge construction (data generation / classification) and knowledge management (data utilization). Motion control refers to technologies that control the autonomous driving of vehicles and the movement of robots, including motion control (navigation, collision, driving) and manipulation control (behavior control).

[0061] Generally, to apply machine learning algorithms to real-world situations, training is performed using a trial-and-error method due to the inherent characteristics of the fundamental methodologies. In particular, deep learning requires hundreds of thousands of iterations. Since it is impossible to execute this in a real physical external environment, training is instead performed through simulations that virtually recreate the actual physical environment on a computer.

[0062] In the present invention, Artificial Intelligence (AI) refers to a technology that imitates human learning ability, reasoning ability, and perceptual ability, and implements them on a computer, and may include concepts such as machine learning and symbolic logic. Machine Learning (ML) is an algorithmic technology that classifies or learns the characteristics of input data on its own. AI technology can analyze input data as a machine learning algorithm, learn from the results of the analysis, and make judgments or predictions based on the results of the learning. Furthermore, technologies that mimic the functions of the human brain, such as cognition and judgment, by utilizing machine learning algorithms can also be understood as falling within the category of AI. For example, technological fields such as linguistic understanding, visual understanding, reasoning / prediction, knowledge representation, and motion control may be included.

[0063] Machine learning can refer to the process of training neural network models using experience in processing data. Through machine learning, computer software can improve its own data processing capabilities. A neural network model is constructed by modeling the correlations between data, and these correlations can be expressed by multiple parameters. A neural network model extracts and analyzes features from given data to derive correlations between them; machine learning can be defined as the process of optimizing the model's parameters by repeating this process. For example, a neural network model can learn the mapping (correlation) between inputs and outputs for data given as input-output pairs. Alternatively, even when only input data is provided, a neural network model can derive regularities between the given data and learn those relationships.

[0064] An artificial intelligence learning model or neural network model can be designed to implement the structure of the human brain on a computer and may include multiple network nodes that have weights and simulate neurons of a human neural network. The multiple network nodes may have interconnected relationships by simulating the synaptic activity of neurons, where neurons exchange signals through synapses. In an artificial intelligence learning model, multiple network nodes may be located in layers of different depths and exchange data according to convolutional connections. The artificial intelligence learning model may be, for example, an Artificial Neural Network (ANN) or a Convolutional Neural Network (CNN). As an embodiment, the artificial intelligence learning model may be machine learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning may include Decision Tree, Bayesian Network, Support Vector Machine, Artificial Neural Network, Ada-boost, Perceptron, Genetic Programming, and Clustering.

[0065] Among these, CNNs are a type of multilayer perceptron designed to use minimal preprocessing. CNNs consist of one or more convolutional layers and standard artificial neural network layers stacked on top, additionally utilizing weights and pooling layers. Thanks to this structure, CNNs can fully utilize two-dimensional input data. Compared to other deep learning architectures, CNNs demonstrate good performance in both image and audio fields. CNNs can also be trained using standard backpropagation. CNNs have the advantage of being easier to train than other feedforward artificial neural network techniques and using a small number of parameters.

[0066] Convolutional networks are neural networks comprising sets of nodes with bounded parameters. Many computer vision tasks have been significantly improved by the combination of increased available training data sizes and the availability of computational power, along with algorithmic advancements such as discriminative linear units and dropout training. In the case of massive datasets, such as those available for many tasks today, outfitting is not critical, and increasing the network size improves test accuracy. Optimal utilization of computing resources becomes a limiting factor. To address this, distributed, scalable implementations of deep neural networks can be used.

[0067] The present invention relates to the field of pharmaceutical inventory management technology, and more specifically, to a pharmaceutical inventory management and order processing automation system that automatically classifies over-the-counter drugs (OTC), prescription drugs and ethical drugs (ETC), medical supplies, drinks, external preparations, and items subject to storage in storage spaces handled in pharmacies according to the type of pharmaceutical, sales volume, dispensing volume, usage volume, packaging unit, displayable quantity, pack multiple, discount / surcharge conditions, and storage space characteristics, automatically calculates the minimum holding quantity, maximum holding quantity, standard appropriate quantity, and required order quantity based on this, and finally automates order processing, transaction document generation, and transaction brokerage between pharmacies.

[0068] In particular, the present invention is configured to automatically analyze pharmaceuticals based on sales volume, dispensing volume, inventory volume, and purchase unit price data extracted from a POS (Point of Sale) system or billing program within a pharmacy, and to execute dynamic inventory management logic that reflects consumption patterns and storage characteristics for each pharmaceutical, in order to solve problems such as pharmaceutical inventory shortages, excess inventory, order delays, insufficient storage space, and complexity of ordering operations occurring in a pharmacy operating environment.

[0069] In addition, the present invention automatically classifies over-the-counter (OTC) drugs and prescription drugs based on different criteria and applies separate order calculation logic to each, thereby enabling order optimization for OTC drugs considering displayable quantity, volume, discounts / surcharges, and packaging units, and for prescription drugs calculating the appropriate standard quantity and determining the order based on prescription deviation, daily dispensing volume, and prescription concentration.

[0070] In addition, the present invention can be configured to automatically recognize the storage location, display characteristics, packaging structure, order unit, and discount conditions of pharmaceuticals using specific symbols and string patterns included in the drug name, thereby improving storage space management efficiency by automatically classifying whether the product is stored in a warehouse, whether it is stored in an upper or lower cabinet, whether it is a drink, and whether it is a large package.

[0071] In addition, the present invention may include an online brokerage function for pharmaceutical transactions between pharmacies and falls under the field of technology that supports the securing of emergency medicines and the improvement of pharmaceutical distribution efficiency by providing functions for registering transaction requests, accepting transactions, transmitting real-time notifications, approving transactions based on electronic signatures, and automatically generating transaction records between pharmacies.

[0072] In other words, the present invention relates to the field of an integrated pharmacy operation automation platform technology that fuses inventory management technology, order automation technology, pharmaceutical classification technology, data-based demand forecasting technology, pharmacy operation support technology, electronic document automatic generation technology, and online transaction brokerage technology.

[0073] Generally, pharmacies handle a wide variety of medicines and products simultaneously, including over-the-counter (OTC) drugs, ethical (ETC) drugs, medical supplies, health functional foods, drinks, external preparations, and compounded medicines, and for each item, the sales frequency, prescription frequency, packaging structure, storage conditions, and order units differ.

[0074] In particular, unlike simple merchandise inventory management, pharmaceutical inventory management in pharmacies is directly linked to patient treatment, making the prevention of stockouts and inventory stability critical. However, in reality, pharmacies must simultaneously manage thousands of types of medications with limited storage space and operating funds, leading to recurring problems of stock shortages and excess inventory.

[0075] For example, sales volumes of over-the-counter (OTC) drugs are inconsistent, and demand fluctuates significantly depending on the season, holidays, long weekends, epidemics, and manufacturers' supply schedules. In particular, during holiday periods or summer vacations, delivery delays can occur for extended periods due to the closure of pharmaceutical companies and distributors, requiring a higher level of inventory than usual. However, conventional technology has failed to adequately reflect these periodic fluctuations, leading to frequent problems of inventory shortages or overordering.

[0076] In addition, some over-the-counter drugs have large packaging structures, and when the box is opened, there are multiple small packages inside. For example, a single box of beverages may contain multiple bottle units, and a set of small packages may exist within a large package of nutritional supplements. Conventional inventory management systems failed to account for this concept of pack multiples, resulting in a discrepancy between the actual sales unit and the order unit.

[0077] Furthermore, because pharmacies have very limited display space, it is necessary to separately manage the maximum display quantity for specific medications. However, existing systems calculate order quantities based solely on simple inventory standards, leading to a problem of over-ordering that exceeds the actual display space.

[0078] Meanwhile, inventory management for prescription and compounded medicines is more complex than for over-the-counter medicines. The demand for compounded medicines can fluctuate rapidly depending on the prescribing patterns of specific medical institutions, and even for the same drug, prescription volumes may be concentrated during certain periods. In particular, due to the prescribing characteristics of departments such as family medicine, internal medicine, and otolaryngology, prescriptions for multiple items in small quantities occur frequently; therefore, if inventory is managed based solely on simple average values, shortages of medicine may frequently occur during actual dispensing.

[0079] However, conventionally, pharmacists had to manually check prescription records for a certain period to reflect prescription variations by prescription drug, which resulted in a significant amount of time and workload. In addition, it was difficult to reflect sudden increases in dispensing volume on a daily basis, leading to a problem of a time lag between the actual dispensing situation and inventory assessment.

[0080] Furthermore, the management of storage space within pharmacies was often operated inefficiently. While pharmacies generally utilize multiple storage spaces—such as upper cabinets, lower cabinets, warehouses, and display cases—systems that automatically determine appropriate storage locations based on the size, weight, and turnover rate of medications were virtually non-existent. In particular, despite the critical importance of space efficiency for bulky products like beverages, existing technologies had limitations in that they could not comprehensively assess both storage location and order volume.

[0081] Furthermore, in the case of pharmaceutical transactions between pharmacies, transactions were previously conducted in an unstructured manner using telephones, text messages, or messengers, and transaction records were often prepared manually. However, since the creation of transaction records is mandatory for pharmaceutical transactions under relevant regulations, inefficiencies in the transaction process and the burden of document management have persisted.

[0082] In particular, despite the importance of rapid transaction response for urgently needed medicines, existing systems faced problems where it was difficult to verify the registration status of specific medicines in real time and to immediately determine whether a transaction had been accepted.

[0083] Therefore, there is a continuously being raised need for a new type of automated pharmaceutical inventory management and order processing system capable of automatically classifying over-the-counter and prescription drugs based on different criteria, automatically calculating required order quantities by comprehensively reflecting sales volume, dispensing volume, inventory volume, packaging unit, display capacity, stock volume, storage space characteristics, and discount / surcharge conditions, and automating order processing and transaction document generation.

[0084] The objective of the present invention is to solve the problems of the aforementioned prior art by providing an automated pharmaceutical inventory management and order processing system capable of automatically classifying general pharmaceuticals, prescription pharmaceuticals, and compounding pharmaceuticals handled in pharmacies by pharmaceutical type, and automatically calculating the required order quantity by comprehensively analyzing sales volume, compounding volume, inventory volume, appropriate quantity, packaging unit, stacking volume, displayable quantity, and storage space characteristics.

[0085] Another objective of the present invention is to provide an order quantity calculation technology that applies the concepts of minimum maintenance amount and maximum retention amount to over-the-counter drugs and considers the stock volume, packaging unit, and displayable quantity to prevent over-ordering while minimizing the risk of stockout.

[0086] Another objective of the present invention is to provide an order automation technology capable of minimizing excess inventory while reducing the risk of prescription drug shortages by providing a primary, non-primary, and manual classification system for prescription drugs and compounded drugs that considers prescription variations, and by providing a technology for calculating a standard appropriate amount that reflects the dispensing volume and daily usage of each drug.

[0087] Another objective of the present invention is to provide a string-based drug attribute analysis technology capable of automatically recognizing specific strings, numbers, and symbols included in a drug name to automatically classify the quantity, packaging unit, discount / surcharge conditions, displayable quantity, and storage location of the drug.

[0088] Another objective of the present invention is to enable the user to customize settings for minimum maintenance quantity, maximum holding quantity, discount / surcharge criteria, classification criteria for main and non-main products, holding days, displayable quantity, and order criteria, so as to respond to operating policies that differ from pharmacy to pharmacy.

[0089] Another objective of the present invention is to provide a storage space management technology that automatically determines the storage location and warehouse availability for each medicine by reflecting the structure and characteristics of the storage space within a pharmacy, and automatically calculates the quantity to be moved from the storage space based on changes in usage over a specific period.

[0090] Another objective of the present invention is to provide an order processing technology capable of automating order tasks by automatically aggregating order items by manufacturer, automatically determining whether the minimum order amount is met, and automatically generating order statements and order messages.

[0091] Another objective of the present invention is to provide an online brokerage platform for pharmaceutical transactions between pharmacies and to improve the speed of emergency pharmaceutical transactions and the efficiency of legal document management by implementing functions such as transaction request registration, transaction acceptance, real-time notification, electronic signature, and automatic generation of transaction records.

[0092] Another objective of the present invention is to provide an integrated pharmaceutical operation automation system that automatically links Point of Sale (POS) data, sales data, dispensing data, and purchasing data to minimize manual input and reduce the workload of pharmacy operators.

[0093] In an order processing automation system based on inventory management according to pharmaceutical classification type and automatic calculation of order quantity according to one embodiment of the present invention, the system comprises: a memory; a communication unit; The electronic device includes a processor connected to the communication unit and memory, wherein the processor receives drug name, drug code, manufacturer, stock quantity, appropriate quantity, sales quantity, dispensing quantity, usage quantity, total purchase unit price, and order data of a drug from a pharmacy's POS (Point of Sale) Safety Stock system, a drug billing program, or an external server, extracts and analyzes string patterns, number patterns, prefixes, suffixes, and symbol patterns for the drug name, and based on the analysis results, applies a preset drug classification standard to classify and determine the drug by mapping it to at least one first to nth code (n is an integer) among over-the-counter drugs (OTC), ethical drugs (ETC), oral preparations, topical preparations, drinks, nutritional supplements, pediatric drugs, patches, herbal granules, veterinary drugs, items stored in storage space, items excluded from discounts, and items excluded from orders, and determines the string of text corresponding to the first to kth symbol (k is an integer) included in the drug name Extracts and calculates the actual quantity, displayable quantity, packaging unit, and discount / surcharge standard quantity; calculates the maximum holding quantity and minimum maintenance quantity by applying the minimum holding factor, maximum holding factor, and standard maximum value as user-configured parameters; calculates the final maximum quantity as the smaller value between the maximum holding quantity and the displayable quantity; calculates the required order quantity based on the difference between the final maximum quantity and the current inventory quantity; performs an order correction operation to convert the required order quantity into an integer by dividing it by the actual quantity to calculate the final reference order quantity; sets the reference order quantity to 0 if the prefix of the drug name corresponds to the order exclusion criteria; determines whether to apply a discount / surcharge based on the total purchase unit price and the standard maximum value; and calculates the final order amount using the reference order quantity and the purchase price.The above final order amounts are summed by manufacturer to calculate the total amount by manufacturer, and the order availability is determined by comparing the total amount by manufacturer with the minimum order amount by manufacturer. At least one condition among immediate order availability, discount / surcharge application availability, manufacturer, storage space classification, and order availability is applied using a logical AND-based intersection filtering method to output the filtering result to the display unit. Based on the filtering result, order request data or message data is generated and transmitted to an external terminal, message transmission server, or order server. The first to nth codes may consist of identifier information already stored in the drug classification database.

[0094] The processor according to one embodiment of the present invention receives dispensing volume and usage data for a certain period for a prescription drug or a compounding drug, analyzes a string pattern included in the drug name to classify it into oral preparations and topical preparations, classifies oral preparations into at least one of a main group, a non-main group, and a manual review group, classifies topical preparations into at least one of a main group, a non-main group, and a manual review group, calculates a standard appropriate amount by applying a standard retention period stored for each group, calculates a first order value by subtracting the current inventory amount from the standard appropriate amount, calculates a determined usage amount by applying a set multiplier value to the usage amount of the day, calculates a second order value by comparing the determined usage amount with the current inventory amount, determines the larger value between the first order value and the second order value as an order evaluation value, sets the order evaluation value as a reference order amount if it is a number and classifies it as a subject for manual review if it is a character value, and if the reference order amount is less than a standard value, applies a standard retention period to correct it to be greater than or equal to the minimum order standard, and for a specific drug, the appropriate amount multiplier value If set, the appropriate amount is multiplied by the corresponding multiplier value to calculate the corrected appropriate amount; if the holding instruction quantity is set for a specific pharmaceutical product, the larger value between the value obtained by subtracting the current inventory quantity from the holding instruction quantity and the order evaluation value is determined as the final reference order quantity; if the maximum displayable quantity is set for a specific pharmaceutical product, the reference order quantity is limited and corrected so as not to exceed the maximum displayable quantity, and the guidance message set for the specific pharmaceutical product can be displayed on the display unit.

[0095] The processor according to one embodiment of the present invention analyzes the sales volume, dispensing volume, consumption volume, volume, weight, packaging size, storage characteristics, and turnover rate of the pharmaceuticals to automatically classify the pharmaceuticals to be stored in the storage space, analyzes the code and symbol patterns included in the pharmaceutical names to classify them into at least one of store display items, warehouse storage items, upper cabinet storage items, lower cabinet storage items, drink items, nutritional supplement items, and discount exclusion items, calculates the difference between the cumulative usage up to a first point in time designated by the user and the cumulative usage up to a second point in time prior to the first point in time to calculate the replenishment quantity to be moved from the storage space, generates a storage space movement list based on the replenishment quantity, outputs the pharmaceuticals to be moved and the moving quantity to a display unit according to the storage space movement list, receives pharmaceutical transaction request information between pharmacies and sends a notification message to a user terminal when the pharmaceuticals to be traded are posted, automatically generates a transaction statement including transaction counterparty information, pharmaceutical information, transaction quantity information, and transaction date and time information when an acceptance input for the transaction request is received, and applies an electronic signature to the transaction statement when an electronic signature input is received. Reflecting and generating a final transaction document, transmitting the final transaction document to a user terminal, an external server, or a message transmission server, and storing and managing the final transaction document as evidence for face-to-face or non-face-to-face transactions, and the processes of storage space classification, movement list generation, transaction request processing, and transaction statement generation and transmission are performed integrally in conjunction with the order processing automation system, and the storage space classification and movement are performed periodically based on differences in consumption amounts by time interval, and the time interval may include multiple reference points defined by user settings or system settings.

[0096] The processor according to one embodiment of the present invention collects disposal record data, order history data, and inter-pharmacy transaction history data based on the expiration of the expiration date of each pharmaceutical product for each of a plurality of pharmacies; obtains first group classification data reclassified into at least one of a main group, a non-main group, and a manual review group through a first model based on the disposal record data and order history data; corrects the standard appropriate amount based on the first group classification data; calculates a first match rate for each group by comparing the first group classification data with the second group classification data, which is the group classification data prior to reclassification; calculates an Eco Risk Score for each pharmaceutical product for groups where the first match rate is less than a preset standard value; calculates a Trade Feasibility Score for each pharmaceutical product based on at least one of the number of transaction requests, the number of transaction successes, the transaction quantity, and the transaction time included in the inter-pharmacy transaction history data; calculates an Adjusted Eco Risk Score by correcting the disposal risk score using the Trade Feasibility Score; and based on the Adjusted Eco Risk Score, the main group, the non-main group, or Reclassification is performed to at least one of the manual review groups, and at least one of the order evaluation value, the standard appropriate quantity, or the reference order quantity is corrected based on the reclassification result and the standard appropriate quantity, and an Environment Score is periodically calculated for each of the plurality of pharmacies based on the corrected disposal risk score, and Environment Points are awarded to user accounts corresponding to each pharmacy based on the Environment Score, and the first model is an artificial intelligence model trained to output group classification results and disposal risk scores by pharmaceutical using disposal record data, order history data, and group classification data as training data, and the disposal risk score is the frequency of disposal occurrence by pharmaceutical, disposal quantity,It is a value calculated based on at least one of the inventory turnover rate and group classification results, the transaction possibility score is a value quantifying the possibility that the medicine will be transferred to another pharmacy, the environment score is a value calculated based on the amount of waste reduction over a certain period and the amount of medicine moved through transactions between pharmacies, the environment point is a compensation value calculated by applying a weight proportional to the amount of reduction when the amount of waste is reduced through transactions between pharmacies, and may include a value that can be deducted once as a correction value for the order amount when determining whether the minimum order amount is satisfied.

[0097] The processor according to one embodiment of the present invention collects pharmaceutical collection history data for each of the pharmacies among a plurality of pharmacies where pharmaceutical collection boxes are installed, generates regional collection data based on the collection history data and location information of the pharmacies where the collection boxes are installed, groups the plurality of pharmacies into a first group according to the units of Eup, Myeon, Dong, or administrative districts based on the location information, groups pharmacies that are different from the matching first group and whose distance between pharmacies is within a preset threshold distance into a second group, calculates whether there is a need to expand collection boxes at each base through a second model trained to determine whether there is a need to expand collection boxes at each base based on the collection history data, and, according to the output result of the second model, identifies the first pharmacy within the first base group where collection box expansion is needed and the second pharmacies excluding the first pharmacy among the first groups, recommends the installation of a collection box to the user account corresponding to the third pharmacy if there is a third pharmacy among the second pharmacies where the first pharmacy does not exist within a preset standard distance, and if the third pharmacy does not exist In the case, a second base group adjacent to the first base group is additionally identified, a fourth pharmacy with a collection box installed within the second base group and fifth pharmacies excluding the fourth pharmacy are identified, and if there is at least one first pharmacy among the fourth pharmacies and a sixth pharmacy grouped into the second group, a seventh pharmacy located within a reference distance from the sixth pharmacy and the first pharmacy grouped into the second group among the fifth pharmacies is identified, and the installation of a collection box is recommended for the user account corresponding to the seventh pharmacy, and if there is no sixth pharmacy, at least one first pharmacy among the fifth pharmacies and an eighth pharmacy grouped into the second group are identified, and the installation of a collection box is recommended for the user account corresponding to the eighth pharmacy.Based on the sales volume of pharmaceuticals handled within the first base group and the transaction history between pharmacies within the first base group and other base groups, the average primary group, average non-primary group, and average manual review group of the first base group are calculated; a group-specific match rate is calculated by comparing the average group with the group for each pharmacy; first recommendation information, which is a list of replaceable pharmaceuticals, is generated for groups where the calculated match rate is less than a threshold value; and second recommendation information, which is a list of additional replaceable pharmaceuticals, is generated for groups where the match rate calculated by comparing the primary group, non-primary group, and manual review group for each pharmacy within the first base group with the average primary group, average non-primary group, and average manual review group is less than a threshold value; and the second model is an artificial intelligence model trained to output collection demand and collection distribution maps by base using collection history data and pharmacy location data of multiple pharmacies as training data; the first recommendation information is provided to accounts for each pharmacy within the first base group, and the second recommendation information can be provided to user accounts corresponding to matching pharmacies. there is.,

[0098] A device according to one embodiment of the present invention may be combined with hardware and controlled by a computer program stored on a medium to execute any one of the operation methods by the processor of the system described above.

[0099] According to the present invention, by automatically classifying general medicines and prescription medicines handled in pharmacies according to different inventory management standards and calculating the order quantity, precise inventory management reflecting the characteristics of each medicine type becomes possible.

[0100] In addition, since the present invention calculates the required order quantity by simultaneously considering sales volume, dispensing volume, inventory volume, optimal quantity, quantity, packaging unit, displayable quantity, and storage space characteristics, it has the effect of significantly reducing the possibility of inventory shortages and excess inventory compared to a simple average-based system.

[0101] In addition, the present invention applies the concepts of minimum maintenance amount and maximum retention amount to over-the-counter medicines and automatically adjusts the order quantity by reflecting the limitations of display space, thereby having the effect of efficiently utilizing the limited space within a pharmacy.

[0102] In addition, the present invention applies a primary, non-primary, and manual classification system to prescription drugs and introduces the concept of assessed usage reflecting daily usage, thereby having the effect of reducing the risk of stock shortages for compounded drugs with large prescription variations.

[0103] In addition, the present invention automatically analyzes the quantity, packaging unit, discount / surcharge conditions, and storage location using specific symbols and strings included in the drug name, thereby having the effect of automatically recognizing drug attributes without the need for separate manual data input.

[0104] In addition, the present invention has the effect of contributing to the reduction of pharmaceutical purchasing costs and the improvement of order efficiency in pharmacies by optimizing order strategies through the automatic determination of discount / surcharge conditions and minimum order amounts.

[0105] In addition, the present invention has the effect of streamlining the inventory replenishment work of pharmacy operators by automatically distinguishing between items held in the warehouse and items for store display through a storage space management function, and by calculating the quantity of items to be moved in the warehouse based on changes in usage over a specific time interval.

[0106] In addition, the present invention has the effect of shortening the order processing time for pharmacy operators and reducing work errors by automatically aggregating order items by manufacturer and automatically generating order messages and order records.

[0107] In addition, the present invention enables the rapid execution of emergency drug transactions through a transaction system between pharmacies and provides an automatic generation function for electronic signature-based transaction records, thereby having the effect of improving the legal stability of drug transactions and the efficiency of document management.

[0108] In addition, the present invention is configured to allow users to customize inventory management policies, storage space structures, and ordering strategies that differ from pharmacy to pharmacy, thereby having the effect of being flexibly applicable to various types of pharmacy operating environments.

[0109] Consequently, the present invention has the effect of significantly contributing to improved pharmacy operational efficiency, reduced inventory costs, reduced risk of stockouts, and enhanced levels of business automation by integrally performing functions of pharmaceutical inventory management, order automation, storage space management, and inter-pharmacy transaction management.

[0110] FIG. 1 is a block diagram schematically illustrating the basic configuration of a device according to one embodiment, and FIG. 2 is a diagram schematically illustrating a system according to one embodiment.

[0111] Referring to FIG. 1, the system of the present invention may include an electronic device (100) comprising a processor (110) and a memory (120). According to one embodiment, the electronic device (100) may be a server or a terminal. According to one embodiment, the processor (110) may be composed of one or more processors (110) such that it is configured to perform operations or data processing regarding the control and / or communication of each component of the electronic device (100). The memory (120) may store information related to the method of performing operations of the processor (110) described above, or store a program in which the method described above is implemented. The memory (120) may be a volatile memory (120) or a non-volatile memory (120).

[0112] According to one embodiment, the processor (110) can execute a program and control a device. The code of the program executed by the processor (110) can be stored in memory (120). Operations of the processor (110) can be performed by loading instructions stored in memory (120). The electronic device (100) can be connected to an external device (e.g., a personal computer or a network) through an input / output device (not shown in the drawing) and exchange data.

[0113] According to one embodiment, there are no limitations on the computation and data processing functions that the processor (110) can implement on the electronic device (100), but the process processing functions of the system of the present invention will be described below.

[0114] Additionally, the electronic device (100) according to one embodiment may further include a communication unit (130).

[0115] The electronic device (100) is connected to a communication unit (130) and, as shown in FIG. 2, can transmit and receive signals and / or data to and from other electronic devices, such as a user terminal (200), or other servers through the communication unit (130). The communication unit (130) may be provided with a conductive line or a wireless communication chip, etc.

[0116] For example, the user terminal (200) may be an electronic device already registered for an account registered in the system, and may be provided as a smartphone, PC, laptop, tablet, POS (Point of Sale) device, etc., but is not limited thereto.

[0117] Hereinafter, the operation of the processor (110) can be described as the operation of the electronic device (100).

[0118] FIGS. 3 and 4 are basic operation flowcharts of a method according to one embodiment.

[0119] Referring to FIG. 3, a processor (110) according to one embodiment of the present invention can receive (S310) drug name, drug code, manufacturer, stock quantity, appropriate quantity, sales quantity, dispensing quantity, usage quantity, total purchase unit price, and order data of a drug from a pharmacy's POS Safety Stock system, a drug billing program, or an external server.

[0120] The processor (110) can extract and analyze string patterns, number patterns, prefixes, suffixes, and symbol patterns for the drug name (S320).

[0121] The processor (110) can classify and determine (S330) the pharmaceuticals by applying a preset drug classification standard based on the analysis results and mapping them to at least one of the following: over-the-counter drugs (OTC), ethical drugs (ETC), oral preparations, topical preparations, drinks, nutritional preparations, pediatric medicines, patches, herbal granules, veterinary medicines, items stored in storage space, items excluded from discounts, and items excluded from orders, by mapping them to a first code to an n-th code (n is an integer).

[0122] The processor (110) can extract strings of text corresponding to the first to kth symbols (k is an integer) included in the drug name to calculate the number of items, the displayable quantity, the packaging unit, and the discount / surcharge standard quantity (S340).

[0123] Here, the quantity may be a quantity corresponding to the minimum order unit or packaging unit set by the manufacturer or supplier, and may be used as a reference value to adjust the order quantity to an appropriate order unit.

[0124] For example, if the medicine is a single unit, it may not be reflected, and it may be reflected as the number of bottles.

[0125] For example, the range of items eligible for discounts and surcharges can be adjusted for each pharmacy. For instance, the processor (110) can receive data regarding the range of items eligible for discounts and surcharges from the pharmacy's POS Safety Stock system, a drug billing program, or an external server. The processor (110) can calculate the standard quantity for discounts and surcharges based on the data regarding the range of items. By adjusting the range of items eligible for discounts and surcharges in this way, it is possible to prevent, for instance, pharmacies from ordering only a small quantity of drugs compared to the actual number of drugs eligible for discounts and surcharges, and abandoning the order of the remaining drugs, depending on the size of the pharmacy. Furthermore, this adjustment of the range can prevent small pharmacies from suffering losses due to low benefits compared to the maintenance costs of the warehouse and management costs of the stored drugs (e.g., labor, temperature control, etc.) required to store the drugs ordered according to the discounted order quantity.

[0126] The processor (110) can calculate the maximum holding amount and minimum holding amount (S350) by applying the minimum holding factor, the maximum holding factor, and the reference maximum value as user-set parameters. According to one embodiment, the reference usage amount may be reference consumption amount information calculated based on sales volume, dispensing volume, usage volume, or a combination thereof during a specific period.

[0127] For example, the maximum retention amount may be calculated by applying a maximum retention factor to a standard usage amount derived from sales volume, dispensing volume, usage amount, or a combination thereof, and the minimum maintenance amount may be calculated by applying a minimum retention factor to the aforementioned standard usage amount. However, this is not limited thereto, and various formulas may be applied depending on the pharmacy's operational policy.

[0128] For example, the reference usage can be calculated using at least one of the average value, moving average value, or weighted average value of the sales volume, dispensing volume, or usage volume during a recently set period.

[0129] The processor (110) can calculate the smaller value between the maximum holding amount and the displayable quantity as the final maximum amount (S360). According to one embodiment, the final maximum amount may refer to the maximum target inventory amount that can be maintained during the inventory management process for each pharmaceutical product, and may be determined as the smaller value between the maximum holding amount and the displayable quantity.

[0130] The processor (110) can calculate the required order quantity (S370) based on the difference between the final maximum quantity and the current inventory quantity.

[0131] For example, the required order quantity may refer to the additional quantity that needs to be secured to meet the target inventory level.

[0132] For example, after performing step S370, if an order request is received from a user terminal (200) for a required order quantity or a value changed thereto by user selection, the processor (110) may store a list of medicines corresponding to the order request in a shopping cart of a pharmacy account corresponding to the user terminal (200), and provide information about the medicines stored in the shopping cart to the user terminal (200) through a message, a pop-up window, etc.

[0133] Referring to FIG. 4, the processor (110) can calculate the final reference order quantity (S410) by performing an order correction operation to convert the required order quantity into an integer by dividing it by the number of items. Specifically, the order correction operation may be a method of calculation that divides the required order quantity by the number of items, which is the minimum handling and sales unit set for each medicine, and then performs an integer conversion operation to remove the decimal point from the value divided by the number of items, and then reflects the packaging unit, which is the order package unit required by the pharmaceutical company when receiving an order from a pharmacy.

[0134] For example, the reference order quantity may be a recommended order quantity calculated by the system, serving as a value provided as a criterion for determining whether to place an actual order or the order quantity. As an example, the reference order quantity may be a recommended order quantity calculated by applying a cumulative value, a correction rule, or a user-defined condition to the required order quantity. As an example, if the drug name contains a string indicating the displayable quantity, the correction rule may include a correction operation in which the final reference order quantity is divided by the packaging unit of the corresponding drug, rounded down to the second decimal place, and then multiplied by the packaging unit. Additionally, if the drug name does not contain a string indicating the displayable quantity, the correction rule may include a correction operation in which the final reference order quantity is divided by the packaging unit of the corresponding drug, rounded up to the second decimal place, and then multiplied by the packaging unit.

[0135] At this time, in step S410, the processor (110) can set the reference order quantity to 0 if the prefix of the drug name corresponds to the order exclusion criteria.

[0136] After step S410, the processor (110) can determine whether to apply a discount / surcharge based on the total purchase unit price and the standard maximum value (S420).

[0137] The processor (110) can calculate the final order amount (S430) using the reference order quantity and the purchase price.

[0138] The processor (110) can calculate the total amount by manufacturer by summing the final order amounts by manufacturer (S440).

[0139] The processor (110) can determine whether an order is possible (S450) by comparing the total amount by manufacturer with the minimum order amount by manufacturer.

[0140] After step S450, the processor (110) can output a filtering result to the display unit by applying at least one condition among whether an immediate order is made, whether a discount / surcharge is applied, the manufacturer, the storage space classification, and whether an order is possible using a logical AND-based intersection filtering method.

[0141] For example, an AND-based intersection filtering method may be a method that selects the relevant medicine as an output target only when multiple conditions among immediate order status, discount / surcharge application status, manufacturer, storage space classification, and order availability are all satisfied.

[0142] The processor (110) can generate order request data or message data based on the filtering result and transmit it to a user terminal (200), an external terminal, a message transmission server, or an order server.

[0143] The first to nth codes may consist of identifier information already stored in a drug classification database.

[0144] For example, a drug classification database may be configured to include a plurality of table structures as a means of storing basic information for performing automatic classification and order processing of pharmaceuticals.

[0145] Specifically, the drug classification database may include a drug information table that stores basic drug information, a classification criteria table that stores classification criteria information for each drug, and a code mapping table that stores identifier information corresponding to symbols and string patterns included in the drug name or drug code.

[0146] The drug information table may store at least one piece of information among drug code, drug name, manufacturer, stock quantity, appropriate quantity, sales quantity, dispensing quantity, usage amount, and total purchase unit amount.

[0147] The classification criteria table may store a classification identifier corresponding to at least one of general medicines, prescription medicines, oral preparations, topical preparations, drinks, nutritional supplements, items for storage space, items excluded from discounts, and items excluded from orders, and a judgment rule corresponding to each classification.

[0148] The code mapping table stores classification codes corresponding to the prefix, suffix, numeric string, and symbol pattern of the drug name, and the classification codes may consist of the first to nth codes that are uniquely defined within the drug classification database.

[0149] Additionally, the database may further include a manufacturer information table that stores minimum order amount information by manufacturer, and the manufacturer information table may store manufacturer identification information and the minimum order standard amount for the corresponding manufacturer.

[0150] The database configured as described above is called by the processor (110) and linked with the results of string and symbol analysis based on drug names, and can be used in the automatic classification of drugs, calculation of order quantities, classification of storage spaces, and transaction processing processes.

[0151] According to one embodiment, inventory management and order processing for over-the-counter (OTC) drugs may begin with receiving information on the drug name, manufacturer, inventory quantity, and sales quantity from a Point of Sale (POS) system or an external server.

[0152] Afterward, the processor (110) can analyze the string, number, and symbol patterns included in the drug name and map the drug to one of the classification codes, such as general medicine, drink, or nutritional supplement.

[0153] Additionally, the processor (110) can extract the number of items, the displayable quantity, and the packaging unit based on the symbol information included in the drug name, and calculate the maximum holding quantity and the minimum holding quantity according to user setting parameters.

[0154] The processor (110) can determine the final maximum quantity based on the smaller value between the calculated maximum holding quantity and the displayable quantity, and calculate the required order quantity by subtracting the current inventory quantity.

[0155] For example, the displayable quantity may refer to the maximum allowable quantity of a specific medicine that can be displayed or stored within a pharmacy, and may be used as an upper limit to prevent excessive stockpiling. According to one embodiment, the displayable quantity may be the maximum quantity of medicine that can actually be placed in the pharmacy's display space, storage space, or designated storage location. For example, the displayable quantity may be set based on at least one of the display shelf size, storage container capacity, the allowable quantity per storage location, or a user-defined value. However, it goes without saying that it is not limited thereto.

[0156] Subsequently, the processor (110) performs a correction operation to convert the required order quantity into an integer by dividing it by the number of orders to generate a final reference order quantity, and based on the result, order data and message data for each manufacturer are automatically generated and transmitted to an external server.

[0157] According to one embodiment, the user's manual inventory management work can be reduced by the above-described automatic classification and order quantity calculation process, and the possibility of excess inventory or shortage of inventory for each pharmaceutical product can be reduced.

[0158] In addition, by simultaneously considering the stock volume, display capacity, and minimum order amount per manufacturer, the actual orderable quantity can be automatically calculated, thereby improving order accuracy and business processing efficiency.

[0159] In addition, by providing intersection-based filtering for multiple filter conditions, users can quickly search for drugs to order and reduce order review time.

[0160] According to one embodiment, the drug classification database may include a data storage structure for performing automatic classification of drugs, inventory management, order quantity calculation, and order processing functions.

[0161] The drug classification database may include at least one of a drug information table, a classification criteria table, a code mapping table, and a manufacturer information table, and each table may be implemented as a logical data structure and may be implemented as a database table, a file structure, an object storage structure, or other data storage structure.

[0162] The drug information table may store at least one of the following: drug code, drug name, manufacturer, stock quantity, appropriate quantity, sales quantity, dispensing quantity, usage quantity, total purchase unit price, storage location information, actual quantity information, displayable quantity information, and order history information.

[0163] The classification criteria table may store classification identifier information corresponding to at least one of over-the-counter drugs, prescription drugs, oral preparations, topical preparations, drinks, nutritional supplements, items stored in storage space, items excluded from discounts, items excluded from orders, core groups, non-core groups, and manual review groups, as well as string conditions, symbol conditions, numeric conditions, or user-defined conditions for determining the corresponding classification. A core group may refer to a set of drugs that are managed preferentially during inventory operations and order management processes. A non-core group may refer to a set of drugs with a relatively low frequency of use or transaction.

[0164] The code mapping table may store first to nth codes corresponding to prefixes, suffixes, numeric strings, special symbols, or character patterns included in the drug name or drug code.

[0165] The processor (110) can convert a string pattern extracted from a drug name or drug code into a corresponding classification code by referring to a code mapping table, and can perform classification of the drug, determination of storage space, determination of order exclusion, determination of discount application, or determination of balance using the converted classification code.

[0166] The manufacturer information table may store at least one of manufacturer identification information, manufacturer name, minimum order amount, discount standard amount, surcharge standard amount, order availability information, order transmission information, and manufacturer-specific order policy information.

[0167] The processor (110) can aggregate the order amount by manufacturer by referring to the manufacturer information table, determine whether the minimum order amount is met, and determine whether to apply a discount or a surcharge.

[0168] Additionally, the drug classification database may further include a user setting table, and the user setting table may store at least one of a minimum retention factor, a maximum retention factor, a standard maximum value, a standard retention period, a judgment usage multiplier value, an appropriate amount multiplier value, a retention instruction quantity, a limit value for the quantity that can be displayed, and a filtering condition.

[0169] The processor (110) can call a value stored in a user setting table to perform inventory management and order processing operations corresponding to the pharmacy-specific operation policy.

[0170] According to the present invention, inventory management and order processing operations are performed automatically to prevent the return of pharmaceuticals due to over-ordering and poor sales, thereby reducing the amount of pharmaceuticals wasted.

[0171] For example, the processor (110) may select a pharmacy among multiple pharmacies based on the number of returned medicines within a recent period, or a pharmacy with a return quantity less than a certain quantity, and select it as a target to receive a certificate certifying an order-excellent pharmacy (e.g., a clean order exemplary pharmacy).

[0172] Meanwhile, a processor (110) according to one embodiment of the present invention can receive data on the dispensing amount and usage amount for a certain period of time for a prescription drug or a compounding drug.

[0173] The processor (110) can classify the drug into oral and topical preparations by analyzing the string pattern included in the drug name.

[0174] The processor (110) can classify oral medications into at least one of a main group, a non-main group, and a passive review group.

[0175] According to one embodiment, the main group may be a group of pharmaceuticals in which at least one of sales volume, dispensing volume, usage volume, inventory turnover rate, transaction frequency, or profit contribution is relatively high.

[0176] The non-core group may be a group of pharmaceuticals with at least one of sales volume, dispensing volume, usage volume, inventory turnover, transaction frequency, or profit contribution being relatively low.

[0177] For example, if the dosage amount is a multiple of 30, the area where the dosage amount is listed on the dosage amount and usage data can be indexed by the processor (110).

[0178] The manual review group may be a group of drugs corresponding to cases where the variability of the above indicators is greater than or equal to a threshold value, or where the reliability of the automatic classification result is less than a threshold value. As an example, the manual review group may be set for drugs where the sales volume, usage volume, or inventory variability exceeds a preset threshold range, or where the reliability of the automatic judgment is less than a threshold value.

[0179] The processor (110) can determine the main group, non-main group, and manual review group based on the above indicators, or perform reclassification among the groups according to the output result of the first model.

[0180] Accordingly, the processor (110) can classify external preparations into at least one of a main group, a non-main group, and a manual review group.

[0181] The processor (110) can calculate the standard appropriate amount by applying the standard retention period stored for each group.

[0182] The processor (110) can calculate a first order value by subtracting the current inventory amount from the reference appropriate amount. For example, the first order value can be calculated as the value obtained by subtracting the current inventory amount from the reference appropriate amount.

[0183] The processor (110) can calculate the determined usage amount by applying a set multiplier value to the daily usage amount.

[0184] The processor (110) can calculate a second order value by comparing the judgment usage amount with the current inventory amount. For example, the second order value can be calculated by subtracting the current inventory amount from the judgment usage amount.

[0185] The processor (110) can determine the larger value between the first order value and the second order value as the order evaluation value.

[0186] The processor (110) can set the order evaluation value as a reference order quantity if it is a number and classify it as a manual review target if it is a character value.

[0187] The processor (110) can apply a reference holding period when the reference order quantity is less than the reference value to adjust it to be greater than the minimum order standard.

[0188] The processor (110) can calculate a corrected appropriate amount by multiplying the appropriate amount by the corresponding multiplier value when an appropriate amount multiplier value is set for a specific medicine.

[0189] When a holding instruction quantity is set for a specific medicine, the processor (110) can determine the larger value between the value obtained by subtracting the current stock quantity from the holding instruction quantity and the order evaluation value as the final reference order quantity.

[0190] The processor (110) can limit and adjust the reference order quantity so as not to exceed the maximum display quantity when the maximum display quantity is set for a specific medicine.

[0191] For example, oral and topical preparations within the core and non-core groups may have a minimum order quantity per order set to a 7-day supply to resolve the issue of requiring relatively frequent orders compared to other medicines due to small reference order quantities. Specifically, for oral and topical preparations, if the calculated reference order quantity for the core or non-core group is greater than 0, and the reference order quantity for the medicine is less than the value obtained by multiplying the standard appropriate amount for the medicine by 7 and dividing by 30, the reference order quantity is changed to the value obtained by multiplying the standard appropriate amount by 7 and dividing by 30; however, if the reference order quantity for the medicine is equal to or greater than the value obtained by multiplying the standard appropriate amount by 7 and dividing by 30, the reference order quantity for the medicine may be maintained. For instance, the standard appropriate amount may be the dispensing quantity of the corresponding medicine within a certain period.

[0192] The processor (110) can output a set instruction message for a specific medicine to the display unit. For example, the electronic device (100) may further include a display unit that visualizes and outputs data, or control the output of data through a display unit provided in an external device such as a user terminal (200). As an example, the display unit may be a screen display device such as a display.

[0193] According to another embodiment, data on the dispensing amount and usage amount for a certain period of time for a prescription drug or a compounding drug can be received by the processor (110).

[0194] The processor (110) analyzes the string pattern included in the drug name to classify it into oral preparations and topical preparations, and can classify each drug into one of the main group, non-main group, or manual review group.

[0195] The processor (110) can calculate a standard appropriate amount by applying the standard holding days set for each group and generate a first order value by subtracting the current inventory amount from the appropriate amount.

[0196] Additionally, the processor (110) can calculate the determined usage amount by applying a set multiplier value to the daily usage amount, and calculate the second order value by comparing the determined usage amount with the current inventory amount.

[0197] The processor (110) can determine the larger value between the first order value and the second order value as the order evaluation value, wherein if the value is a number, it is set as a reference order quantity, and if it is a character, it can be classified as a subject for manual review.

[0198] Afterwards, the order quantity can be corrected by the processor (110) according to the holding instruction quantity, the maximum displayable quantity, and the multiplier setting value, and the final reference order quantity can be determined.

[0199] A processor (110) according to one embodiment of the present invention can automatically classify pharmaceuticals to be stored in a storage space by analyzing the sales volume, dispensing volume, consumption volume, volume, weight, packaging size, storage characteristics, and turnover rate of the pharmaceuticals.

[0200] For example, storage characteristics may be information indicating the storage location, storage method, or space utilization characteristics of the medicine. Storage characteristics may include at least one of whether it is subject to warehouse storage, whether it is subject to store display, whether it is subject to upper cabinet storage, whether it is subject to lower cabinet storage, whether it is subject to refrigerated storage, whether it is subject to room temperature storage, whether it is subject to large packaging, whether it is a heavy item, whether it is a drink, and whether it is subject to priority display based on turnover rate. The processor (110) can determine the storage location of the medicine or determine whether it is subject to relocation of the storage space based on the storage characteristics.

[0201] Accordingly, the processor (110) can analyze the code and symbol patterns included in the drug name and classify it into at least one of store display items, warehouse storage items, upper cabinet storage items, lower cabinet storage items, drink items, nutritional supplement items, and discount exclusion items.

[0202] The processor (110) can calculate the difference between the cumulative usage up to a first point in time designated by the user and the cumulative usage up to a second point in time prior to the first point in time and calculate the amount of replenishment to be moved from the storage space.

[0203] The processor (110) can generate a storage space movement list based on the replenishment quantity. Accordingly, medicines with a high turnover rate can be placed in appropriate locations, and the efficiency of storage space utilization and dispensing work can be improved. In addition, the storage space can be managed efficiently by preventing the excessive display of medicines that are not used for a long period of time.

[0204] Furthermore, the processor (110) can output the medicine to be moved and the quantity moved according to the storage space movement list to the display unit.

[0205] The processor (110) receives information on requests for drug transactions between pharmacies and can send a notification message to the user terminal (200) when the drugs subject to transaction are posted.

[0206] When an acceptance input for a transaction request is received, the processor (110) can automatically generate a transaction statement including transaction counterparty information, drug information, transaction quantity information, and transaction date and time information.

[0207] When an electronic signature input is received, the processor (110) can reflect the electronic signature in the transaction statement and generate the final transaction document.

[0208] The processor (110) can transmit the final transaction document to a user terminal (200), an external server, or a message transmission server.

[0209] The processor (110) can store and manage the final transaction document as proof for face-to-face or non-face-to-face transactions. Accordingly, the disposal of medicines nearing their expiration date can be reduced, and the overall efficiency of medicine distribution can be improved by promoting inventory circulation between pharmacies.

[0210] The processes of storage space classification, move list generation, transaction request processing, and transaction statement generation and transmission can be performed integrally in conjunction with the order processing automation system.

[0211] Storage space classification and movement can be performed periodically based on differences in consumption over time intervals.

[0212] The time interval may include multiple reference points defined by user settings or system settings.

[0213] According to another embodiment, based on information regarding the sales volume, dispensing volume, volume, weight, and turnover rate of the medicines, the medicines to be stored in the storage space can be automatically classified by the processor (110).

[0214] The processor (110) can classify the medicine into one of the storage locations, such as a store, warehouse, upper cabinet, or lower cabinet, by analyzing the code and symbol information included in the medicine name.

[0215] Afterward, the processor (110) can calculate the difference in cumulative usage between the first time point and the second time point to determine the amount of replenishment to be moved from the storage space, and based on this, generate a storage space movement list.

[0216] For example, the replenishment quantity may refer to the quantity of medicines that need to be moved from the storage space to the display space or usage space.

[0217] For example, the storage space transfer list may be a data set containing information on the drugs to be transferred and information on the quantity transferred.

[0218] Additionally, when information regarding a request for a drug transaction between pharmacies is received, the processor (110) sends a notification message to the user terminal (200), and when the user (pharmacy) accepts the transaction through the user terminal (200), it can automatically generate a transaction statement including information on the counterparty, drug information, and transaction quantity information.

[0219] For example, a transaction statement may be a transaction proof document containing information on the counterparty, information on the drugs traded, information on the quantity traded, and information on the date and time of the transaction.

[0220] When an electronic signature input is received, the processor (110) can generate a final transaction document with the signature reflected in the transaction record, and transmit the document to an external server or message transmission server so that it can be stored and managed at the transmitted location.

[0221] In addition, the storage space transfer and transaction processing processes can be performed integrally in conjunction with the order processing automation system.

[0222] Meanwhile, a processor (110) according to one embodiment of the present invention can collect disposal record data, order history data, and transaction history data between pharmacies based on the expiration of the expiration date of each medicine for each of the plurality of pharmacies.

[0223] The processor (110) can obtain first group classification data that is reclassified into at least one of a main group, a non-main group, and a manual review group through a first model based on waste record data and order history data.

[0224] The processor (110) can correct the standard appropriate amount based on the first group classification data.

[0225] The processor (110) can calculate a first matching rate for each group by comparing the second group classification data and the first group classification data, which are group classification data prior to reclassification.

[0226] The processor (110) can calculate an Eco Risk Score for each drug for groups where the first match rate is less than a preset threshold value.

[0227] The processor (110) can calculate a trade feasibility score for each drug based on at least one of the number of transaction requests, the number of transaction successes, the transaction quantity, and the transaction time included in the transaction history data between pharmacies.

[0228] For example, as the transaction possibility score increases, the disposal risk score may be adjusted in a decreasing direction, and if the transaction possibility score is below a threshold value, the disposal risk score may be maintained or adjusted in an increasing direction.

[0229] The processor (110) can calculate an Adjusted Eco Risk Score by adjusting the Eco Risk Score using the transaction possibility score.

[0230] The processor (110) can perform reclassification into at least one of a main group, a non-main group, or a manual review group based on the corrected disposal risk score.

[0231] The processor (110) can correct at least one of the order evaluation value, the reference appropriate amount, or the reference order amount based on the reclassification result and the reference appropriate amount.

[0232] The processor (110) can periodically calculate an Environment Score for each of the multiple pharmacies based on the corrected disposal risk score.

[0233] The processor (110) can award Environment Points to user accounts corresponding to each pharmacy based on the environment score.

[0234] The first model may be an artificial intelligence model trained to output group classification results and disposal risk scores by pharmaceutical product using disposal record data, order history data, and group classification data as training data.

[0235] According to one embodiment, the first model may be implemented as a supervised learning-based classification model, a neural network model, a Random Forest model, a gradient boosting model, or a combination thereof.

[0236] The input data of the first model may include at least one of the disposal frequency, disposal quantity, inventory turnover rate, number of orders, order quantity, usage amount, current group classification information, and transaction history information by drug.

[0237] The first model can be trained to output group reclassification results or disposal risk scores based on input data.

[0238] The disposal risk score may be a value calculated based on at least one of the disposal frequency, disposal quantity, inventory turnover rate, and group classification results for each drug.

[0239] The transaction potential score can be a numerical value representing the likelihood that a drug will be transferred to another pharmacy.

[0240] The environmental score may be a value calculated based on the reduction in waste over a certain period and the volume of pharmaceutical movement through transactions between pharmacies.

[0241] For example, the reduction in disposal may be defined as the difference between the quantity of pharmaceutical waste generated during a reference period and the quantity generated during a comparison period for a specific pharmacy. For instance, the reference period may be the previous month or previous quarter, and the comparison period may be the current month or current quarter. Alternatively, the reduction in disposal may be defined as the decrease in disposal volume at that pharmacy relative to the average disposal volume of multiple pharmacies for the same drug or the same classification group.

[0242] According to one embodiment, the environmental score is a numerical value calculated based on the amount of waste reduction over a certain period and the amount of pharmaceuticals moved through transactions between pharmacies, and may be a value that quantifies the contribution to waste reduction and the efficiency of pharmaceutical circulation. Specifically, the environmental score may be calculated by including a first weighting value proportional to the amount of waste reduction and a second weighting value proportional to the quantity of pharmaceuticals moved to other pharmacies through transactions between pharmacies.

[0243] Environmental points may be a reward value calculated by applying a weight proportional to the amount of reduction when the amount of waste is reduced through transactions between pharmacies.

[0244] Additionally, the environment points may include a one-time deductible value as a correction value for the order amount when determining whether the minimum order amount is met.

[0245] According to one embodiment, the environmental point is a reward value calculated based on the environmental score, and may be a value intended to provide incentives for reducing waste and circulating pharmaceuticals through transactions between pharmacies.

[0246] Additionally, Environment Points may be applied as a one-time deduction to the order amount during the process of determining whether the minimum order amount is met, and this can be used as a correction factor when determining order eligibility. For example, if the order amount is less than the minimum order amount, Environment Points can be applied to the order amount to correct for compliance with the minimum order amount.

[0247] Additionally, environmental points can be accumulated and stored in the user account and can be used for at least one of the following: order amount adjustment, service usage benefits, collection box operation incentives, or transaction fee reduction.

[0248] Meanwhile, a processor (110) according to one embodiment of the present invention can collect pharmaceutical collection history data for each of the pharmacies among a plurality of pharmacies where a pharmaceutical collection box is installed.

[0249] The processor (110) can generate regional collection data based on collection history data and location information of pharmacies where collection boxes are installed.

[0250] The processor (110) can group multiple pharmacies into a first group according to the unit of town, township, dong or administrative district based on location information.

[0251] The processor (110) can group pharmacies that are different from the first matching group and have a distance between them within a preset threshold distance into a second group.

[0252] According to one embodiment, the matching of the first group may refer to the relationship between identical or corresponding base groups based on administrative district units or location-based cluster information. Specifically, the matching first group may refer to a group formed by additionally configuring a set of pharmacies into corresponding second groups, provided that, after classifying multiple pharmacies into a first group based on administrative district units or location-based clusters, the physical distance or movable distance between pharmacies exists within a preset threshold distance even between different first groups. For example, if Pharmacy A and Pharmacy B have the same first group, Group C, the matching first groups are identical; conversely, if Pharmacy A has the same first group, but Pharmacy B has the same first group, Pharmacy A and Pharmacy B can be identified as having different first groups. In this case, if the matching first groups are different and the physical distance between Pharmacy A and Pharmacy B is within a preset threshold distance, Pharmacy A and Pharmacy B may be grouped into Group E. Therefore, Pharmacy A may belong to Group C and Group E, and Pharmacy B may belong to Group D and Group E. In this case, Group E can be classified into the aforementioned Group 2. That is, Group 2 can be defined as a set of pharmacies that satisfy distance-based adjacency among pharmacies belonging to different Group 1.

[0253] The processor (110) can calculate whether there is a need to increase the collection bins at each base through a second model trained to determine whether there is a need to increase the collection bins at each base based on collection history data.

[0254] The processor (110) can identify, based on the output result of the second model, the first pharmacy and the second pharmacy excluding the first pharmacy within the first base group that requires an expansion of the collection box among the first groups.

[0255] The processor (110) may recommend the installation of a collection box for the user account corresponding to the third pharmacy if there is a third pharmacy among the second pharmacies where the first pharmacy does not exist within a pre-set standard distance.

[0256] If there is no third pharmacy, the processor (110) can additionally identify a second base group adjacent to the first base group.

[0257] The processor (110) can identify the fourth pharmacy and the fifth pharmacy excluding the fourth pharmacy, in which a collection box is installed within the second base group.

[0258] If there is at least one first pharmacy among the fourth pharmacy and a sixth pharmacy grouped into a second group, the processor (110) can identify a seventh pharmacy located within a reference distance from the sixth pharmacy among the fifth pharmacy and the first pharmacy grouped into a second group with the sixth pharmacy and recommend the installation of a collection box for the user account corresponding to the seventh pharmacy.

[0259] If the 6th pharmacy does not exist, the processor (110) may identify at least one of the 5th pharmacies, the 1st pharmacy, and the 8th pharmacy grouped into the 2nd group, and recommend the installation of a collection box for the user account corresponding to the 8th pharmacy.

[0260] The processor (110) can calculate the average main group, average non-main group, and average manual review group of the first base group based on the sales volume of pharmaceuticals handled within the first base group and the transaction history between pharmacies within the first base group and other base groups.

[0261] The processor (110) can calculate the group-specific match rate by comparing the average group with each pharmacy-specific group, and generate first recommendation information, which is a list of alternative medicines, for groups where the calculated match rate is less than the reference value.

[0262] For example, the group agreement rate may be a value representing the similarity between the group classification result of a specific pharmacy and the average group classification result of a base group.

[0263] The processor (110) can generate second recommendation information, which is a list of additional alternative medicines, for groups where the match rate calculated through comparison between the main group, non-main group, and manual review group for each pharmacy within the first base group and the average main group, average non-main group, and average manual review group is less than a threshold.

[0264] The second model may be an artificial intelligence model trained to output collection demand and collection distribution maps by base using collection history data and pharmacy location data from multiple pharmacies as training data.

[0265] According to one embodiment, the second model may include a cluster analysis model, a demand forecasting model, a regression model, or a neural network model.

[0266] The input data of the second model may include at least one of the number of collections, the quantity of collections, the collection cycle, pharmacy location information, population density information, regional pharmaceutical sales volume information, and pharmacy count information.

[0267] The second model can output a collection demand score or whether there is a need to expand collection bins based on input data.

[0268] For example, the collection distribution map is a value obtained by distributing pharmaceutical collection history data generated at multiple pharmacies or bases according to spatial location information, and may be data representing the pattern of collection occurrence at a specific region or base unit.

[0269] For example, the processor (110) can identify drugs with a high probability of being substituted based on the sales volume, usage, transaction history, disposal history, and information on the same therapeutic group of drugs belonging to the group, and generate a recommendation list as recommendation information.

[0270] The first recommendation information can be provided to pharmacy-specific accounts within the first base group.

[0271] The second recommendation information may be provided to the user account corresponding to the matching pharmacy.

[0272] According to one embodiment, the reference distance and threshold distance are values ​​set based on the physical distance or movable distance between pharmacies, and may be reference values ​​for determining the possibility of interaction between pharmacies within the same or similar cluster.

[0273] According to one embodiment of the present invention, by automating the automatic classification of pharmaceuticals, inventory analysis, and order quantity calculation, not only is the efficiency of inventory management improved, but the disposal of pharmaceuticals nearing their expiration date and the pharmaceutical circulation rate can also be improved through a transaction function between pharmacies.

[0274] In addition, according to one embodiment of the present invention, the possibility of excess inventory occurrence can be reduced through artificial intelligence-based group reclassification and disposal risk prediction.

[0275] In addition, according to one embodiment of the present invention, the efficiency of collecting expired medicines can be improved by optimizing the installation location of collection bins, and an eco-friendly medicine distribution ecosystem can be established through an environmental score and environmental point system.

[0276] In addition, according to one embodiment of the present invention, the efficiency of establishing an infrastructure for collecting expired medicines can be improved by predicting areas requiring the installation of collection bins based on regional collection history data and pharmacy location information.

[0277] A device according to one embodiment of the present invention may be controlled by a computer program stored in a medium to execute any one of the operation methods by the processor (110) of the system described above, in combination with hardware.

[0278] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0279] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0280] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0281] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0282] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 In an automated order processing system based on inventory management according to pharmaceutical classification types and automatic calculation of order quantities, memory; communication unit; The electronic device includes a processor connected to the communication unit and memory, wherein the processor receives drug name, drug code, manufacturer, stock quantity, appropriate quantity, sales quantity, dispensing quantity, usage quantity, total purchase unit price, and order data of a drug from a pharmacy's POS (Point of Sale) Safety Stock system, a drug billing program, or an external server, extracts and analyzes string patterns, number patterns, prefixes, suffixes, and symbol patterns for the drug name, and based on the analysis results, applies a preset drug classification standard to classify and determine the drug by mapping it to at least one first code to nth code (n is an integer) among over-the-counter drugs (OTC), ethical drugs (ETC), oral preparations, topical preparations, drinks, nutritional supplements, pediatric drugs, patches, herbal granules, veterinary drugs, items stored in storage space, items excluded from discounts, and items excluded from orders, and determines the string of text corresponding to the first to kth symbol (k is an integer) included in the drug name Extracts and calculates the actual quantity, displayable quantity, packaging unit, and discount / surcharge standard quantity; calculates the maximum holding quantity and minimum maintenance quantity by applying the minimum holding factor, maximum holding factor, and standard maximum value as user-configured parameters; calculates the final maximum quantity as the smaller value between the maximum holding quantity and the displayable quantity; calculates the required order quantity based on the difference between the final maximum quantity and the current inventory quantity; performs an order correction operation to convert the required order quantity into an integer by dividing it by the actual quantity to calculate the final reference order quantity; sets the reference order quantity to 0 if the prefix of the drug name corresponds to the order exclusion criteria; determines whether to apply a discount / surcharge based on the total purchase unit price and the standard maximum value; calculates the final order amount using the reference order quantity and the purchase price; and calculates the total amount by manufacturer by summing the final order amounts by manufacturer.An automated order processing system for inventory management and automatic calculation of order quantity according to pharmaceutical classification types, characterized by determining whether an order is possible by comparing the total amount by manufacturer and the minimum order amount by manufacturer, applying at least one condition among immediate order status, discount / surcharge application status, manufacturer, storage space classification, and order availability using a logical AND-based intersection filtering method, outputting the filtering result to a display unit, generating order request data or message data based on the filtering result and transmitting it to an external terminal, a message transmission server, or an order server, wherein the first to nth codes are composed of identifier information already stored in a pharmaceutical classification database. Claim 2 In claim 1, the processor receives dispensing volume and usage data for a certain period for prescription drugs or compounding drugs, analyzes string patterns included in the drug name to classify them into oral preparations and topical preparations, classifies oral preparations into at least one of a main group, a non-main group, and a manual review group, classifies topical preparations into at least one of a main group, a non-main group, and a manual review group, calculates a standard appropriate amount by applying the standard retention period stored for each group, calculates a first order value by subtracting the current inventory amount from the standard appropriate amount, calculates a judgment usage amount by applying a set multiplier value to the usage amount of the day, calculates a second order value by comparing the judgment usage amount with the current inventory amount, determines the larger value between the first order value and the second order value as the order evaluation value, sets the order evaluation value as a reference order amount if it is a number and classifies it as a subject for manual review if it is a character value, and if the reference order amount is less than the standard value, applies the standard retention period to correct it to be greater than or equal to the minimum order standard, and for a specific drug, the appropriate amount An automated order processing system based on inventory management and automatic calculation of order quantity according to pharmaceutical classification types, characterized by calculating a corrected appropriate amount by multiplying the appropriate amount by the multiplier value when a multiplier value is set, determining the larger value between the value obtained by subtracting the current inventory amount from the order evaluation value and the order quantity when a holding instruction quantity is set for a specific pharmaceutical product, limiting and correcting the reference order quantity so as not to exceed the maximum displayable quantity when a maximum displayable quantity is set for a specific pharmaceutical product, and outputting a guide message set for the specific pharmaceutical product to a display unit. Claim 3 In claim 2, the processor analyzes the sales volume, dispensing volume, consumption volume, volume, weight, packaging size, storage characteristics, and turnover rate of the pharmaceuticals to automatically classify the pharmaceuticals to be stored in the storage space; analyzes the code and symbol patterns included in the pharmaceutical names to classify them into at least one of store display items, warehouse storage items, upper cabinet storage items, lower cabinet storage items, drink items, nutritional supplement items, and discount exclusion items; calculates the difference between the cumulative usage up to a first point in time designated by the user and the cumulative usage up to a second point in time prior to the first point in time to calculate the replenishment quantity to be moved from the storage space; generates a storage space movement list based on the replenishment quantity; outputs the pharmaceuticals to be moved and the moving quantity to a display unit according to the storage space movement list; receives pharmaceutical transaction request information between pharmacies and, when the pharmaceuticals to be traded are posted, sends a notification message to the user terminal; when an acceptance input for the transaction request is received, automatically generates a transaction statement including transaction counterparty information, pharmaceutical information, transaction quantity information, and transaction date and time information; and when an electronic signature input is received, on the transaction statement An order processing automation system characterized by reflecting an electronic signature and generating a final transaction document, transmitting the final transaction document to a user terminal, an external server, or a message transmission server, storing and managing the final transaction document as proof for face-to-face or non-face-to-face transactions, wherein the processes of storage space classification, movement list generation, transaction request processing, and transaction statement generation and transmission are performed integrally in conjunction with the order processing automation system, wherein the storage space classification and movement are performed periodically based on differences in consumption amounts by time interval, and wherein the time interval includes multiple reference points defined by user settings or system settings.

Images