Multifunctional medicine chest control method, system and equipment and storage medium

Abstract

The invention relates to the technical field of computer software, and particularly provides a multifunctional medicine chest control method, system and device and a storage medium, and the method comprises the steps: collecting an image of a medicine put into a medicine chest, and recognizing medicine information based on the image of the medicine; acquiring demand data through a sound pickup or an image acquisition device, and converting the demand data into structured data; collecting physical sign data through a sensor, and generating temporary demand data based on the physical sign data; generating a medicine taking scheme based on the medicine information, the structured data and the temporary demand data; and disassembling the medicine taking scheme into a timed task, wherein the timed task comprises playing a voice prompt at a target moment and sending an unlocking instruction to a medicine box lock. The intelligent level of medicine management and the medicine taking compliance of a patient are improved.

Description

Technical Field

[0001] The present invention belongs to the field of computer software technology, and in particular relates to a multifunctional medicine box control method, system, device and storage medium. Background Art

[0002] In the field of modern medical and health management, with the continuous development of science and technology, intelligent drug management and medication reminder systems have gradually become a hot spot for research and application. Traditional drug management methods often rely on manual memory and paper records, which is not only inefficient but also prone to omissions or errors. Especially for patients who need to take multiple drugs for a long time, the management difficulty is doubled.

[0003] Some existing medication reminder devices only serve as timed reminders and are unable to provide detailed information, such as medication information and dosage.

[0004] Therefore, the market is in urgent need of a system that can automatically identify drugs, understand patient needs, intelligently generate medication plans and provide timely reminders. Summary of the invention

[0005] In view of the above-mentioned deficiencies in the prior art, the present invention provides a multifunctional medicine box control method, system, device and storage medium to solve the above-mentioned technical problems.

[0006] In a first aspect, the present invention provides a multifunctional medicine box control method, comprising: Collecting images of medicines placed in the medicine box, and identifying medicine information based on the images of the medicines; Collecting demand data through a microphone or an image collector, and converting the demand data into structured data; Collecting vital sign data through sensors, and generating temporary demand data based on the vital sign data; generating a medication regimen based on the drug information, the structured data, and the temporary demand data; The medication regimen is broken down into timed tasks, which include playing a voice prompt at a target time and sending an unlocking instruction to the medicine box lock.

[0007] In an optional implementation, collecting an image of a medicine placed in a medicine box, and identifying medicine information based on the image of the medicine, includes: Collect images of medicines through cameras deployed in medicine boxes; Uploading the drug image to a cloud, where a recognition model is deployed; Receive drug information returned from the cloud, including drug name, usage and dosage, contraindications, indications, production date, and shelf life; The drug information is saved to the drug list.

[0008] In an optional embodiment, the recognition model includes: A Stacking model, wherein the base model of the Stacking model comprises an optical character recognition sub-model and a target recognition sub-model, wherein the optical character recognition sub-model recognizes the identity of a drug based on text features of the drug image, and the target recognition sub-model recognizes the identity of a drug based on appearance features of the drug image; the drug identity comprises a drug name, a manufacturer, and a batch code.

[0009] In an optional embodiment, the method further comprises: Based on the drug identity, the cloud retrieves corresponding drug information from a pre-built drug information database and sends the drug information to the multi-functional medicine box control terminal.

[0010] In an optional implementation, collecting the demand data through a microphone or an image collector and converting the demand data into structured data includes: Collecting voice data through a microphone and converting the voice data into structured demand data; The demand report image is collected by an image collector, and the demand report image is converted into structured demand data using text recognition technology.

[0011] In an optional embodiment, collecting vital sign data through a sensor and generating temporary demand data based on the vital sign data include: Acquire sensor signals through a wireless communication link and convert the sensor signals into vital sign data; Comparing the physical sign data with a preset physical sign index, and if the physical sign data is not within a reasonable range defined by the physical sign index, marking the physical sign data as abnormal physical sign data; Based on the preset corresponding rules and the abnormal vital sign data, temporary demand data is generated, and the temporary demand data includes the required drug information and dosage.

[0012] In an optional implementation, generating a medication regimen based on the drug information, the structured data, and the temporary demand data includes: Extract drug information from the temporary demand data, determine whether the drug information exists in the drug list containing drug information, generate a temporary medication plan if the drug information exists in the drug list, and set the medication time of the temporary medication plan to the current system time; if the drug information does not exist in the drug list, generate a voice prompt message; The structured data is matched with the drug information in the drug list, a medication time and a corresponding medication amount are generated based on the matched drug information, and the medication time and corresponding medication amount of multiple drug information are integrated into a medication plan; and voice prompt information is generated based on unmatched drug information.

[0013] In a second aspect, the present invention provides a multifunctional medicine box control system, comprising: An information input module, used to collect images of medicines placed in the medicine box and recognize medicine information based on the images of the medicines; A first acquisition module, used for acquiring demand data through a microphone or an image collector, and converting the demand data into structured data; A second acquisition module, used for acquiring vital sign data through sensors, and generating temporary demand data based on the vital sign data; A scheme generating module, used for generating a medication scheme based on the drug information, the structured data and the temporary demand data; The task generation module is used to decompose the medication regimen into scheduled tasks, wherein the scheduled tasks include playing a voice prompt at a target time and sending an unlocking instruction to the medicine box lock.

[0014] In a third aspect, a device is provided, comprising: A memory, used for storing a multifunctional medicine box control program; The processor is used to implement the steps of the multifunctional medicine box control method provided in the first aspect when executing the multifunctional medicine box control program.

[0015] In a fourth aspect, a computer-readable storage medium is provided, on which a multifunctional medicine box control program is stored. When the multifunctional medicine box control program is executed by a processor, the steps of the multifunctional medicine box control method provided in the first aspect are implemented.

[0016] The beneficial effects of the present invention are that the multifunctional medicine box control method, system, device and storage medium provided by the present invention can identify drug information by collecting images of drugs placed in the medicine box, collect patients' medication needs through microphones or image collectors, and monitor patients' vital signs data in real time through sensors. On this basis, the system can intelligently generate personalized medication plans and disassemble the plans into a series of timed tasks to ensure that patients can take medicines on time and in quantity. The present invention not only solves many problems existing in traditional drug management methods, but also greatly improves the intelligence level of drug management and patients' compliance with medication. Through the application of this system, patients can manage their own medicines more easily, reduce the risk of missing or taking the wrong medicine, and thus better protect their health. At the same time, for medical institutions and medical staff, it can also be used as an effective auxiliary tool to help them manage patients' medicines and medication more efficiently and improve the quality and efficiency of medical services.

[0017] In addition, the invention has a reliable design principle, a simple structure and a very broad application prospect. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention.

[0020] Figure 2 is a schematic block diagram of a system according to an embodiment of the present invention.

[0021] Figure 3 A schematic diagram of the structure of a device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention.

[0024] The multifunctional medicine box control method provided in the embodiment of the present invention is executed by a computer device, and accordingly, the multifunctional medicine box control system runs in the computer device.

[0025] Figure 1 is a schematic flow chart of a method according to an embodiment of the present invention. Figure 1 The execution subject can be a multifunctional medicine box control system. According to different requirements, the order of the steps in the flow chart can be changed, and some can be omitted.

[0026] like Figure 1 As shown, the method includes: S1. Collect images of medicines placed in a medicine box, and identify medicine information based on the images of the medicines.

[0027] The images of each medicine placed inside the medicine box are accurately captured by high-definition cameras. These images are then transmitted to the advanced image recognition algorithm module, which uses deep learning technology to conduct a comprehensive analysis of the multi-dimensional features of the medicine's packaging, shape, color, label text, etc., so as to accurately identify the key information of each medicine, such as the name, specification, and expiration date. This step ensures that the drug information stored in the system is accurate and provides a solid foundation for subsequent operations.

[0028] S2. Collect demand data through a microphone or an image collector, and convert the demand data into structured data.

[0029] By using the built-in microphone to capture the voice commands of users or medical staff, or by using image collectors (such as cameras) to recognize the user's gestures and expressions, these unstructured demand information can be converted into a processable digital form. Subsequently, using natural language processing (NLP) and computer vision technology, this information can be further parsed and converted into a structured data format, such as the patient's name, the name of the required drug, the dosage, the time of taking, etc., to facilitate subsequent logical judgment and data processing.

[0030] S3. Collect vital sign data through sensors, and generate temporary demand data based on the vital sign data.

[0031] A series of biosensors are integrated, such as heart rate monitors, blood pressure monitors, and temperature sensors, to monitor patients' vital signs in real time. These sensors collect data regularly or on demand and transmit the data to the central processing unit. Based on these vital sign data, the system uses complex algorithm models to analyze the patient's health status and automatically generates temporary drug demand adjustment suggestions, such as increasing or decreasing the dosage of specific drugs, or adjusting the medication time to suit the patient's current physical condition.

[0032] S4. Generate a medication plan based on the drug information, the structured data and the temporary demand data.

[0033] After obtaining complete drug information, structured demand data, and temporary demand data, the system inputs this information into the intelligent decision-making engine. The engine takes into account the patient's health status, drug characteristics, doctor's orders, and any possible allergies or interaction risks to generate a personalized medication plan. This plan details the time, dosage, method, and any special precautions for each drug to ensure that the patient can receive treatment safely and effectively.

[0034] S5. Decompose the medication regimen into scheduled tasks, wherein the scheduled tasks include playing a voice prompt at a target time and sending an unlocking instruction to the medicine box lock.

[0035] The generated medication plan is broken down into a series of specific timed tasks. These tasks are precisely set to specific time points to ensure that patients can take their medications on time. When the target time arrives, the system plays clear voice prompts through built-in speech synthesis technology to inform patients of the current medications to be taken and related information. At the same time, the system sends an unlocking instruction to the smart lock of the medicine box, allowing patients or caregivers to safely take out the required medications. In addition, the system may also provide visual prompts (such as screen displays) or SMS / APP push notifications as additional reminders to ensure that patients do not miss any medication. This series of intelligent operations greatly improves patient medication compliance and safety.

[0036] In an embodiment of the present invention, based on step S1, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner.

[0037] S101. Collect medicine images through a camera deployed in the medicine box.

[0038] Inside the smart medicine box, a high-resolution camera is deployed, which has automatic focus adjustment and light sensing functions to ensure that each drug placed in the medicine box can be clearly captured under different lighting conditions. The camera will automatically start periodically or according to preset conditions (such as when a new drug is put in) to collect full and detailed images of the drug.

[0039] S102. Upload the drug image to the cloud, where a recognition model is deployed.

[0040] The collected drug images are instantly uploaded to the cloud server through a secure and stable network connection. An advanced recognition model is deployed on the cloud server, which uses the Stacking ensemble learning method and combines multiple sub-models to improve the accuracy and robustness of recognition.

[0041] Stacking model structure details Model hierarchy: First layer (base model layer): Optical Character Recognition (OCR) sub-model: This sub-model is usually built based on a deep learning framework (such as TensorFlow or PyTorch), using structures such as convolutional neural networks (CNN) or recurrent neural networks (RNN), and is specifically designed to process text information in images. It can accurately extract text information such as drug name, manufacturer, batch code, etc. from images of drug packaging, which is crucial for accurate drug identification.

[0042] Object recognition sub-model: This sub-model is also based on deep learning technology, especially variants of convolutional neural networks (CNN) (such as ResNet, VGG, etc.), which is used to identify the appearance characteristics of drugs. These characteristics include the shape, color, pattern of the drug, and special logos on the packaging. Through training, this sub-model can learn to distinguish different types of drugs and assign unique identification to them.

[0043] Second layer (meta-learning layer): This layer receives the outputs from the two sub-models in the first layer and further learns and integrates them through another machine learning model (such as logistic regression, support vector machine or random forest, etc.). The task of the second layer model is to make a comprehensive judgment and derive the final drug identification result based on the prediction results of the first layer sub-model. This process usually involves steps such as feature selection, feature fusion and decision making.

[0044] Details of the drug identification process Image preprocessing: Before inputting drug images into the Stacking model, a series of preprocessing operations are usually required, including image denoising, grayscale, binarization, cropping, and scaling, etc. These operations are designed to improve image quality, reduce noise interference, and make it meet the requirements of model input.

[0045] Feature extraction: The OCR sub-model and the object recognition sub-model are responsible for extracting text features and appearance features from drug images respectively. These features are learned by the model and can reflect the key information of the drug's identity. During the feature extraction process, the model uses structures such as convolutional layers, pooling layers, and fully connected layers to process the image layer by layer, and finally obtain a high-dimensional feature vector.

[0046] Feature fusion and decision making: In the second layer model, the feature vectors from the OCR sub-model and the object recognition sub-model are fused together to form a comprehensive feature representation. This feature representation is then input into the meta-learning model for the final decision. The meta-learning model determines the identity of the drug based on the information in the feature representation and outputs the recognition result.

[0047] Result packaging and return: After identification is completed, the cloud will package the identified drug identity (including drug name, manufacturer, batch code, etc.) and related detailed drug information (such as usage and dosage, contraindications, indications, production date, shelf life, etc.) into a data package. This data package will then be sent back to the medicine box system for users to view and manage.

[0048] By deploying the model on the cloud, the computing workload of the medicine box control terminal is reduced, thereby reducing the hardware requirements for the medicine box control terminal.

[0049] S103. Receive drug information returned from the cloud, the drug information including drug name, usage and dosage, contraindications, indications, production date, and shelf life.

[0050] After receiving the data packet returned by the cloud, the smart medicine box first decrypts and verifies it to ensure the integrity and security of the information. Then, the medicine box system extracts the drug information, including key fields such as drug name, usage and dosage, contraindications, indications, production date, and shelf life.

[0051] This information will be used to update the medicine list inside the medicine box. At the same time, the medicine box system will automatically calculate and remind users of medicines that are about to expire based on the shelf life information of the medicines to ensure safe use of the medicines.

[0052] S104. Save the drug information to the drug list.

[0053] The processed drug information is saved in the drug list database of the medicine box system. The database adopts an efficient data structure, supports fast retrieval and update, and ensures that users can view and manage all drugs in the medicine box at any time.

[0054] To protect user privacy and data security, access to and operation of the drug list are subject to strict authority control to ensure that only authorized users can view and modify drug information.

[0055] In an embodiment of the present invention, based on step S2, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner.

[0056] S201. Voice data collection and structured processing.

[0057] Pickup configuration and optimization: The system's built-in microphone uses a high-sensitivity microphone array to accurately capture the voice commands of users or medical staff. In order to ensure the clarity and accuracy of voice data, the microphone is also equipped with noise reduction technology and echo cancellation functions to effectively reduce the interference of environmental noise and echo.

[0058] Speech Recognition Technology: The collected voice data is transmitted to the speech recognition module, which uses advanced deep learning algorithms (such as long short-term memory network LSTM, Transformer, etc.) to perform speech-to-text processing. By training a large number of voice samples, the model can accurately identify various voice features, including speaking speed, intonation, pronunciation habits, etc., thereby converting voice data into high-precision text information.

[0059] Natural Language Processing (NLP): The converted text information is input into the natural language processing module, which uses semantic understanding, entity recognition, relationship extraction and other technologies to deeply analyze the text. By understanding the intent, keywords and contextual information in the text, the NLP module can convert unstructured voice data into structured demand data, such as the patient's name, the name of the required drug, dosage, and time of administration.

[0060] The operation process of voice interaction is roughly as follows: First, the user issues a voice command through the device's microphone. These voice signals are collected and digitized by the system. Then, voice recognition technology converts the digitized voice signals into text. This text will go through multiple steps of natural language processing, including lexical analysis, syntactic analysis, and semantic analysis to understand the user's intention. The system will match the extracted key information with a huge knowledge base, which includes drug information, disease knowledge, health advice, etc. Based on the matching results, the system will generate a corresponding text response, and convert the text into natural and fluent speech through speech synthesis technology, and feedback to the user.

[0061] In order to achieve smarter and more humane interactions, we have introduced a number of advanced technologies. Natural language processing technology can not only identify keywords, but also understand the context and even infer the user's potential meaning. The knowledge graph links information such as drugs, diseases, and symptoms, allowing the system to provide more comprehensive health advice. Machine learning technology enables the system to have the ability to self-learn and evolve. Through continuous interaction with users, the system can continuously optimize the model and improve the accuracy of understanding user intentions. In addition, emotion recognition technology allows the system to perceive the user's emotions and respond accordingly, enhancing the warmth of human-computer interaction. The combination of these technologies enables the voice interaction system to provide users with personalized health management services like a caring health consultant.

[0062] S202. Image data collection and structured processing.

[0063] Image collector configuration: The system is equipped with a high-resolution camera as an image collector, which can clearly capture the medical records, prescriptions and other demand report images provided by users. The camera also supports functions such as autofocus and light adjustment to ensure that high-quality image data can be obtained under different lighting conditions.

[0064] Optical Character Recognition (OCR) Technology: The collected image data is transmitted to the OCR module, which uses deep learning algorithms (such as convolutional neural networks (CNN)) to accurately recognize the text in the image. OCR technology can recognize a variety of fonts, font sizes, and typesetting formats, and convert the text information in the image into editable text data.

[0065] Structured data extraction: The converted text data is input into the structured data extraction module, which uses natural language processing technology and rule engines to further parse and structure the text. By extracting keywords and building data tables, the module can convert text data into structured demand data, such as basic patient information, diagnosis results, and doctor's orders.

[0066] In actual applications, the system will flexibly choose voice or image data collection methods based on the specific needs of users. For users who can clearly express their needs, the system will give priority to voice recognition technology; for users who need to show detailed medical records or prescriptions, the system will collect data through image collectors.

[0067] In an embodiment of the present invention, based on step S3, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner.

[0068] S301. Wireless communication link and sensor signal acquisition.

[0069] Sensor deployment and configuration: Various types of sensors are deployed in the user's living or working environment, such as heart rate sensors, blood pressure sensors, blood sugar sensors, etc., to monitor the user's vital signs in real time. These sensors are connected to the smart medicine box system through wireless communication methods (such as Bluetooth, Wi-Fi, Zigbee, etc.).

[0070] When configuring the sensor, you need to set the frequency and accuracy of data collection to ensure that the sensor signal obtained is accurate and reliable. At the same time, the sensor also needs to be calibrated and maintained regularly to maintain its long-term stable operation.

[0071] Wireless communication link establishment: The smart medicine box system establishes a stable communication link with each sensor through the built-in wireless communication module. The system can automatically identify and connect to nearby sensors to ensure real-time transmission and reception of data.

[0072] In order to ensure the security and reliability of data transmission, the system uses encryption technology and data verification mechanism to prevent data from being stolen or tampered with during transmission.

[0073] Sensor signal reception and conversion: The system receives raw signals from sensors via a wireless communication link, which typically represent the user's vital signs in analog or digital form.

[0074] The received signal is input into the signal processing module, which uses algorithms to filter, amplify, quantify and process the signal, and convert it into readable vital signs data, including key indicators such as heart rate, blood pressure and blood sugar.

[0075] S302. Comparison of physical sign data and indicators.

[0076] Vital sign indicator settings: When the system is initialized, it will preset a set of reasonable vital sign indicator ranges based on the user's health status, age, gender, etc. These indicator ranges are formulated based on medical standards and expert advice to assess whether the user's vital signs are normal.

[0077] Users can also adjust and optimize the preset indicator range according to their actual situation.

[0078] Comparison of physical sign data: The system compares the vital signs data obtained in real time with the preset indicator range to determine whether the user's vital signs are within the normal range.

[0079] If the vital sign data exceeds the indicator range, the system will mark the data as abnormal vital sign data and trigger the corresponding alarm mechanism to remind the user to pay attention to their health status.

[0080] S303. Generate temporary demand data.

[0081] For data marked as abnormal signs, the system can automatically generate temporary demand data based on pre-set corresponding rules and abnormal signs data.

[0082] Examples of corresponding rules include: Abnormal heart rate corresponding rules: Abnormal heart rate identification: The system monitors the user's heart rate data in real time and compares it with the preset heart rate index range. If the heart rate data exceeds the normal range (such as the heart rate is too fast or too slow), the system will mark the heart rate data as abnormal physical sign data.

[0083] Corresponding drug selection: For abnormal heart rate, the system automatically selects appropriate drugs for recommendation based on the preset corresponding rules. Take Suxiao Jiuxin Pills as an example. This drug is usually used to relieve angina pectoris and improve myocardial blood supply. It is suitable for symptoms such as myocardial ischemia caused by excessive heart rate.

[0084] When selecting medicines, the system will comprehensively consider factors such as the user's health status, allergy history, medication history, etc. to ensure that the recommended medicines are safe and effective.

[0085] Dosage determination: The system automatically calculates and determines the dosage of the Quick-acting Heart-saving Pills based on the user's personal information such as weight, age, gender, and the severity of the abnormal heart rate. The dosage includes the dose and frequency of each dose to ensure that the user can take the medicine at the correct dose and frequency.

[0086] Other abnormal signs corresponding rules: In addition to abnormal heart rate, the system also has corresponding rules for other abnormal physical signs. For example: Abnormal blood pressure: The system will determine whether the user has symptoms of hypertension or hypotension based on the blood pressure data, and recommend corresponding antihypertensive or pressor drugs.

[0087] Abnormal blood sugar: The system will determine whether the user has symptoms of hyperglycemia or hypoglycemia based on blood sugar data, and recommend corresponding blood sugar-lowering drugs or methods of sugar supplementation.

[0088] Abnormal breathing: The system will determine whether the user has symptoms such as shortness of breath or difficulty breathing based on the breathing data, and recommend appropriate breathing assistance equipment or drugs.

[0089] These demand data include the drug information (such as drug name, specifications, manufacturer, etc.) and dosage (such as dosage per dose, frequency of use, etc.) currently required by the user.

[0090] The corresponding rules are formulated based on medical knowledge, drug instructions and expert advice, and are used to guide the system on how to generate reasonable medication recommendations based on abnormal physical sign data.

[0091] In an embodiment of the present invention, based on step S4, a possible embodiment is given below to illustrate its specific implementation scheme in a non-limiting manner.

[0092] Extracting drug information from the temporary demand data is a step that is performed in response to the user's current health status or sudden demand. The system first parses the temporary demand data and extracts the drug information currently required by the user, which usually includes key information such as drug name and dosage. Next, the system determines whether the drug information exists in the drug list containing the drug information.

[0093] If the drug information is in the drug list, it means that the drug the user needs is already in the medicine box. At this time, the system will immediately generate a temporary medication plan and set the medication time of the temporary medication plan to the current system time to ensure that the user can get the required drugs as soon as possible. This temporary medication plan will list in detail the name of the drug the user needs to take, the dosage, and the method of taking.

[0094] However, if the drug information does not exist in the drug list, that is, the drug required by the user is not available in the medicine box, the system will generate a voice prompt message. This voice prompt message will inform the user which drugs are currently missing in the medicine box and suggest that the user replenish these drugs as soon as possible or seek other ways to obtain the required drugs.

[0095] In addition to processing temporary demand data, the system will also match the structured data with the drug information in the drug list. Structured data is usually collected and converted by a microphone or image collector, and it contains the user's specific needs for taking medicine. The system will generate the medication time and corresponding dosage based on these matched drug information. For multiple drug information, the system will integrate their medication time and corresponding dosage to form a complete medication plan.

[0096] While generating the medication plan, the system will also notice medications that do not match the medication list. These mismatches may mean that the user has made a request that cannot be met by the current medicine cabinet, or that the user may have entered some incorrect information. In this case, the system will generate another voice prompt to inform the user of the mismatch and suggest that the user check or correct the information they entered.

[0097] In summary, the system can generate a feasible medication plan for users by comprehensively processing temporary demand data, structured data and drug list information. At the same time, the system can also inform users of possible problems or actions to be taken in a timely manner through voice prompts.

[0098] In a specific exemplary scenario, a medication regimen is generated as follows: Temporary demand data: One night, Xiao Zhang felt feverish and his cough worsened, so he sent a voice command to the system through the microphone of the smart medicine box: "I need antipyretics and cough syrup." After receiving this voice command, the system will convert it into structured data and extract the drug information: antipyretics and cough syrup.

[0099] Drug List Judgment: The system then checks to see if the drug list contains the two drugs. Assume that the drug list does contain the two drugs and that their quantities are sufficient for Xiao Zhang to use.

[0100] Temporary medication plan generation: Since Xiao Zhang suddenly felt unwell at night, the system will set the medication time of the temporary medication plan to the current system time, that is, take the medicine immediately. The system will also calculate the appropriate dosage of the medicine based on the recommended dosage of the medicine and Xiao Zhang's weight and other information, and generate a detailed temporary medication plan, such as: "Please take XX ml of antipyretic medicine and XX ml of cough syrup immediately, and take it orally." Structured data processing: In addition to temporary demand data, the system also processes the pictures of cold medicine instructions uploaded by Xiao Zhang through the image collector. The system uses text recognition technology to convert the pictures into structured data and extract the information of the cold medicine, including the name of the medicine, usage and dosage, etc.

[0101] Medication regimen integration: The system will match the cold medicine information with the medicine list and generate the time and amount of medicine to be taken based on the matched medicine information. Since cold medicine is used to prevent and treat colds, the system may generate a long-term medication plan for Xiao Zhang based on the severity of his cold and the recommended usage of the medicine, such as: "Take one cold medicine tablet each morning and evening for three days." Then, the system will integrate this long-term medication plan with the previous temporary medication plan to form a complete medication plan, ensuring that Xiao Zhang can take all the necessary medicines on time and in the right amount.

[0102] Mismatch information processing: If Xiao Zhang mentions a drug that the system does not recognize (such as a folk remedy) in a voice command, the system will mark it as mismatched information and generate a voice prompt message: "The XX drug you mentioned is not found in the system. Please check the name of the drug or seek other ways to obtain it." Through the above examples, we can see how the smart medicine box system can comprehensively process temporary demand data, structured data and drug list information to generate a medication plan that meets the user's current health needs. At the same time, the system can also promptly inform users of possible problems or actions to be taken through voice prompts, thereby providing users with a more convenient and safe medication experience.

[0103] In an embodiment of the present invention, based on step S5, a possible embodiment is given below to illustrate its specific implementation in a non-limiting manner.

[0104] In the smart medicine box system, breaking down the medication plan into scheduled tasks is a crucial step. This not only ensures that users take medication on time, but also improves the accuracy and convenience of medication. The following is a detailed description of this process: Setting of scheduled tasks. The system will automatically set a series of scheduled tasks based on the generated medication plan. These tasks will be triggered at specific time nodes to remind users to take medication. Setting of scheduled tasks usually includes the following key steps: Extract medication time: The system will first extract the medication time of all drugs from the medication plan. These times may be fixed (such as 8 am every day) or dynamically adjusted according to the user's actual situation (such as taking medication every 4 hours).

[0105] Set task trigger points: Based on the extracted medication time, the system will set corresponding task trigger points internally. When the system time reaches these trigger points, the scheduled task will be activated.

[0106] Configure task content: Each scheduled task will contain a series of specific operations. For the smart medicine box system, these operations usually include playing voice prompts and sending unlock instructions to the medicine box lock.

[0107] Voice prompt playback: When the scheduled task is activated, the system will immediately play the preset voice prompt information. These prompts are customized according to the specific content of the medication plan to ensure that users can clearly understand the name, dosage and method of taking the medicine to be taken. For example, the system may play: "Please take XX ml of antipyretic medicine and XX ml of cough syrup, and take it orally." Such prompt information is concise and clear, and can effectively guide users to take the medicine correctly.

[0108] Unlocking the medicine box lock: In addition to playing the voice prompt, the system will also send an unlock command to the medicine box lock. The purpose of this step is to ensure that the user can easily open the medicine box and take out the required medicines. After receiving the unlock command, the medicine box lock will automatically unlock, allowing the user to open the medicine box door. At the same time, the system will also record this operation for subsequent medication monitoring and data analysis.

[0109] Execution and monitoring of scheduled tasks: During the execution of a scheduled task, the system will continuously monitor the execution of the task. If the task is not executed on time (such as the user does not take the medicine on time), the system will remind you through voice prompts or text messages. In addition, the system will also record the user's medication history so that doctors or family members can understand the user's medication status and make necessary adjustments or interventions accordingly.

[0110] In summary, breaking down medication plans into scheduled tasks is an important function in the smart medicine box system. It not only ensures that users take medication on time, but also improves the accuracy and convenience of medication. Through this function, the system can provide users with more comprehensive and detailed medication services, thereby ensuring the health and safety of users.

[0111] On the basis of the above embodiment, in order to further improve the reliability of the medication scheme provided in the above embodiment, a feasible way is to construct a medication prediction model, which is as follows: The system conducts in-depth mining and analysis of the massive amount of medication data collected. First, the system will clean and preprocess the raw data to remove noise and outliers to ensure the accuracy and completeness of the data. Next, the data will be feature engineered to extract features that are valuable for analysis, such as medication frequency, medication time, drug type, dosage, etc. These features will serve as the basis for subsequent analysis. Next, the system will use a variety of data mining and machine learning algorithms to conduct in-depth analysis of the data. For example, cluster analysis can be used to divide users into different groups according to their medication habits in order to provide targeted services; association rule mining can be used to discover the interaction relationship between drugs; and classification algorithms can be used to predict whether users will have adverse reactions. In addition, the system can also establish a predictive model to predict users' future medication behavior, such as predicting whether users will miss medication.

[0112] Through in-depth analysis of the data, the system can identify potential problems that users may have during medication, such as irregular medication, drug interactions, allergic reactions, etc. At the same time, the system can also provide users with personalized medication recommendations based on the analysis results to help users better manage their medication. For example, the system can remind users to pay attention to drug interactions or suggest users to adjust medication dosages. In addition, the data analysis module can also provide valuable reference information for doctors and pharmacists to help them better serve patients.

[0113] Convert the system's instructions into actual physical actions. First, the user sends a medicine-taking instruction to the system through voice commands or touch screens. After receiving the instruction, the system will parse the instruction and determine the medicine that needs to be taken out. Then, the system will send the instruction to the hardware control module. According to the instruction, the hardware control module will control the actuators such as stepper motors and servo motors to accurately drive the movement of the medicine box. For example, when the user needs to take out a certain compartment of medicine, the hardware control module will control the motor to move the corresponding compartment to the medicine-taking position and open the medicine box. At the same time, the hardware control module will also control the lighting system to facilitate users to take medicine.

[0114] In order to ensure the safe storage of medicines, the hardware control module will work closely with the sensor. The sensor will monitor the temperature, humidity and other environmental conditions in the medicine box in real time and feed the data back to the system. The system will monitor the environment in the medicine box in real time based on the sensor data. Once it detects that the environmental conditions are beyond the set range, the system will issue an alarm and take corresponding measures, such as turning on the refrigeration equipment to lower the temperature.

[0115] Medication monitoring and recording. When using the system for the first time, users need to create a personal account in the cloud and upload their personal information, medication records and other data. These data will be securely stored on the cloud server. Secondly, the system will regularly synchronize the new medication data generated by users to the cloud to ensure the real-time and integrity of the data. At the same time, the cloud service will provide a unified data interface to facilitate different devices and applications to access and call these data. For example, users can access their medication records, query drug information, and set up the system through mobile APP, web pages, etc. In addition to data storage and management functions, cloud services can realize data backup and recovery to ensure data security. When users change devices or the system fails, data can be restored through the cloud. In addition, cloud services can also realize automatic system upgrades to ensure that users always use the latest system functions. At the same time, cloud services can also provide data analysis and mining functions to help users better understand their medication and provide valuable data support for doctors and pharmacists.

[0116] The user management function is the foundation of the entire smart medicine box system and is responsible for the authentication and management of user identities. First, users can register through mobile APP or web pages. During the registration process, users need to provide some basic information, such as mobile phone number, email address, password, etc. The system will verify the mobile phone number provided by the user to ensure the authenticity of the information. After successful registration, the system will generate a unique user ID for each user as the user's identity in the system. At the same time, the system will encrypt and store the user's password to protect the user's privacy. Users can modify their personal information in the personal center, including name, gender, age, contact information, etc. In addition, users can also set their own medication plans, view historical medication records, and personalize the system. In order to ensure the security of user data, the system will take a series of security measures. For example, the https protocol is used to transmit data to prevent data from being stolen during transmission; a strong password encryption algorithm is used to protect the security of user passwords; and the system is regularly scanned and repaired for vulnerabilities to prevent hacker attacks. In addition, the system will also provide multiple authentication functions, such as SMS verification codes and email verification codes, to further enhance the security of user accounts.

[0117] The intelligent monitoring function integrates multiple sensors, such as heart rate sensors, blood pressure sensors, and blood oxygen sensors, to achieve real-time monitoring of human physiological data. These sensors are usually integrated into wearable devices, smart home devices, or medical devices. The collected physiological data will be transmitted to a cloud server or local storage device via a wireless network. In the cloud, the data will be cleaned, processed, and analyzed. Through data mining, machine learning, and other technologies, the system can establish a personal health model for the user and monitor his or her health status in real time. For example, the system can analyze heart rate variability to assess heart health, determine respiratory function through blood oxygen saturation, and assess cardiovascular disease risk based on blood pressure data. Based on the analysis of the data, the system can provide users with personalized health advice. For example, if the system finds that the user's blood pressure is long-term high, it will remind the user to pay attention to diet and lifestyle habits, and recommend regular physical examinations. In addition, the system can also set a health warning function. When the user's physiological data exceeds the normal range, the system will promptly issue an alarm to the user or his or her emergency contact so that medical measures can be taken in time.

[0118] In order to help users better understand their health status, the system provides a graphical interface to visualize complex physiological data in the form of charts, curves, etc. Users can view their health data through this interface, understand their physical change trends, and communicate with doctors. At the same time, the system can also correlate the data with other health data (such as exercise data, sleep data) to provide a more comprehensive health assessment.

[0119] In some embodiments, the multifunctional medicine box control system may include a plurality of functional modules composed of computer program segments. The computer programs of the various program segments in the multifunctional medicine box control system may be stored in a memory of a computer device and executed by at least one processor to perform (see Figure 1 Description) Functions of multi-function medicine box control.

[0120] In this embodiment, the multifunctional medicine box control system can be divided into multiple functional modules according to the functions it performs, such as Figure 2 As shown. The functional modules of the system 200 may include: an information entry module 210, a first acquisition module 220, a second acquisition module 230, a solution generation module 240 and a task generation module 250. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in a memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0121] An information input module, used to collect images of medicines placed in the medicine box and recognize medicine information based on the images of the medicines; A first acquisition module, used for acquiring demand data through a microphone or an image collector, and converting the demand data into structured data; A second acquisition module, used for acquiring vital sign data through sensors, and generating temporary demand data based on the vital sign data; A scheme generating module, used for generating a medication scheme based on the drug information, the structured data and the temporary demand data; The task generation module is used to decompose the medication regimen into scheduled tasks, wherein the scheduled tasks include playing a voice prompt at a target time and sending an unlocking instruction to the medicine box lock.

[0122] Optionally, as an embodiment of the present invention, collecting an image of a medicine placed in a medicine box, and recognizing medicine information based on the image of the medicine includes: Collect images of medicines through cameras deployed in medicine boxes; Uploading the drug image to a cloud, where a recognition model is deployed; Receive drug information returned from the cloud, including drug name, usage and dosage, contraindications, indications, production date, and shelf life; The drug information is saved to the drug list.

[0123] Optionally, as an embodiment of the present invention, the recognition model includes: A Stacking model, wherein the base model of the Stacking model comprises an optical character recognition sub-model and a target recognition sub-model, wherein the optical character recognition sub-model recognizes the identity of a drug based on text features of the drug image, and the target recognition sub-model recognizes the identity of a drug based on appearance features of the drug image; the drug identity comprises a drug name, a manufacturer, and a batch code.

[0124] Optionally, as an embodiment of the present invention, it further includes: Based on the drug identity, the cloud retrieves corresponding drug information from a pre-built drug information database and sends the drug information to the multi-functional medicine box control terminal.

[0125] Optionally, as an embodiment of the present invention, collecting demand data through a microphone or an image collector, and converting the demand data into structured data, includes: Collecting voice data through a microphone and converting the voice data into structured demand data; The demand report image is collected by an image collector, and the demand report image is converted into structured demand data using text recognition technology.

[0126] Optionally, as an embodiment of the present invention, collecting vital sign data through a sensor, and generating temporary demand data based on the vital sign data, includes: Acquire sensor signals through a wireless communication link and convert the sensor signals into vital sign data; Comparing the physical sign data with a preset physical sign index, and if the physical sign data is not within a reasonable range defined by the physical sign index, marking the physical sign data as abnormal physical sign data; Based on the preset corresponding rules and the abnormal vital sign data, temporary demand data is generated, and the temporary demand data includes the required drug information and dosage.

[0127] Optionally, as an embodiment of the present invention, generating a medication plan based on the drug information, the structured data and the temporary demand data includes: Extract drug information from the temporary demand data, determine whether the drug information exists in the drug list containing drug information, generate a temporary medication plan if the drug information exists in the drug list, and set the medication time of the temporary medication plan to the current system time; if the drug information does not exist in the drug list, generate a voice prompt message; The structured data is matched with the drug information in the drug list, a medication time and a corresponding medication amount are generated based on the matched drug information, and the medication time and corresponding medication amount of multiple drug information are integrated into a medication plan; and voice prompt information is generated based on unmatched drug information.

[0128] Figure 3 The multifunctional medicine box control method provided for the embodiment of the present application can be applied to equipment. It will be appreciated by those skilled in the art that the equipment structure involved in the embodiment of the present invention does not constitute a limitation on the equipment, and the equipment may include more or less components than shown, or combine certain components, or different component arrangements. In an embodiment of the present invention, the equipment includes but is not limited to laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The equipment may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples, and are not intended to limit the implementation of the embodiments of the present application described herein and / or required.

[0129] The device 300 may include: a processor 310, a memory 320 and a communication unit 330. These components communicate via one or more buses. Those skilled in the art will appreciate that the server structure shown in the figure does not limit the present invention, and it may be a bus structure or a star structure, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0130] The memory 320 may be used to store the execution instructions of the processor 310, and the memory 320 may be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the device 300 is enabled to perform some or all of the steps in the following method embodiments.

[0131] The processor 310 is the control center of the storage device, and uses various interfaces and lines to connect various parts of the entire electronic device. It runs or executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic device and / or process data. The processor can be composed of an integrated circuit (IC), for example, it can be composed of a single packaged IC, or it can be composed of a plurality of packaged ICs with the same or different functions. For example, the processor 310 can include only a central processing unit (CPU). In an embodiment of the present invention, the CPU can be a single computing core or multiple computing cores.

[0132] The communication unit 330 is used to establish a communication channel so that the storage device can communicate with other devices, receive user data sent by other devices or send user data to other devices.

[0133] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and when the program is executed, the program may include some or all of the steps in each embodiment provided by the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0134] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution in the embodiments of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, and other media that can store program codes, including several instructions for enabling a computer device (which can be a personal computer, a server, or a second device, a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0135] In this specification, the same or similar parts between the various embodiments can be referred to each other. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiment.

[0136] In the several embodiments provided by the present invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of systems or modules, which can be electrical, mechanical or other forms.

[0137] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, each functional module in each embodiment of the present invention may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0139] Although the present invention has been described in detail with reference to the accompanying drawings and in combination with the preferred embodiments, the present invention is not limited thereto. Without departing from the spirit and essence of the present invention, a person of ordinary skill in the art may make various equivalent modifications or substitutions to the embodiments of the present invention, and these modifications or substitutions shall be within the scope of the present invention. Any person of ordinary skill in the art may easily think of changes or substitutions within the technical scope disclosed by the present invention, and these shall be within the scope of protection of the present invention.

Claims

1. A multifunctional medicine box control method, characterized in that: include: Collecting images of medicines put into the medicine box, and identifying medicine information based on the images of medicines; Collecting demand data through a microphone or an image collector, and converting the demand data into structured data; Collecting vital sign data through sensors, and generating temporary demand data based on the vital sign data; generating a medication regimen based on the drug information, the structured data, and the temporary demand data; The medication regimen is broken down into timed tasks, which include playing a voice prompt at a target time and sending an unlocking instruction to the medicine box lock.

2. The method according to claim 1, characterized in that: Collecting images of medicines put into a medicine box, and recognizing medicine information based on the images of medicines, including: Collect images of medicines through cameras deployed in medicine boxes; Uploading the drug image to a cloud, where a recognition model is deployed; Receive drug information returned from the cloud, including drug name, usage and dosage, contraindications, indications, production date, and shelf life; The drug information is saved to the drug list.

3. The method according to claim 2, characterized in that The recognition model includes: A Stacking model, wherein the base model of the Stacking model comprises an optical character recognition sub-model and a target recognition sub-model, wherein the optical character recognition sub-model recognizes the identity of a drug based on text features of the drug image, and the target recognition sub-model recognizes the identity of a drug based on appearance features of the drug image; the drug identity comprises a drug name, a manufacturer, and a batch code.

4. The method according to claim 3, characterized in that: The method further comprises: Based on the drug identity, the cloud retrieves corresponding drug information from a pre-built drug information database and sends the drug information to the multi-functional medicine box control terminal.

5. The method according to claim 1, characterized in that Collecting demand data through a microphone or an image collector, and converting the demand data into structured data, including: Collecting voice data through a microphone and converting the voice data into structured demand data; The demand report image is collected by an image collector, and the demand report image is converted into structured demand data using text recognition technology.

6. The method according to claim 1, characterized in that Collecting vital sign data through sensors and generating temporary demand data based on the vital sign data, including: Acquire sensor signals through a wireless communication link and convert the sensor signals into vital sign data; Comparing the physical sign data with a preset physical sign index, and if the physical sign data is not within a reasonable range defined by the physical sign index, marking the physical sign data as abnormal physical sign data; Based on the preset corresponding rules and the abnormal vital sign data, temporary demand data is generated, and the temporary demand data includes the required drug information and dosage.

7. The method according to claim 1, characterized in that Generating a medication plan based on the drug information, the structured data, and the temporary demand data includes: Extract drug information from the temporary demand data, determine whether the drug information exists in the drug list containing drug information, generate a temporary medication plan if the drug information exists in the drug list, and set the medication time of the temporary medication plan to the current system time; if the drug information does not exist in the drug list, generate a voice prompt message; The structured data is matched with the drug information in the drug list, a medication time and a corresponding medication amount are generated based on the matched drug information, and the medication time and corresponding medication amount of multiple drug information are integrated into a medication plan; and voice prompt information is generated based on unmatched drug information.

8. A multifunctional medicine box control system, characterized in that: include: An information input module, used to collect images of medicines placed in the medicine box and recognize medicine information based on the images of the medicines; A first acquisition module, used for acquiring demand data through a microphone or an image collector, and converting the demand data into structured data; A second acquisition module, used for acquiring vital sign data through sensors, and generating temporary demand data based on the vital sign data; A scheme generating module, used for generating a medication scheme based on the drug information, the structured data and the temporary demand data; The task generation module is used to decompose the medication regimen into scheduled tasks, wherein the scheduled tasks include playing a voice prompt at a target time and sending an unlocking instruction to the medicine box lock.

9. A device, characterized in that: include: A memory, used for storing a multifunctional medicine box control program; A processor is used to implement the steps of the multifunctional medicine box control method as described in any one of claims 1 to 7 when executing the multifunctional medicine box control program.

10. A computer-readable storage medium storing a computer program, characterized in that: The readable storage medium stores a multifunctional medicine box control program, and when the multifunctional medicine box control program is executed by a processor, the steps of the multifunctional medicine box control method according to any one of claims 1 to 7 are implemented.

Images