Domestic intelligent medicine chest medicine storing and taking system and device based on greedy strategy

By adopting greed strategies and drug correlation algorithms in home smart medicine boxes, the drug storage and drug collection process is optimized, and the problems of irregular drug storage and inconvenience of drug collection are solved, and the intelligent management and efficient utilization of drugs are realized, and the User experience and drug use efficiency.

CN119007338AActive Publication Date: 2024-11-22贵州轻工职业大学
View PDF 12 Cites 0 Cited by

Patent Information

Application Number
CN202410949198.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2024-11-22
Estimated Expiration
2044-07-16

AI Technical Summary

Technical Problem

The existing household smart medicine boxes have defects in drug storage and classification, and cannot store drugs according to the rules, and it is difficult to correspond to drugs, resulting in inconvenience in drug storage and medication.

Method used

Using an algorithm based on greedy strategy, combining drug information, frequency of use and prescription correlation, optimizes drug storage strategy, enters prescription information through facial recognition and mobile APP, automatically arranges the time to pick up the medicine and matches the box where the medicine is located, and reduces the number of pop-ups in the box. Improve space utilization and drug management efficiency.

Benefits of technology

It realizes intelligent management and personalized storage of drugs, improves the standardization and utilization rate of drug storage, reduces expired drug waste, reduces management complexity and time cost, and enhances user experience and drug use efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119007338A_ABST
    Figure CN119007338A_ABST
Patent Text Reader

Abstract

The invention discloses a greedy strategy-based household intelligent medicine box medicine storage and taking system, which is characterized by comprising the following contents: (1) medicine storage: obtaining medicine information, and then calculating according to a prescription correlation degree to obtain a storage box; (2) medicine taking: a user needs to input identity information of a medicine taking person; a user inputs a prescription, and the system automatically associates medicine storage and distribution in the medicine box according to complaint information; then, the medicine taking time of the user is automatically arranged according to the recorded effective prescription, and when the medicine taking time is up, the system gives a prompt through sound; after the identity of the user is verified, the system automatically matches the names and the number of the medicines in the prescription according to the identified identity, judges whether there is a lack of medicines, and gives a prompt if there is a lack of medicines; and when the system detects that the user takes the medicine according to the prescription, the system pops up the corresponding medicine grid.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a household intelligent medicine box medicine storage and retrieval system and device based on a greedy strategy, belonging to the field of intelligent household products. Background Art

[0002] At present, most of the household medicine boxes on the market are physical medicine boxes, which are only used for simple storage of medicines, and cannot provide guidance for the drug information stored in the entire medicine box and the patient's medication. At the same time, although the existing smart medicine boxes on the market provide some intelligent functions, there are still great defects in the entire drug storage and classification. They simply store the medicines and remind users to take medicines according to relevant regulations. There are some irregularities in the storage of medicines. Different types of medicines are stored in each medicine box, and it is difficult to match prescriptions with medicines.

[0003] The device of the present invention is similar in form to other smart medicine boxes in appearance, but is very different in purpose and technical implementation. The purpose of the device of the present invention is to make the storage of medicines for users in a household smart medicine box more reasonable, standardized and humane. It combines greedy strategies and local search algorithms to optimize the storage strategy of medicines during storage. It can make efficient use of the medicine box space according to user habits, especially providing the optimal storage medicine box when the prescriptions and usage habits are complex. Summary of the invention

[0004] The purpose of the present invention is to provide a household intelligent medicine box medicine storage and retrieval system and device based on a greedy strategy, so as to solve the problems that the existing technology still has great defects in the entire medicine storage and classification. The medicines are simply stored and users are reminded to take medicines according to relevant regulations. In terms of storing medicines, there are problems such as not storing them according to rules, different types of medicines are stored in each medicine box, and it is difficult to match prescriptions with medicines.

[0005] The technical solution of the present invention is: a household intelligent medicine box medicine storage and retrieval system based on a greedy strategy, comprising the following contents: (1) medicine storage: obtaining medicine information, and then calculating the storage box according to the prescription association degree; (2) medicine retrieval: the user needs to enter the identity information of the medicine user, including name and facial feature information, and the system performs face recognition and records; then the user enters the prescription on the mobile phone APP, including the prescription owner, the name of the medicine, the dosage and the time of taking the medicine; the system automatically associates the storage distribution of the medicines in the medicine box according to this information; then the time for the user to take the medicine is automatically arranged according to the entered valid prescription, and the system will prompt through sound when it is time to take the medicine; then, after the user can verify the identity through face recognition through the camera, the system will automatically match the name and quantity of the medicine in the prescription according to the recognized identity, and determine whether there is any missing medicine, and prompt if there is; when the system detects that the user takes the medicine according to the prescription, it will select the box where the medicine is located according to the following strategy: since a medicine may be placed in more than one box, in order to make it more convenient for the user to take the medicine, the system will pop up as few boxes as possible when the medicines in the prescription are met.

[0006] The drug information described includes: drug ID, drug name, production date, shelf life, instructions for use, box length, box width and box height.

[0007] If newDrug is in the historical drug usage, count the number of days used L days 、Usage times L freq 、Total amount of medicine used L num , given the recommended number of times R that drug i is taken per day f And the recommended dosage R n , define the drug use frequency function:

[0008]

[0009] Here w1, w2, w3 are weight coefficients, and w1+w2+w3=1, set w1=0.5, w2=0.3,

[0010] w3=0.2; for the i-th medicine box, traverse all the medicines in the medicine box and calculate the total frequency of use F j :

[0011]

[0012] Step (1) also includes: Considering the centralized storage of prescriptions: Selecting the target box: Selecting the box j*=argmax_j(A[j]) that meets the volume requirements and has the highest prescription correlation. If there are multiple choices, consider the adjacency and the use of the remaining space; if there are multiple boxes that meet the conditions, further select according to the number of drugs with the same prescription in the adjacent boxes, and define the function Choose the box with the largest C[j].

[0013] Step (2), define the decision variable x i (i=1,2,...,m) is a binary variable, m is the number of boxes containing drugs in the prescription; if box i is selected, then x i =1, otherwise x i = 0, so that the objective function is to minimize the number of boxes used And for each drug j (j = 1, 2, ..., n), add constraints to ensure that it is selected at least once, Where S i is the set of drugs in the ith box; by traversing each drug and checking which boxes contain the drug; then ensuring that at least one of these boxes is selected, the constraint condition is constructed to find as few boxes as possible that satisfy the prescription drugs; then the system automatically distributes the drugs and checks whether the drug collection is completed; if the user fails to collect the drugs on time, the system will issue a timeout reminder; when the user finishes collecting the drugs, the system will promptly update the drug information and the remaining quantity to ensure the timeliness and accuracy of the information.

[0014] Step (1) also includes: space utilization optimization: on the basis of satisfying the above conditions, for all possible boxes, select the box with the smallest remaining space but still able to accommodate new drugs to reduce space waste; define R[j] = B[j] / Capacity[j] as the space utilization of the current box, and select the box with the smallest R[j].

[0015] Step (1) also includes: calculating the prescription association degree:

[0016]

[0017] Where: A[j] represents the prescription association score of box j; S is the set of all known prescriptions; N is the set of currently stored drugs in box j; i represents the i-th drug, k represents the k-th prescription; W k Indicates the correlation between multiple drugs appearing in the same prescription; V i Indicates the association between drugs appearing in multiple prescriptions; a function f(i,k) is defined here, so that if drug i exists in prescription k, then f(i,k) = 1, otherwise

[0018] f(i,k)=0;

[0019] (1) The calculation formula for the correlation between multiple drugs appearing in the same prescription is:

[0020]

[0021] Here G is used k The quadratic function of S is used as the prescription k The weighted correlation reflects that when more drugs appear in the same prescription, the correlation has a higher bonus;

[0022] (2) Calculation formula for the correlation between a drug appearing in multiple prescriptions

[0023]

[0024] Here H is used i The logarithm of is used as the weighted association of drug i. The more prescriptions it appears in, the higher the association. In the calculation of the association of this prescription, emphasis is placed on the situation where multiple drugs appear in the same prescription, and a higher score is given.

[0025] Step (1) also includes: adjacent box prescription concentration calculation formula: aims to evaluate the extent to which the drugs stored in the box and its adjacent boxes meet the prescription requirements, which helps to maintain the physical proximity of related drugs and facilitates users to quickly find and use all drugs in the entire prescription; adjacent box prescription concentration calculation formula:

[0026]

[0027] Where: C[j] represents box j and its adjacent boxes j-1 and j+1. Assuming that the boundary conditions are properly handled, the end-to-end or boundary boxes only consider the prescription concentration scores of the neighbors on one side; S is the set of all known prescriptions; M[j] is the set of stored drugs in box j, and also contains the prescription information to which these drugs belong; I(s,M[j]∪M[j-1]∪M[j+1]) is an indicator function that evaluates whether at least part of the drugs in prescription s exist in the joint set of boxes j, j-1 and j+1; if the conditions are met, I(s,M[j]∪M[j-1]∪M[j+1]) = 1, otherwise it is 0.

[0028] Step (1) also includes integral fusion calculation: according to the calculated comprehensive drug usage frequency F of the jth box j, space utilization R[j], prescription association A[j], and adjacent box prescription concentration C[j]. The user sets the importance of the four items through the system, and the importance levels are w1 (important), w2 (relatively important), w3 (general), and w4 (unimportant). Set w1=0.5, w2=0.3, w3=0.2, and w4=0; after the setting is completed, w f 、w r 、w a 、w c Four parameters, here w f 、w r 、w a 、w c represent unique values ​​in w1 to w4, and they will not be repeated. In other words, each parameter (w f 、w r 、w a 、w c ) corresponds to a value in (w1, w2, w3, w4). Then for box j, the integral can be calculated as:

[0029] T j =w f F j +w r R[j]+w a A[j]+w c C[j]

[0030] According to the final score ranking, take the grid with the highest score T, that is, the box with the appropriate storage position.

[0031] Step (1) also includes: prescription entry: using the WIFI module provided by the medicine box to connect and enter the prescription through the mobile phone APP; the prescription includes the drug category, frequency of use, dosage information, and the person to whom the prescription belongs should be specified when entering the prescription.

[0032] A household smart medicine box medicine storage and retrieval device based on a greedy strategy, including the following modules:

[0033] The power supply module is used to provide the 5V power supply required for the system to work and keep the voltage stable;

[0034] Face recognition module, used for user identity permission to pick up or store medicines;

[0035] WIFI module: the medicine box provides a WIFI access configuration module, which is used for remote connection and user interaction via WIFI, and is used to transmit data streams and receive analysis and processing results and control commands from the cloud server;

[0036] The scanning module is used to intuitively obtain the relevant properties of the medicine box during the storage process, including size and drug information;

[0037] Storage module, used for data storage during the operation of the equipment, including face results, prescription storage and related process data;

[0038] The rotary machine control module is used to control the relevant medicine box control switches in the medicine box and control the closing operation through the algorithm scheduling results;

[0039] Voice module, used for medicine box to remind and give instructions for taking medicine.

[0040] Beneficial effects of the present invention: Intelligent prescription integrated management: Traditional household medicine boxes often only provide simple physical storage functions, while this algorithm realizes intelligent prescription management by considering the centralized storage of medicines in prescriptions. It not only optimizes the physical layout of medicines, but also improves the efficiency of quickly finding the required medicines in emergency situations, reducing the risk of delayed treatment due to searching for medicines.

[0041] Dynamic adaptive storage optimization: The algorithm dynamically adjusts the storage location based on the volume, shelf life, usage habits and prescription requirements of the medicine, which greatly improves space utilization and flexibility compared to the fixed layout of the family medicine box. It can automatically optimize the storage strategy as the health status of family members changes and the inventory of medicines changes, ensuring that the medicine box is always in an efficient operating state.

[0042] Personalized usage habits: By taking the frequency of drug use into account, the algorithm can provide personalized storage recommendations for family members’ specific medication habits. This solves the problem that standard medicine box products cannot adapt to diverse personal needs and enhances the user experience.

[0043] Reduce the waste of expired medicines: Giving priority to the storage strategy of boxes with less remaining space can help reduce space waste. A good storage strategy indirectly promotes the rational circulation and timely consumption of medicines, avoids the expiration of medicines due to improper storage, saves family expenses, and also reflects environmental awareness. (When family members take commonly used medicines, if there are similar medicines that are about to expire placed next to them, they may give priority to these medicines to avoid waste).

[0044] Continuous optimization without frequent resetting: When designing the algorithm, special emphasis is placed on not needing to reallocate existing drugs, and only selecting the optimal location for newly added drugs, which reduces the complexity and time cost of daily management, making medicine box management more convenient and sustainable.

[0045] Data analysis aids decision-making: The data processing and analysis capabilities behind the algorithm provide data support for family health management. Long-term applications can collect data such as drug use frequency and shelf life compliance, providing a scientific basis for future family medical resource planning and procurement plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 This is the system structure diagram of the medicine storage and medicine dispensing device of the household intelligent medicine box;

[0047] Figure 2 This is a functional structure diagram of the medicine storage and retrieval function of the household smart medicine box;

[0048] Figure 3 Flow chart for storing medicines in a home smart medicine box;

[0049] Figure 4 Flow chart for retrieving medicines from a home smart medicine box. DETAILED DESCRIPTION

[0050] 1. Initialize the medicine box

[0051] Define variables:

[0052] V[i] represents the volume of the i-th drug;

[0053] P[i] represents the shelf life of the i-th drug;

[0054] F[i] represents the frequency of use of the i-th drug;

[0055] B[j] represents the current remaining volume of the jth box;

[0056] M[j] represents the set of medicines currently stored in the jth box and their prescription information;

[0057] S[k] represents the set of medicines contained in the k-th prescription;

[0058] N is the number of known drugs;

[0059] S is the number of known prescriptions;

[0060] newDrug indicates the drug information to be stored, including volume, prescription ownership, etc.

[0061] 2. Determination of prescription relevance

[0062] For the drug newDrug to be stored, query the prescription drug details table in the system to determine whether it is in the stored prescription.

[0063] First, perform a query operation in the prescription drug details table based on the name or identification information of newDrug. If the query result returns the corresponding record, it means that newDrug already exists in the stored prescription, and the calculations in steps 5 and 6 need to be performed;

[0064] 3. Consider centralized storage of high-frequency drugs

[0065] For newDrug that is not in any prescription, sort all boxes that meet the volume in descending order according to the frequency of use F[newDrug], and select the one with the highest frequency. First, query the drug usage table for the past 180 days. If newDrug is in the historically used drugs, count the number of days used L days 、Usage times L freq 、Total amount of medicine used L num Given the recommended daily dose R of drug i f And the recommended dosage R n , define the drug use frequency function:

[0066]

[0067] Here w1, w2, w3 are weight coefficients, and w1+w2+w3=1, set w1=0.5, w2=0.3, w3=0.2

[0068] For the i-th medicine box, traverse all the medicines in the medicine box and calculate the total usage frequency F j

[0069]

[0070] 4. Optimize space utilization

[0071] On the basis of satisfying the above conditions, for all possible boxes, select the box with the smallest remaining space but still able to accommodate the new drug to reduce space waste. For the space utilization of the current box, select the box with the largest R[j].

[0072] 5. Calculation of prescription association

[0073] The calculation of prescription relevance aims to quantify how closely the newly added drug meets the existing drug combination in the medicine box. We found a way to measure which box the new drug should be stored in to best maintain or enhance the coverage of the current drug combination in the medicine box. The following is a simplified formula for calculating prescription relevance and its explanation:

[0074] Prescription association calculation formula:

[0075]

[0076] Where: A[j] represents the prescription association score of box j; S is the set of all known prescriptions; N is the set of currently stored drugs in box j; i represents the i-th drug, k represents the k-th prescription; W k Indicates the correlation between multiple drugs appearing in the same prescription; V i Indicates the association between drugs appearing in multiple prescriptions; a function f(i,k) is defined here, so that if drug i exists in prescription k, then f(i,k) = 1, otherwise

[0077] f(i,k)=0.

[0078] (1) The calculation formula for the correlation between multiple drugs appearing in the same prescription is:

[0079]

[0080] Here G is used k The quadratic function of S is used as the prescription k The weighted correlation reflects that when more drugs appear in the same prescription, the correlation has a higher bonus;

[0081] (2) Calculation formula for the correlation between a drug appearing in multiple prescriptions

[0082]

[0083] Here H is used i The logarithm of is used as the weighted association of drug i. The more prescriptions it appears in, the higher the association.

[0084] The explanation is as follows: Traverse all prescriptions: The formula first traverses all prescriptions s∈S, in order to check whether each prescription has an intersection with the drugs in the box under consideration, and to check the number of types of drugs with intersection. Traverse all drugs in all boxes: For each type of drug, check the frequency of its appearance in all prescriptions, that is, observe how many prescriptions it is required by. Accumulate the score: By accumulating the matching scores of all prescriptions and the number of prescriptions in which all drugs appear, the overall prescription association score A[j] of box j is obtained. The higher the score, the more the combination of drugs in the box can meet or nearly meet the requirements of more prescriptions, and the system is more inclined to store multiple drugs in the same prescription in one box, which will give higher points. Through the above formula and explanation, the prescription association can be quantified, thereby helping the decision-making process, ensuring that newly added drugs can be effectively integrated into the existing storage system, and promoting the rapid matching and efficient use of prescriptions.

[0085] 6. Formula for calculating the concentration of prescriptions in adjacent boxes

[0086] The calculation of the concentration of prescriptions in adjacent boxes aims to evaluate how well the drugs stored in a box and its adjacent boxes meet the prescription needs, which helps to maintain the physical proximity of related drugs and facilitates users to quickly find and use all drugs in the entire set of prescriptions. The following is a calculation formula for the concentration of prescriptions in adjacent boxes and its explanation:

[0087] The formula for calculating the concentration of prescriptions in adjacent boxes is:

[0088] Where: C[j] represents the prescription concentration score of box j and its adjacent boxes j-1 and j+1, assuming that the boundary conditions are properly handled, such as being connected end to end or the boundary box only considering neighbors on one side); S is the set of all known prescriptions; M[j] is the set of drugs stored in box j, M[j-1] and M[j+1] represent the drug sets of adjacent boxes, and the specific adjacent boxes need to be actually calculated.

[0089] I(s,M[j]∪M[j-1]∪M[j+1]) is an indicator function that evaluates whether prescription s has at least some drugs in the union of boxes j, j-1, and j+1. If the condition is met, I(s,M[j]∪M[j-1]∪M[j+1])=log2(n), where n is the number of drugs in boxes j, j-1, and j+1 in the prescription, otherwise it is 0.

[0090] Explanation: Expanded consideration scope: Compared with only considering the prescription association of a single box, this formula is expanded to consider the joint influence of the current box j and its left and right adjacent boxes (assuming a circular or linear sequence, and handling boundary cases). Extensiveness of prescription matching: For each prescription s, this formula checks whether the prescription can find enough ingredients in the current box j and its two adjacent boxes to satisfy the prescription. If all the drugs or key drug sets in at least one prescription can be found in these boxes, this indicates that the area is very beneficial for meeting prescription requirements. Cumulative number of satisfied prescriptions: By accumulating the number of all prescriptions that can be satisfied by the current box and its adjacent boxes, we get the C[j] value. The higher this value is, the better the boxes in this area can support the rapid retrieval of prescriptions as a whole.

[0091] 7. Integral fusion calculation

[0092] According to the calculations in steps 3, 4, 5, and 6, the comprehensive frequency of drug use F in the jth box is obtained respectively. j, space utilization R[j], prescription association A[j], and adjacent box prescription concentration C[j]. The user sets the importance of the four items through the system, and the importance levels are w1 (important), w2 (relatively important), w3 (general), and w4 (unimportant). Set w1=0.5, w2=0.3, w3=0.2, and w4=0; after the setting is completed, w f 、w r 、w a 、w c Four parameters, here w f 、w r 、w a 、w c represent unique values ​​in w1 to w4, and they will not be repeated. In other words, each parameter (w f 、w r 、w a 、w c ) corresponds to a value in (w1, w2, w3, w4). Then for box j, the integral can be calculated as:

[0093] T j =w f F j +w r R[j]+w a A[j]+w c C[j]

[0094] According to the final score ranking, take the grid with the highest score T, that is, the box with the appropriate storage position.

[0095] 9. Medication collection process

[0096] The figure shows a flow chart of the household smart medicine box medication system. First, the user needs to enter the identity information of the medication user, including name and facial features, and the system will perform face recognition and record it. Next, the user enters the prescription on the mobile phone APP, including the prescription owner, the name of the medication, the dosage and the time of taking. Based on this information, the system automatically associates the storage distribution of the medicines in the medicine box. Then, according to the entered valid prescription, the user's medication time is automatically arranged, and when it is time to take the medicine, the system will prompt through sound. Then, the user can use the camera to verify the identity through face recognition, and the system will search the drug information table and the prescription drug detailed list table according to the identified identity, and then know the name and usage quantity of the medicine in the prescription, and then search the drug information table, and determine whether there are any missing drugs, and if so, prompt.

[0097] When the system detects that the user is picking up medicine according to the prescription, it will select the box where the medicine is located according to the following strategy: Since a medicine may be placed in more than one box, in order to make it more convenient for users to pick up medicine, the system will pop up as few boxes as possible when the medicine in the prescription is met. Define the decision variable x i (i=1,2,...,m) is a binary variable, m is the number of boxes containing drugs in the prescription. If box i is selected, then x i =1, otherwise x i = 0, so that the objective function is to minimize the number of boxes used And for each drug j (j = 1, 2, ..., n), add constraints to ensure that it is selected at least once, Where S i is the set of drugs in the ith box. We construct constraints by iterating over each drug and checking which boxes contain it, and then ensuring that at least one of these boxes is selected, and then find the fewest possible boxes that satisfy the prescription.

[0098] The system will then automatically dispense the medicine and check whether the medicine has been taken. If the user fails to take the medicine on time, the system will issue a timeout reminder. When the user has finished taking the medicine, the system will promptly update the medicine information and the remaining quantity to ensure the timeliness and accuracy of the information.

[0099] When the user needs to take out the medicine in the medicine box in time, he can find the grid where the required medicine is located according to the medicine name on the mobile phone APP. When taking out the medicine and putting the remaining medicine back, he only needs to scan the barcode of the medicine packaging box again, and the system will automatically update the remaining medicine amount in the system according to the default dosage. If the medicine is not put back, the system will set the information recorded for this medicine to an invalid state, and automatically clear the record if it is still not put into the warehouse again after a certain period of time.

[0100] Data storage specifications

[0101] 1. Face entry data structure

[0102] When designing a database for storing facial features, it is necessary to consider the type of facial features and the way the data is organized. Face recognition generally uses high-dimensional feature vectors for recording.

[0103]

[0104] 2. Drug Information Sheet

[0105] Column Name Data Types describe Drug ID INT A number that uniquely identifies each drug Drug Name VARCHAR Full name of the drug Production Date DATE Date of manufacture of the drug Shelf life INT Shelf life days Instructions TEXT Instructions for use of medicines Boxed Length DECIMAL Length of the packaging box (unit: mm) Boxed Width DECIMAL Width of the packaging box (unit: mm) Boxed Height DECIMAL Height of the packaging box (unit: mm) Storage grid number INT The warehouse grid number where the drug is stored Warehouse time DATETIME Time of drug storage

[0106] 3. Prescription Information Sheet

[0107] Column Name Data Types describe Prescription ID INT A number that uniquely identifies each prescription Prescription owner VARCHAR Information about the person who owns the prescription Warehouse time DATETIME The time when the prescription is recorded in the warehouse

[0108] 4. Prescription drug details list

[0109]

[0110] 5. Storage grid details table

[0111]

[0112] 6. Prescription and medication record form

[0113] Column Name Data Types describe Prescription ID INT A number that uniquely identifies each prescription Prescription owner VARCHAR Information about the person who owns the prescription Time of medicine delivery DATETIME The time when the drug is used in this prescription .

Claims

1. A household intelligent medicine box medicine storage and retrieval system based on a greedy strategy, characterized by: The system includes the following contents: (1) Drug storage: obtain drug information, and then calculate the storage box based on the prescription association degree; (2) Picking up medicine: the user needs to enter the identity information of the drug user, including name and facial feature information, and the system performs facial recognition and records; the user enters the prescription, including the prescription owner, the name of the drug, the dosage and the time of taking the drug; the system automatically associates the storage distribution of the drugs in the medicine box based on the above information; then the time for the user to pick up the medicine is automatically arranged according to the entered valid prescription, and the system prompts through sound when it is time to take the medicine; after the user verifies the identity, the system automatically matches the name and quantity of the drugs in the prescription according to the recognized identity, and determines whether there are any missing drugs, and prompts if there are any missing drugs; when the system detects that the user is picking up the medicine according to the prescription, the box where the drug is located is selected according to the following strategy: Since a drug may be placed in more than one box, in order to make it more convenient for users to pick up the medicine, the system pops up as few boxes as possible while satisfying the drugs in the prescription.

2. According to claim 1, a household intelligent medicine box medicine storage and retrieval system based on a greedy strategy is characterized by: The drug information described includes: drug ID, drug name, production date, shelf life, instructions for use, box length, box width and box height.

3. A household intelligent medicine box medicine storage and retrieval system according to claim 1, characterized in that: If newDrug is in the historical drug usage, count the number of days used L days 、Usage times L freq 、Total amount of medicine used L num , given the recommended number of times R that drug i is taken per day f And the recommended dosage R n , define the drug use frequency function: Here w1, w2, w3 are weight coefficients, and w1+w2+w3=1, set w1=0.5, w2=0.3, w3=0.2; for the i-th medicine box, traverse all the medicines in the medicine box and calculate the total frequency of use F j :

4. According to the greedy strategy-based household smart medicine box medicine storage and retrieval system of claim 1, it is characterized by: Step (1) also includes: Considering the centralized storage of prescriptions: Selecting the target box: Selecting the box j*=argmax_j(A[j]) that meets the volume requirements and has the highest prescription correlation. If there are multiple choices, consider the adjacency and the use of the remaining space; if there are multiple boxes that meet the conditions, further select according to the number of drugs with the same prescription in the adjacent boxes, and define the function Choose the box with the largest C[j].

5. According to claim 1, a household intelligent medicine box medicine storage and retrieval system based on a greedy strategy is characterized by: Step (2), define the decision variable x i (i=1,2,...,m) is a binary variable, m is the number of boxes containing drugs in the prescription; if box i is selected, then x i =1, otherwise x i = 0, so that the objective function is to minimize the number of boxes used And for each drug j (j = 1, 2, ..., n), add constraints to ensure that it is selected at least once, Where S i is the set of drugs in the ith box; by traversing each drug and checking which boxes contain the drug; then ensuring that at least one of these boxes is selected, the constraint condition is constructed to find as few boxes as possible that satisfy the prescription drugs; then the system automatically distributes the drugs and checks whether the drug collection is completed; if the user fails to collect the drugs on time, the system will issue a timeout reminder; when the user finishes collecting the drugs, the system will promptly update the drug information and the remaining quantity to ensure the timeliness and accuracy of the information.

6. A household intelligent medicine box medicine storage and retrieval system based on a greedy strategy according to claim 3 or 4, characterized in that: Step (1) also includes: space utilization optimization: on the basis of satisfying the above conditions, for all possible boxes, select the box with the smallest remaining space but still able to accommodate new drugs to reduce space waste; define R[j] = B[j] / Capacity[j] as the space utilization of the current box, and select the box with the smallest R[j].

7. The household intelligent medicine box medicine storage and retrieval system based on the greedy strategy according to claim 1 is characterized by: Step (1) also includes: calculating the prescription association degree: Where: A[j] represents the prescription association score of box j; S is the set of all known prescriptions; N is the set of currently stored drugs in box j; i represents the i-th drug, k represents the k-th prescription; W k Indicates the correlation between multiple drugs appearing in the same prescription; V i Indicates the association between drugs appearing in multiple prescriptions; a function f(i,k) is defined here, so that if drug i exists in prescription k, then f(i,k) = 1, otherwise f(i,k) = 0; (1) The calculation formula for the correlation between multiple drugs appearing in the same prescription is: Here G is used k The quadratic function of S is used as the prescription k The weighted correlation reflects that when more drugs appear in the same prescription, the correlation has a higher bonus; (2) Calculation formula for the correlation between a drug appearing in multiple prescriptions Here H is used i The logarithm of is used as the weighted association of drug i. The more prescriptions it appears in, the higher the association.

8. The greedy strategy-based household smart medicine box medicine storage and retrieval system according to claim 1, characterized in that: Step (1) also includes: a formula for calculating the concentration of prescriptions in adjacent boxes: which is intended to evaluate the extent to which the drugs stored in a box and its adjacent boxes together meet the prescription needs, which helps to maintain the physical proximity of related drugs and facilitates users to quickly find and use all drugs in the entire prescription set; The formula for calculating the concentration of prescriptions in adjacent boxes is: Where: C[j] represents box j and its adjacent boxes j-1 and j+1. Assuming that the boundary conditions are properly handled, the end-to-end or boundary boxes only consider the prescription concentration scores of the neighbors on one side; S is the set of all known prescriptions; M[j] is the set of stored drugs in box j, and also contains the prescription information to which these drugs belong; I(s,M[j]∪M[j-1]∪M[j+1]) is an indicator function that evaluates whether at least part of the drugs in prescription s exist in the joint set of boxes j, j-1 and j+1; if the conditions are met, I(s,M[j]∪M[j-1]∪M[j+1]) = 1, otherwise it is 0.

9. The greedy strategy-based household smart medicine box medicine storage and retrieval system according to claim 1, characterized in that: Step (1) also includes: integral fusion calculation: according to the calculated comprehensive drug usage frequency F of the jth box j , space utilization rate R[j], prescription association degree A[j], and prescription concentration degree C[j] of adjacent boxes. The user sets the importance of the four items through the system. The importance levels are w1 (important), w2 (relatively important), w3 (general), and w4 (unimportant). Set w1=0.5, w2=0.3, w3=0.2, and w4=0. After the setting is completed, w f 、w r 、w a 、w c Four parameters, here w f 、w r 、w a 、w c Represents unique values ​​in w1~w4, and they will not be repeated; each parameter (w f 、w r 、w a 、w c ) corresponds to a value in (w1, w2, w3, w4), and for box j, the integral is calculated as: T j =w f F j +w r R[j]+w a A[j]+w c C[j] According to the final score ranking, take the grid with the highest score T, that is, the box with the appropriate storage position.

10. A household intelligent medicine box medicine storage and retrieval device based on a greedy strategy, characterized in that: Contains the following modules: The power supply module is used to provide the 5V power supply required for the system to work and keep the voltage stable; Face recognition module, used for user identity permission to pick up or store medicines; WIFI module: the medicine box provides a WIFI access configuration module, which is used for remote connection and user interaction via WIFI, and is used to transmit data streams and receive analysis and processing results and control commands from the cloud server; The scanning module is used to intuitively obtain the relevant properties of the medicine box during the storage process, including size and drug information; Storage module, used for data storage during the operation of the equipment, including face results, prescription storage and related process data; The rotary machine control module is used to control the relevant medicine box control switches in the medicine box and control the closing operation through the algorithm scheduling results; Voice module, used for medicine box to remind and give instructions for taking medicine.

Citation Information

Patent Citations

  • Control system and method for taking medicine in intelligent medicine box

    CN109243566A

  • A pharmaceutical control method and device based on risk management and control

    CN109544359A

  • Intelligent medicine box and control method thereof

    CN112489754A

  • Storage position optimization method of relevance part intelligent warehouse system

    CN115062810A

  • Dispensing method of automatic dispensing machine based on improved Fick's law algorithm

    CN117192993A