Dangerous drug cabinet based on emotion recognition

Abstract

The application relates to the field of medical devices and discloses a dangerous drug cabinet based on emotion recognition, which prevents patients from taking or returning dangerous drugs when they are in a bad mood. The dangerous drug cabinet comprises a cabinet body, an electronic lock system, a drug detection system, an emotion recognition system and an alarm system. The cabinet body is divided into a first area and a second area. The first area is used for storing dangerous drugs less than a dangerous dose. The drug detection system comprises a first RFID reader and a second RFID reader, which are respectively used for detecting the number of dangerous drugs in different areas. If the number of dangerous drugs in the first area is detected to exceed a dangerous dose, the alarm system sends an alarm to a monitoring terminal. The emotion recognition system is used for voice interaction with a drug taker. An LLM is used to identify the emotional state of the drug taker from the content of the interaction. When the emotional state of the drug taker is abnormal, the first area is unlocked, the second area is locked, and the alarm system sends an alarm. When the emotional state of the drug taker is normal, the second area is unlocked.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and more specifically to a dangerous medicine cabinet technology based on emotion recognition. Background Technology

[0002] This section is intended to provide background or context for the embodiments of this application as set forth in the claims. The description herein is not intended to imply that it is prior art that has been disclosed, simply because it is included in this section.

[0003] Some common household medications, such as strong analgesics and sleeping pills, while having important medical uses, can pose serious health risks and even life-threatening dangers if overused. This is especially true for individuals with mental illnesses or at risk of suicide, where improper use of these medications could lead to tragedy.

[0004] In many families, medication management often relies on individual self-control or supervision from family members. This approach has its flaws; patients may overdose on medication when in a bad mood, especially when unconscious or disoriented, or fail to take medication on time or in the correct dosage.

[0005] Family supervision may not be timely or comprehensive enough, especially when family members are busy at work or away from home. Even if family members notice abnormal consumption of medication, it may be too late, such as overdose leading to acute reactions, or repeated failure to take medication causing the condition to worsen.

[0006] Existing smart medicine cabinets cannot determine the patient's emotional state to provide different dosages of medicine or remind family members of changes in the amount of medicine, thus preventing patients from taking or putting back dangerous medicines when they are in a bad mood. Summary of the Invention

[0007] The purpose of this invention is to provide a dangerous medicine cabinet based on emotion recognition to prevent patients from taking or putting back dangerous medicines when they are in a bad mood.

[0008] In this invention, an emotion-recognition-based hazardous medicine cabinet is provided, comprising a cabinet body, an electronic lock system, a medicine detection system, an emotion recognition system, and an alarm system.

[0009] The cabinet is divided into a first area and a second area. The first area is used to store dangerous drugs in doses less than the dangerous dose, and the second area is used to store dangerous drugs in doses greater than the dangerous dose. The electronic lock system includes multiple electronic locks, and the first area and the second area are controlled to open and close by different electronic locks.

[0010] The drug detection system includes a first RFID reader and a second RFID reader. Each hazardous drug is individually packaged in a package containing RFID. The first RFID reader is used to detect the quantity of hazardous drugs in the first area by reading the RFID information in the first area. If the first RFID reader detects that the quantity of hazardous drugs in the first area exceeds the dangerous dose, the alarm system sends an alarm to the monitoring terminal.

[0011] The second RFID reader is used to detect the quantity of hazardous drugs in the second area by reading the RFID information in the second area;

[0012] The emotion recognition system is used to interact with the person picking up the medication via voice. It uses LLM to identify the emotional state of the person picking up the medication from the content of the interaction. When the emotional state of the person picking up the medication is abnormal, the first area is unlocked and the second area is locked. The alarm system sends an alarm to the monitoring terminal. When the emotional state of the person picking up the medication is normal, the second area is unlocked.

[0013] In a preferred embodiment, a storage system is also included:

[0014] The drug detection system is also used to record the time when the types and quantities of dangerous drugs in different areas change through the first RFID reader and the second RFID reader, and to verify them with the prescriptions recorded in the storage system. When the quantity of dangerous drugs taken in a single transaction exceeds the dangerous dose or the frequency of drug taking exceeds the prescription requirements, an alarm is issued to the monitoring terminal.

[0015] In a preferred embodiment, the LLM includes an intelligent voice assistant powered by GPT;

[0016] The emotion recognition system is also used to remind the person taking the medication via voice and / or to provide care when the person's emotional state is abnormal.

[0017] In a preferred embodiment, the system further includes a video control system for performing facial recognition on the person picking up the medication via video to confirm their identity.

[0018] In a preferred embodiment, the system further includes a video control system for monitoring the medication taker via video and confirming that the taker has completed the action of swallowing the medication.

[0019] In a preferred embodiment, the emotion recognition system is further used to determine the emotional state of the person picking up the medication by recognizing changes in their facial expressions through video, and to verify the emotional state detected by voice.

[0020] In a preferred embodiment, when the packaging of a hazardous drug is intact, the RFID information on the packaging can be detected by the drug detection system; when the packaging of a hazardous drug is damaged, the RFID information on the packaging cannot be detected by the drug detection system.

[0021] In a preferred embodiment, the drug detection system further includes a weight sensor, which is used to determine the change in the quantity of the drug by the change in the weight of the drug, and to verify the quantity of the drug detected by RFID.

[0022] In a preferred embodiment, the system also includes a WiFi module or a Bluetooth module. The storage system is further used to record information about when the hazardous drugs are taken and to generate a report. The WiFi module or Bluetooth module is used to transmit the generated report to the cloud or to a monitoring terminal.

[0023] In a preferred embodiment, a central control system is also included:

[0024] The central control system supports the operation of the electronic lock system, the drug detection system, the emotion recognition system, and the alarm system, and supports the input and output of data and command information within the above systems.

[0025] The main differences and effects of the embodiments of the present invention compared with the prior art are as follows:

[0026] To prevent patients from taking or returning dangerous medications when they are in a bad mood;

[0027] Furthermore, in case of abnormal use of dangerous medications, family members should be notified promptly, and patients should be reminded and cared for to ensure they have swallowed the medication.

[0028] It should be understood that, within the scope of this invention, the above-described technical features of this invention and the technical features specifically described below (such as in the embodiments) can be combined with each other to form new or preferred technical solutions. Due to space limitations, they will not be described in detail here. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0030] Figure 1 This is a schematic diagram of a hazardous medicine cabinet structure according to one embodiment of this application.

[0031] Figure 2This is a schematic diagram of the relationship of a hazardous medicine cabinet system according to one embodiment of this application.

[0032] Figure 3 This is a schematic diagram of the relationship of a hazardous medicine cabinet system according to one embodiment of this application.

[0033] Figure 4 This is a schematic diagram of a dangerous drug packaging according to one embodiment of this application.

[0034] The labels in each of the attached figures are as follows:

[0035] 1-Cabinet;

[0036] 101 - First Area;

[0037] 102 - Second Region;

[0038] 2-Electronic lock system;

[0039] 3-Drug testing system;

[0040] 301 - First RFID Reader;

[0041] 302 - Second RFID reader;

[0042] 303 - Weight sensor;

[0043] 4-Emotion recognition system;

[0044] 5-Alarm system;

[0045] 6-Storage system;

[0046] 7-Video Control System;

[0047] 8-WiFi module / Bluetooth module;

[0048] 9-Central control system;

[0049] 10. Packaging of hazardous drugs;

[0050] 1001 - Tear open the seam;

[0051] 1002-RFID tag. Detailed Implementation

[0052] In the following description, many technical details are presented to help the reader better understand this application. However, those skilled in the art will understand that the technical solutions claimed in this application can be implemented even without these technical details and various variations and modifications based on the following embodiments.

[0053] Explanation of some concepts

[0054] LLM: Large Language Model, refers to a deep learning model trained on a large amount of text data that can generate natural language text or understand the meaning of language text.

[0055] GPT: Generative Pre-Trained Transformer, is a deep learning model for text generation trained on available internet data.

[0056] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0057] One embodiment of this application relates to a hazardous medicine cabinet based on emotion recognition. The device includes a cabinet body 1, an electronic lock system 2, a medicine detection system 3, an emotion recognition system 4, and an alarm system 5.

[0058] Cabinet 1 structure as follows Figure 1 As shown, the cabinet 1 is divided into a first area 101 and a second area 102. The first area 101 is used to store hazardous medicines in doses smaller than the dangerous dose, and the second area 102 is used to store hazardous medicines in doses larger than the dangerous dose. The electronic lock system 2 includes multiple electronic locks, and the opening and closing of the first area 101 and the second area 102 are controlled by different electronic locks. Considering the convenience and safety of home use, the hazardous medicine cabinet is designed to be easy to store medicines and easy to operate. The division of areas and the presence of electronic locks ensure that the quantity of medicines is more accurately controlled.

[0059] The drug detection system 3 includes a first RFID (Radio Frequency Identification) reader 301 and a second RFID reader 302. Each hazardous drug is individually packaged in a RFID-containing package 10. The first RFID reader 301 detects the quantity of hazardous drugs in the first area 101 by reading the RFID information. If the first RFID reader 301 detects that the quantity of hazardous drugs in the first area 101 exceeds the dangerous dose, the alarm system 5 sends an alarm to the monitoring terminal (assuming the monitoring terminal is controlled by a family member, medical staff, or security administrator). This alarm is to prevent situations where too many drugs are placed, causing danger, or where a person takes the drugs but does not take them and then puts them back. The alarm can be sent via telephone, SMS, or a mobile app notification.

[0060] The second RFID reader 302 is used to detect the quantity of hazardous drugs in the second area 102 by reading the RFID information in the second area 102.

[0061] In one embodiment, a storage system 6 is also included:

[0062] The drug detection system 3 is also used to record the time when the types and quantities of dangerous drugs in different areas change through the first RFID reader 301 and the second RFID reader 302, and to check them against the prescriptions recorded in the storage system 6. When the quantity of dangerous drugs taken in a single instance exceeds the dangerous dose or the frequency of drug taking exceeds the prescription requirements, an alarm is sent to the monitoring terminal. The alarm is to prevent drug takers from taking more drugs than they are required to consume.

[0063] The dangerous dosage of each medicine is determined from the prescription, such as when the guardian or doctor uploads the prescription according to the prescribed document format, or when it is pre-set by the guardian or safety administrator, such as when the medicine is placed for the first time, the original data is entered, including the total amount of medicine, the dosing interval and the single dose.

[0064] In one embodiment, when the packaging 10 of the hazardous drug is intact, the RFID information on the packaging 10 can be detected by the drug detection system 3. When the packaging 10 of the hazardous drug is damaged, i.e., when the RFID tag 1002 is destroyed along the tear line 1001, the RFID information on the packaging 10 cannot be detected by the drug detection system 3. Figure 4 As shown. This ensures that the quantity of medicine detected by the first RFID reader 301 and / or the second RFID reader 302 changes whenever medicine is taken out of or put back into the hazardous medicine cabinet.

[0065] The emotion recognition system 4 is used for voice interaction with the medication user. It uses LLM (Low-Level Management) to assess the patient's tone, speed, and language content from the interaction to identify potential emotional states and mental health issues. When the user's emotional state is abnormal, the first area 101 unlocks, the second area 102 locks, and the alarm system 5 sends an alert to the monitoring terminal. When the user's emotional state is normal, the second area 102 unlocks. The relationships between the systems are as follows: Figure 2 As shown. Because patients can only access medication in Zone 101 when they are in a bad mood, they cannot access potentially life-threatening doses.

[0066] In comparison, the medication placement requirements in Zone 101 are very strict, which can effectively prevent patients from taking or returning dangerous medications, but the frequency of placement is too high. The medication placement requirements in Zone 102 are more lenient, with the quantity only monitored after the patient takes the medication, but it can still effectively supervise the patient's use of dangerous medications. The two zones are open to patients according to their different emotional states, combining the advantages of the two management methods and improving the effectiveness of intelligent management.

[0067] In one embodiment, the LLM includes a GPT-powered intelligent voice assistant; by integrating this GPT-powered intelligent voice assistant, the smart medicine cabinet becomes more than just a medication management tool; it transforms into a comprehensive health management partner. This system helps patients, especially those with mental illnesses, better manage their health, while providing valuable health data to healthcare professionals, enabling more personalized medical services.

[0068] The emotion recognition system 4 is also used to remind patients of their medication needs via voice and / or provide care when their emotional state is abnormal. Based on the patient's response, the voice assistant can provide personalized health advice, such as relaxation exercises, suggestions for outdoor activities, or reminders to schedule a doctor's appointment. If the patient exhibits negative emotions during the conversation, such as excessive anxiety, sadness, or despair, the voice assistant can also provide immediate emotional support as appropriate.

[0069] In one embodiment, a central control system 9 is also included:

[0070] The central control system 9 supports the operation of the electronic lock system 2, the drug detection system 3, the emotion recognition system 4, and the alarm system 5, and supports the input and output of data and command information within the above systems.

[0071] In one embodiment, a video control system 7 is also included. The video control system 7 is used to perform facial recognition on the person retrieving the medication to confirm their identity. The hazardous medicine cabinet is equipped with a high-definition camera facing the patient, using facial recognition technology to confirm that the person operating the cabinet is the patient, preventing unauthorized personnel from accessing the medication.

[0072] In one embodiment, the system further includes a video control system 7, which monitors medication use via video, such as by using a camera to monitor the patient opening the medicine cabinet, taking the medication, and taking it. This confirms that the patient has completed the action of swallowing the medication, preventing situations where patients obtain medication as required but only hoard it without actually taking it, thus avoiding potential risks.

[0073] The video control system 7 uses time series analysis and deep learning algorithms, such as a combination of CNN (Convolutional Neural Networks) and LSTM (Long Short-Term Memory), to identify normal and abnormal medication-taking behaviors based on the training set. If abnormal medication-taking occurs or monitoring becomes more difficult, such as when the patient frequently operates outside the camera's range, additional cameras can be installed around the medication-taking area (such as the bedroom) to capture medication-taking behaviors from all angles.

[0074] In one embodiment, the emotion recognition system 4 is also used to determine the emotional state of the person picking up the medication by recognizing changes in their facial expressions through video, and to verify the emotional state detected by voice, thereby improving the accuracy of emotion recognition.

[0075] In one embodiment, the drug detection system 3 further includes a weight sensor 303, which is used to determine changes in drug quantity by measuring changes in drug weight and to verify the drug quantity detected by RFID. By using cross-validation of weight data and RFID data, the system can more accurately detect and warn of unusual medication use behaviors, such as overdosing or unrecorded medication dispensing.

[0076] In one embodiment, a WiFi module or Bluetooth module 8 is also included. The storage system 6 is further used to record information about when hazardous drugs are accessed and to generate reports. Conversations with patients and assessment results can also be recorded for analysis. The WiFi module or Bluetooth module 8 is used to transmit the generated reports to the cloud or send them to a monitoring terminal. The relationships between the systems are as follows: Figure 3 As shown.

[0077] It should be noted that in the claims and specification of this patent, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0078] All documents mentioned in this invention are incorporated herein by reference as if each document were individually incorporated by reference. Furthermore, it should be understood that after reading the foregoing teachings of this invention, those skilled in the art can make various alterations or modifications to this invention, and these equivalent forms also fall within the scope defined by the appended claims.

Claims

1. A dangerous medicine cabinet based on emotion recognition, characterized in that, This includes the cabinet, electronic lock system, drug detection system, emotion recognition system, and alarm system. The cabinet is divided into a first area and a second area. The first area is used to store dangerous drugs in doses less than the dangerous dose, and the second area is used to store dangerous drugs in doses greater than the dangerous dose. The electronic lock system includes multiple electronic locks, and the first area and the second area are controlled to open and close by different electronic locks. The drug detection system includes a first RFID reader and a second RFID reader. Each dangerous drug is individually packaged in a package containing RFID. When the package of the dangerous drug is intact, the RFID information on the package can be detected by the drug detection system. When the package of the dangerous drug is damaged, the RFID information on the package cannot be detected by the drug detection system. The first RFID reader is used to detect the quantity of hazardous drugs in the first area by reading the RFID information in the first area. If the first RFID reader detects that the quantity of hazardous drugs in the first area exceeds the dangerous dose, the alarm system sends an alarm to the monitoring terminal. The second RFID reader is used to detect the quantity of hazardous drugs in the second area by reading the RFID information in the second area; The emotion recognition system is used to interact with the patient via voice. It uses LLM to evaluate the patient's tone, speed, and language content from the interaction to identify the patient's emotional state. When the patient's emotional state is abnormal, the first area is unlocked and the second area is locked. The alarm system sends an alarm to the monitoring terminal. When the patient's emotional state is normal, the second area is unlocked.

2. The dangerous medicine cabinet based on emotion recognition according to claim 1, characterized in that, It also includes the storage system: The drug detection system is also used to record the time when the types and quantities of dangerous drugs in different areas change through the first RFID reader and the second RFID reader, and to verify them with the prescriptions recorded in the storage system. When the quantity of dangerous drugs taken in a single transaction exceeds the dangerous dose or the frequency of drug taking exceeds the prescription requirements, an alarm is issued to the monitoring terminal.

3. The dangerous medicine cabinet based on emotion recognition according to claim 1, characterized in that, The LLM includes an intelligent voice assistant powered by GPT; The emotion recognition system is also used to remind the person taking the medication via voice and / or to provide care when the person's emotional state is abnormal.

4. The dangerous medicine cabinet based on emotion recognition according to claim 1, characterized in that, It also includes a video control system, which is used to perform facial recognition on the person picking up the medication to confirm their identity.

5. The dangerous medicine cabinet based on emotion recognition according to claim 1, characterized in that, It also includes a video control system, which is used to monitor the medication taker through video and confirm that the medication taker has completed the action of swallowing the medication.

6. The dangerous medicine cabinet based on emotion recognition according to claim 1, characterized in that, The emotion recognition system is also used to determine the emotional state of the person picking up the medication by recognizing changes in their facial expressions through video, and to verify the emotional state detected by voice.

7. The dangerous medicine cabinet based on emotion recognition according to claim 1, characterized in that, The drug detection system also includes a weight sensor, which is used to determine the change in drug quantity by the change in drug weight, and to verify the drug quantity detected by RFID.

8. The dangerous medicine cabinet based on emotion recognition according to claim 2, characterized in that, It also includes a WiFi module or a Bluetooth module. The storage system is also used to record information when dangerous drugs are taken and to generate a report. The WiFi module or Bluetooth module is used to transmit the generated report to the cloud or send it to a monitoring terminal.

9. The dangerous medicine cabinet based on emotion recognition according to claim 1, characterized in that, It also includes a central control system: The central control system supports the operation of the electronic lock system, the drug detection system, the emotion recognition system, and the alarm system, and supports the input and output of data and command information within the above systems.

Images