Public welfare medicine giving intelligent matching method based on medicine photo recognition

Abstract

The invention discloses an intelligent public welfare medicine giving matching method based on medicine photo recognition. The method comprises the steps that S1, medicine photos are collected, wherein the photos of medicines in the hands of a patient are collected through mobile equipment or other digital cameras, or a medicine packaging box is brought to the collection position; s2, photo preprocessing: importing the collected medicine photo into a system, and carrying out preprocessing operation; s3, image recognition: using an advanced image recognition algorithm to recognize the preprocessed medicine photo; s4, importing the information; s5, information retrieval and matching: according to an image recognition result, retrieving matched medicine information in a database of public welfare medicine giving items; s6, outputting and feeding back a matching result; s7, storing and recording; and S8, information storage and deletion: through a plurality of medicine photo acquisition modes, public benefit medicine giving can be carried out on people of different age groups, and a user selects whether to store own information by himself or herself, so that the worry of the user on own information safety is avoided.

Description

Technical Field

[0001] The present invention relates to the field of intelligent matching technology, and in particular to an intelligent matching method for public welfare medicine donation based on medicine photo recognition. Background Art

[0002] With the development of information technology, medical informatization has gradually become one of the development directions of the medical industry. In the field of medical informatization, the management of drug information has become an important part of medical informatization construction.

[0003] The characteristic of drug information is that the amount of drug information data is very huge. Specifically, there are about 100,000 drug types alone, and with the development of new drugs, the number of drug types will continue to increase. In addition, each drug can be divided into dozens of reference systems according to different age groups, genders, prices, specifications, etc., that is, the drug information of each drug can contain dozens of drug sub-information.

[0004] The existing intelligent matching method for public welfare drug donations based on drug photo recognition identifies drugs manually. However, this method has a large workload during use and the matching effect is poor. In addition, some uncommon drugs are difficult to find, resulting in low efficiency and poor effect. Summary of the invention

[0005] The purpose of the present invention is to solve at least one of the technical problems existing in the prior art, and to provide an intelligent matching method for public welfare drug donations based on drug photo recognition. Through a variety of drug photo collection methods, public welfare drug donations can be made to people of different age groups. Users can choose whether to save their own information by themselves, thereby avoiding users' concerns about the security of their information.

[0006] The present invention also provides the above-mentioned public welfare drug donation intelligent matching method based on drug photo recognition, comprising the following steps:

[0007] S1. Collection of drug photos: Use mobile devices or other digital cameras to collect photos of drugs in the patient's hands, or bring the drug packaging box to the collection site;

[0008] S2. Photo preprocessing: import the collected drug photos into the system and perform preprocessing operations;

[0009] S3. Image recognition: Use advanced image recognition algorithms to identify pre-processed drug photos and extract drug information: Extract key information and accurately extract drug keywords through intelligent algorithms;

[0010] S4. Information import: import the drugs in large pharmacies into the information storage device, and update the drug information in each region;

[0011] S5. Information retrieval and matching: Based on the image recognition results and the key information of the drug, the matching drug information is retrieved in the database of the public welfare drug donation project;

[0012] S6. Matching result output and feedback: present the matching results to the user in a clear and understandable manner;

[0013] S7. Storage and Records: In order to ensure the transparency and traceability of public welfare drug donation activities, the system should automatically record the relevant information of each matching operation;

[0014] S8. Information preservation and deletion: Users can choose whether to preserve their information based on their own circumstances.

[0015] According to the method for intelligent matching of public welfare drug donations based on drug photo recognition provided by the present invention, the preprocessing operations in S2 are specifically steps of denoising, contrast enhancement, and cropping of useless areas to improve image quality.

[0016] According to the intelligent matching method for charity drug donation based on drug photo recognition provided by the present invention, the recognition in S3 specifically refers to the name, specification and manufacturer of the drug.

[0017] According to the intelligent matching method for public welfare drug donation based on drug photo recognition provided by the present invention, the database in S5 should contain detailed information of various public welfare drug donation projects, including the types, quantities, and applicable conditions of drugs that can be donated. The system will compare the automatically identified drug information with the information in the database to find the most suitable match.

[0018] According to the method for intelligent matching of public welfare medicine donations based on medicine photo recognition provided by the present invention, S6 specifically displays information such as the name, quantity and collection method of successfully matched medicines on the mobile phone screen. At the same time, the system can also provide a feedback mechanism to allow users to confirm the matching results or raise objections, so as to further adjust and optimize the matching algorithm.

[0019] According to the method for intelligent matching of charity medicine donations based on medicine photo recognition provided by the present invention, the relevant information in S7 is specifically the recipient information, matching medicine information, and operation time, and the information is stored in a secure storage medium.

[0020] According to the method for intelligent matching of public welfare drug donations based on drug photo recognition provided by the present invention, the storage medium is specifically a cloud server.

[0021] According to the intelligent matching method for public welfare drug donation based on drug photo recognition provided by the present invention, the drug photo collection in S1 also includes transmission via USB connection to complete the collection.

[0022] Beneficial Effects

[0023] 1. Compared with the existing technology, this intelligent matching method for public welfare drug donation based on drug photo recognition can provide public welfare drug donation to people of different age groups through a variety of drug photo collection methods. Users can choose whether to save their own information by themselves, thereby avoiding users' concerns about the security of their information. The dual recognition of images and text can increase the accuracy of recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The present invention is further described below in conjunction with the accompanying drawings and embodiments;

[0025] Figure 1 The present invention is a flow chart of the method for intelligent matching of public welfare medicine donations based on medicine photo recognition. DETAILED DESCRIPTION

[0026] This section will describe in detail the specific embodiments of the present invention. The preferred embodiments of the present invention are shown in the accompanying drawings. The purpose of the accompanying drawings is to supplement the description of the text part of the specification with graphics, so that people can intuitively and vividly understand each technical feature and the overall technical solution of the present invention, but it cannot be understood as a limitation on the scope of protection of the present invention.

[0027] Reference Figure 1 The embodiment of the present invention provides a method for intelligent matching of medicine donations for public benefit based on medicine photo recognition, which comprises the following steps:

[0028] S1. Collection of drug photos: Use a mobile device or other digital camera to collect photos of the drugs in the patient's hand, or bring the drug packaging box to the collection site. The collection of drug photos also includes transmission via USB connection to complete the collection;

[0029] S2. Photo preprocessing: import the collected drug photos into the system and perform preprocessing operations. The preprocessing operations specifically include denoising, contrast enhancement, and cropping of useless areas to improve image quality;

[0030] S3. Image recognition: Use advanced image recognition algorithms to identify the pre-processed drug photos. Specifically, the recognition includes identifying the name, specification, and manufacturer of the drug, extracting key information, and accurately extracting drug keywords through intelligent algorithms. The recognition algorithm is specifically a convolutional neural network in deep learning. The convolutional neural network is a type of feedforward neural network that includes convolution calculations and has a deep structure. It is one of the representative algorithms of deep learning. The convolutional neural network has the ability to represent learning and can perform translation-invariant classification of input information according to its hierarchical structure;

[0031] S4. Information import: import the drugs in large pharmacies into the information storage device, and update the drug information in each region;

[0032] S5. Information retrieval and matching: Based on the results of image recognition and key information recognition, the system searches for matching drug information in the database of public welfare drug donation projects. The database should contain detailed information on various public welfare drug donation projects, including the types, quantities, and applicable conditions of the drugs that can be donated. The system will automatically compare the drug information identified with the information in the database to find the most suitable match;

[0033] S6. Matching result output and feedback: The matching results are presented to the user in a clear and understandable manner, specifically by displaying the name, quantity and collection method of the successfully matched drug on the mobile phone screen. At the same time, the system can also provide a feedback mechanism to allow users to confirm or raise objections to the matching results in order to further adjust and optimize the matching algorithm;

[0034] S7. Storage and Recording: In order to ensure the transparency and traceability of public welfare drug donation activities, the system should automatically record the relevant information of each matching operation, including the recipient information, matching drug information, and operation time, and store this information in a secure cloud server;

[0035] S8. Information preservation and deletion: Users can choose whether to preserve their information based on their own circumstances.

[0036] The embodiments of the present invention are described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Various changes can be made within the knowledge scope of ordinary technicians in the technical field without departing from the purpose of the present invention.

Claims

1. A method for intelligent matching of public welfare medicine donations based on medicine photo recognition, characterized in that: The following steps are involved: S1. Collection of drug photos: Use mobile devices or other digital cameras to collect photos of drugs in the patient's hands, or bring the drug packaging box to the collection site; S2. Photo preprocessing: import the collected drug photos into the system and perform preprocessing operations; S3. Image recognition: Use advanced image recognition algorithms to identify pre-processed drug photos and extract drug information: Extract key information and accurately extract drug keywords through intelligent algorithms; S4. Information import: import the drugs in large pharmacies into the information storage device, and update the drug information in each region; S5. Information retrieval and matching: Based on the image recognition results and the key information of the drug, the matching drug information is retrieved in the database of the public welfare drug donation project; S6. Matching result output and feedback: present the matching results to the user in a clear and understandable manner; S7. Storage and Records: In order to ensure the transparency and traceability of public welfare drug donation activities, the system should automatically record the relevant information of each matching operation; S8. Information preservation and deletion: Users can choose whether to preserve their information based on their own circumstances.

2. According to claim 1, a method for intelligent matching of public welfare medicine donations based on drug photo recognition is characterized in that: The preprocessing operation in S2 specifically includes the steps of denoising, contrast enhancement, and cutting out useless areas to improve the image quality.

3. According to claim 1, a method for intelligent matching of public welfare medicine donations based on drug photo recognition is characterized in that: The identification in S3 specifically refers to the name, specification and manufacturer of the drug.

4. According to claim 1, a method for intelligent matching of public welfare medicine donations based on medicine photo recognition is characterized in that: The database in S5 should contain detailed information on various public welfare drug donation projects, including the types, quantities, and applicable conditions of the donated drugs. The system will compare the automatically identified drug information with the information in the database to find the most suitable match.

5. According to claim 1, a method for intelligent matching of public welfare medicine donations based on medicine photo recognition is characterized in that: Specifically, S6 displays the name, quantity, and collection method of successfully matched drugs on the mobile phone screen. At the same time, the system can also provide a feedback mechanism to allow users to confirm or raise objections to the matching results in order to further adjust and optimize the matching algorithm.

6. According to claim 1, a method for intelligent matching of public welfare medicine donations based on medicine photo recognition is characterized in that: The relevant information in S7 specifically includes recipient information, matching drug information, and operation time, and the information is stored in a secure storage medium.

7. The method for intelligent matching of public welfare medicine donations based on medicine photo recognition according to claim 6 is characterized in that: The storage medium is specifically a cloud server.

8. According to claim 1, a method for intelligent matching of public welfare medicine donations based on medicine photo recognition is characterized in that: The drug photo collection in S1 also includes transmission via a USB connection, thereby completing the collection.

Images