Intention judgment-based automatic qr code recognition method and system

Abstract

The application belongs to the technical field of medical Internet of Things, and provides a two-dimensional code automatic identification method and system based on intention judgment, which comprises the following steps: when it is judged that a terminal device is in a ready state, a camera is controlled to collect a video stream in a low-power mode in the background; a two-dimensional code in the video stream is detected locally; the scanning intention of a user is judged based on the space-time stability of the two-dimensional code in the picture, such as continuous stay in the central area for more than a preset time length; when it is judged that the scanning intention condition is met, the two-dimensional code is automatically decoded to obtain a device identifier, and a wireless connection is established with a target device. The application solves the problems of complicated two-dimensional code device binding process, low efficiency and easy mis-triggering, realizes a zero-interaction automatic experience of connection upon alignment, significantly improves the operation efficiency, reduces the hardware cost, and fundamentally guarantees the data and privacy security.

Description

Technical Field

[0001] This invention belongs to the field of medical Internet of Things technology, specifically, it relates to a method and system for automatic QR code recognition based on intent judgment. Background Technology

[0002] In modern medical settings, various portable medical devices, such as electronic thermometers, blood pressure monitors, and blood glucose meters, need to be linked to patients or their beds to enable the automatic collection and information management of patients' vital signs data.

[0003] Currently, the main method for linking portable medical devices to patients or hospital beds relies on scanning QR codes using specialized handheld devices (such as nurse PDAs). This requires healthcare workers to perform multiple manual steps: first, locate and open a specific scanning application; then, click the scan button to scan the QR code on the patient's wristband or bedside; next, point the camera at the QR code on the medical device and scan it; and finally, they may need to manually confirm the linking. This process is cumbersome and time-consuming, proving inefficient in the high-intensity, fast-paced work environment of healthcare.

[0004] To simplify operation, some solutions integrate dedicated RFID scanning modules into bedside smart terminal devices (such as bedside screens, bedside displays, and smart gateways). However, this directly increases the material costs and hardware complexity of the devices. Other solutions, in pursuit of higher recognition accuracy, upload video streams or images captured by cameras to cloud servers for analysis and decoding. This not only increases network latency but, more importantly, transmits sensitive data that may contain information about the ward environment and patients to external sources, posing a serious risk of patient privacy leaks and challenges to medical data compliance. Even when using the bedside screen's built-in camera for local processing, current technologies mostly rely on active scanning, requiring users to explicitly initiate the scanning function.

[0005] On the other hand, if the camera is allowed to continuously scan in the background in order to achieve automation, it is easy to cause false triggers and repeated recognitions because the QR code on the medical device may accidentally flash by or stay briefly in the camera's field of view. This not only interferes with the user's normal operation, but also causes unnecessary waste of system resources.

[0006] The patent application document "System and method for actively identifying and displaying relevant content on a touch-sensitive device" (CN108027738A) discloses a technical solution that automatically obtains trigger conditions based on user usage data in an application and provides relevant action or content prompts to the user when the trigger conditions are met. However, it does not address the scenario of QR code recognition and device connection, making it difficult to solve the problems of cumbersome operation, false triggering, and low connection efficiency during the QR code device binding process.

[0007] Patent application document "Device Configuration and Binding Method and Fetal Heart Monitoring System Based on QR Code" (CN117669622A) discloses a technical solution that generates a QR code carrying the configuration information of the bedside machine and the user binding information in the bedside machine, and the device configuration or user binding is completed by scanning and recognizing the QR code by the bedside machine to be configured or the user terminal. However, it still relies on the scanning device to actively scan the QR code and jump to the configuration or binding interface according to the interface to perform the corresponding operation. It still has the problems of many interaction steps, insufficient automation, and difficulty in avoiding accidental triggering of the QR code.

[0008] Therefore, a new method for automatic QR code recognition and device connection is needed to solve the technical problems existing in the current technology of binding QR code devices using bedside smart terminals, such as cumbersome operation process, low efficiency, high hardware cost, privacy and security risks, and easy accidental triggering. Summary of the Invention

[0009] In view of the shortcomings of the prior art, the purpose of this invention is to provide a method and system for automatic QR code recognition based on intent judgment.

[0010] According to the present invention, an automatic QR code recognition method based on intent determination is applied to a bedside or bedside smart terminal device, comprising: When the smart terminal device is in a preset ready state, the camera module of the smart terminal device collects video streams in the background; Smart terminal devices process video streams and detect the presence of QR codes. When a QR code is detected, the system determines whether the preset scanning intent conditions are met based on the spatiotemporal stability of the QR code in the video stream. When the conditions for scanning the code are met, the QR code is automatically decoded to obtain the device identifier. Based on the device identifier, a binding relationship is established between the portable device, the hospital bed, and the patient being measured. This relationship is recorded locally and uploaded to the application server backend.

[0011] The processes of processing the video stream, detecting the QR code, and decoding are all performed locally on the smart terminal device, and the video stream is not uploaded to the cloud server.

[0012] Preferably, the smart terminal device establishes a wireless connection with the portable medical device, including a Bluetooth-based handshake pairing connection; or the portable medical device wirelessly uploads test data through other wireless receiving devices, and the backend server software associates the data with the bound patient.

[0013] Preferably, the preset ready state includes: The terminal device's screen is locked, or the terminal device displays a preset standby interface.

[0014] The low-power preview mode includes: Set the camera module's capture frame rate to 5-30fps and / or set the capture resolution to a level lower than VGA.

[0015] Preferably, the scanning intent conditions include: The QR code remains in the preset central area of ​​the corresponding screen in the video stream for a period of time exceeding a preset duration threshold.

[0016] and / or The QR code moves at a speed lower than a preset threshold in the image, and its trajectory conforms to a preset alignment mode.

[0017] Preferably, feedback information is displayed through a feedback module; After the smart terminal device establishes a wireless connection with the portable device, or after the portable device establishes a wireless connection with other smart terminal devices or network devices, feedback prompts are provided through the speaker and / or display screen of the smart terminal device.

[0018] Preferably, when the smart terminal device detects a QR code, if the overlap rate of the outer rectangle is greater than a preset overlap threshold within a preset time window, then multiple QR code detection results are identified as continuous tracking of the same QR code target.

[0019] According to the present invention, an automatic QR code recognition system based on intent determination is applied to a terminal device, comprising: The status monitoring module determines whether the smart terminal device is in a preset ready state; The camera driver management module controls the camera module of the terminal device to collect video streams in the background when the status monitoring module determines that the smart terminal device is in a preset ready state. The local detection module processes the video stream to detect the presence of QR codes. The intent determination module determines whether the preset scanning intent conditions are met when the local detection module detects a QR code, based on the spatiotemporal stability of the QR code in the video stream. The automatic connection module automatically decodes the QR code to obtain the device identifier when the intent judgment module determines that the scanning intent conditions are met, and establishes a binding relationship between the portable device and the measured patient ID based on the device identifier.

[0020] Preferably, when the status monitoring module detects that the screen of the smart terminal device is locked or the smart terminal device displays a preset standby interface, it determines that the smart terminal device is in a preset ready state.

[0021] The low-power preview mode includes: Set the camera module's capture frame rate to 5-30fps and / or set the capture resolution to a level lower than VGA.

[0022] Preferably, the intent determination module identifies that the QR code remains in the preset central area of ​​the corresponding frame in the video stream for a period of time exceeding a preset duration threshold. and / or The intent determination module recognizes that the QR code's movement speed in the image is lower than a preset threshold, and the movement trajectory conforms to a preset alignment mode; Then, it is determined that the conditions for scanning the code are met.

[0023] Preferably, it also includes a feedback module; After the terminal device establishes a wireless connection with the target device, or after the portable device establishes a wireless connection with other smart terminal devices or network devices, it sends a feedback prompt on the connection result through the feedback module.

[0024] Preferably, when the intent determination module detects a QR code, if the overlap rate of the outer rectangle is greater than a preset overlap threshold within a preset time window, then multiple QR code detection results are identified as continuous tracking of the same QR code target.

[0025] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention simplifies the traditional process that requires multiple manual steps into a zero-interaction automated experience of simply aligning and connecting, greatly shortening the device binding time and significantly improving operational efficiency.

[0026] 2. This invention fully reuses the existing camera module and processing capabilities of the terminal device, without the need to add any dedicated scanning hardware, effectively reducing hardware costs and thus effectively reducing the complexity of hardware design.

[0027] 3. In this invention, the acquisition, detection, recognition, and decoding of all video streams are completed locally on the terminal device in a closed loop. The original image data does not leave the device or upload to the cloud, which fundamentally eliminates the privacy leakage and data security risks that may be caused by data transmission, and ensures privacy and data security.

[0028] 4. This invention, through an intent judgment mechanism based on spatiotemporal stability, can accurately determine the user's valid scanning intent, effectively avoiding false triggers and repeated scanning caused by the QR code accidentally entering the frame or moving rapidly, reducing unnecessary system resource consumption, and improving recognition accuracy and system stability. Attached Figure Description

[0029] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the QR code automatic recognition method based on intent judgment; Figure 2 This is a schematic diagram of the terminal device structure in an embodiment of the present invention; Figure 3 This is a schematic diagram of an application scenario in an embodiment of the present invention. Detailed Implementation

[0030] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the present invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0031] This invention provides an automatic QR code recognition method based on intent determination, applied to a terminal device, to... Figure 2 For example, the terminal device is a medical bedside screen device, which aims to enable medical staff to automatically complete the wireless connection between devices without any manual interaction when they point a medical device with a QR code at the bedside screen, thereby greatly improving work efficiency and ensuring data security.

[0032] by Figure 2 For example, bedside screen devices are typically installed at the head of a hospital bed. Their hardware configuration includes, but is not limited to, a display screen for information display and interaction, and a built-in camera module, eliminating the need for additional dedicated scanning hardware. The camera module, acting as an image acquisition unit, is usually located on the front of the device to capture images in front of it. In addition, the device may also include a function button area, a speaker, a microphone, and a wireless communication module (such as a Bluetooth module, a wireless network module, etc.).

[0033] by Figure 2 For example, in this scenario, a healthcare worker holds a medical device to be connected, such as an electronic thermometer. This medical device has a QR code label that encodes the device's unique identification information, such as a Bluetooth media access control address.

[0034] When medical staff point the medical device at the bedside screen device, allowing the QR code label to enter the camera module's field of view, the camera module automatically activates to detect and recognize the QR code. After successfully determining the user's intent and completing the decoding, a binding relationship is established between the portable medical device and the patient in that bed. Simultaneously, the bedside screen device (smart terminal) automatically establishes a wireless connection with the medical device. However, the portable medical device can also transmit data back through other smart devices or network devices, allowing the application backend to determine which bed's patient's data it represents.

[0035] To achieve the above-mentioned automated process, this invention provides an automatic QR code recognition system based on intent judgment, which is divided into multiple collaborative modules, specifically including: a status monitoring module, a camera driver management module, a local detection module, an intent judgment module, and an automatic connection module.

[0036] These modules all run as software programs on the terminal device, preferably on the processor of the bedside screen device.

[0037] Understandably, all image data processing, including acquisition, detection, recognition, and decoding, is completed locally on the terminal device, without relying on cloud servers, thus ensuring data and privacy security.

[0038] The specific process of the QR code automatic recognition method based on intent determination provided by the present invention is as follows: Figure 1 For example, including: Step S101: Monitor equipment status.

[0039] After the system starts, the status monitoring module runs continuously as a background service to monitor the operating status of the bedside screen device in real time.

[0040] This running status includes information from multiple dimensions, such as whether the screen is locked, whether the currently displayed screen is the system's main desktop (i.e., the standby screen), or the information of the applications currently in the foreground.

[0041] Step S102: Determine if the device is idle.

[0042] The status monitoring module determines whether the bedside screen device is in a preset ready state based on the monitored operating status. The preset ready state is defined as one of the following two situations: the display screen of the bedside screen device is locked; or the bedside screen device displays a preset standby interface, such as the system main desktop.

[0043] When healthcare workers or patients are not interacting with the device, it is in one of these two states. If it is determined that the device is not in a ready state (for example, the user is watching a video or using a specific application), the process returns to step S101, where the status monitoring module continues monitoring. No further image acquisition is performed at this time to avoid interfering with normal user operation and to conserve system resources.

[0044] Step S103: Start low-power acquisition.

[0045] When the status monitoring module determines that the bedside screen device has entered the ready state, it sends an activation command to the camera driver management module. Upon receiving this command, the camera driver management module controls and configures the camera module to start capturing video streams in background low-power preview mode.

[0046] During background data collection, the viewfinder image is not displayed on the screen, and the entire process is invisible, thus achieving silent standby.

[0047] To achieve low power consumption, the camera driver management module employs a specific configuration. Specifically, it sets the camera module's acquisition frame rate to a low level, such as 15 frames per second, which is sufficient for dynamic target detection while significantly reducing the power consumption of the processor and image sensor compared to the conventional 30 or 60 frames per second.

[0048] Accordingly, the acquisition resolution is set at a relatively low level, such as QVGA (i.e., 320×240 pixels). Although this resolution is far lower than the current mainstream VGA (640×480 to 1920×1080 pixels, depending on the VGA image acquisition card used) or higher resolution, it is sufficient for detecting and recognizing standard-sized QR codes within a reasonable distance, and can significantly reduce the amount of data in each frame of the image, thereby reducing the computational load and memory usage of subsequent processing.

[0049] The camera driver management module transmits the acquired video frame data to the local detection module for processing in real time through efficient methods such as memory sharing.

[0050] Step S104: Detect the QR code.

[0051] After receiving the low-power video stream from the camera driver management module, the local detection module processes each frame of the image on the local processor of the bedside screen device to detect the presence of a QR code. This module embeds a lightweight QR code detection algorithm, such as a deep learning-based object detection model or a traditional image processing algorithm, which can quickly locate the possible area of ​​a QR code in a low-resolution image and output its position coordinates and bounding box within the image.

[0052] The entire detection process is performed locally on the device, ensuring that the original video data does not leave the device. If no QR code is detected in the current frame, the process returns to step S103 to continue processing the next frame of video.

[0053] In more preferred examples, a three-stage operating mode of "inspection-confirmation-trigger" is adopted to minimize standby power consumption. Ultra-low power inspection steps: The camera runs at extremely low parameters (e.g., 5fps, lowest resolution), while the local detection module runs only a very lightweight "QR code-like mode" detector to detect image features that resemble QR codes.

[0054] Performance enhancement and confirmation steps: If a suspected target is found during the inspection phase, dynamically increase the camera acquisition parameters (e.g., 24fps, QVGA) and switch to the full high-precision QR code detection algorithm for confirmation.

[0055] Intent Judgment and Triggering Steps: In high-performance mode, step S105 is executed to determine the spatiotemporal stability intent. If the intent is confirmed, a connection is triggered; if no confirmation is made within a preset time or the target disappears, the system automatically reverts to the ultra-low power inspection mode of Phase 1.

[0056] Step S105: Determine the spatiotemporal stability.

[0057] When the local detection module detects a QR code in a frame or several consecutive frames, the system does not immediately trigger decoding. Instead, it transmits information such as the QR code's position to the intent judgment module, which then determines the user's true intent, thereby distinguishing between the user's conscious aiming behavior and unconscious skipping behavior.

[0058] In more preferred examples, the basis for determining whether the preset scanning intent conditions are met is the spatiotemporal stability of the QR code in the video stream, which is measured by two dimensions: the stability of spatial location and the stability of temporal continuity.

[0059] Specifically, the intent determination module executes the following determination logic: The system determines whether the center point of the detected QR code is located within a preset central area of ​​the image. This central area is preferably a central rectangle occupying approximately 60% x 60% of the image, thus conforming to the user's subconscious habit of aligning the QR code with the center of the screen when scanning. If the QR code is located within this central area, a timer is started to calculate its duration. In subsequent consecutive video frames, if the QR code remains stably within the central area, the timer increments the duration.

[0060] When the cumulative dwell time exceeds a preset threshold (e.g., 500 milliseconds), the user's scanning intent is considered valid, satisfying the preset scanning intent conditions. If the QR code moves out of the center area or disappears from the screen before the dwell time reaches the threshold, the timer is reset to zero, and the system waits for the next stable QR code to appear.

[0061] By combining the judgment mechanism of the central area and continuous stay, it can effectively filter out situations where the QR code accidentally and quickly flashes in the camera's field of view due to device movement or people walking, thereby avoiding false triggering.

[0062] In more preferred embodiments, when the local detection module detects QR codes in consecutive video frames, these detection results are compared.

[0063] For example, within a preset time window (e.g., 100 milliseconds), if the overlap rate (e.g., crossover ratio) between the outer rectangle of the QR code detected in the next frame and the previous frame is greater than a preset overlap threshold (e.g., 0.7), these consecutive detection results are identified as continuous tracking of the same QR code target.

[0064] The intent determination module calculates dwell time based on continuously tracked targets, rather than treating each frame's detection as an independent event, which further enhances the stability and accuracy of the determination and effectively filters out jumps in the detection box position caused by slight jitter.

[0065] In many preferred embodiments, the sensitivity of the intent determination module is not static, but adaptively adjusted according to the different contexts of the bedside screen device, thereby achieving a more intelligent and optimized user experience in different scenarios. The intent determination module not only receives QR code information from the local detection module, but also obtains richer contextual information from the status monitoring module, and dynamically adjusts its judgment parameters based on this information.

[0066] Specifically, in addition to monitoring screen lock and standby states, the state monitoring module also monitors applications currently running in the foreground and transmits this contextual information to the intent determination module. The intent determination module has multiple preset judgment strategies and selects the appropriate strategy to execute based on the received context information, including: High-priority connection scenarios. When the status monitoring module detects that the foreground application of the current bedside screen device is a specific vital sign collection application, it infers that the current medical staff are very likely to need to connect to external medical devices to input data, and judges it as a high-intent context.

[0067] At this point, the intent judgment module will relax the judgment criteria for spatiotemporal stability: expand the preset central area from 60%×60% to 80%×80%, and at the same time reduce the preset duration threshold from 500 milliseconds to 300 milliseconds.

[0068] In normal standby scenarios, when the status monitoring module detects that the bedside screen device is on the lock screen or the general system home screen, the user's intent is unclear. At this time, the intent judgment module adopts a standard judgment strategy, namely, a preset central area of ​​60%×60% and a preset duration threshold of 500 milliseconds, to ensure high anti-accidental touch capability and avoid unnecessary recognition and connection attempts caused by QR codes that appear accidentally in the environment (for example, a QR code on the packaging of an item is randomly placed in front of the camera).

[0069] Long-duration static filtering scenarios. To further optimize system resources and avoid ineffective processing of static environments, when the intent judgment module detects that a QR code remains in any position in the camera image (not limited to the central area) for too long (e.g., more than 5 seconds), it is judged as a static object without interactive intent, rather than an attempt to scan the code.

[0070] At this point, the features or location information of the QR code are added to a temporary ignore list. During the next preset time period (e.g., 1 minute), even if the QR code is detected again by the local detection module, the intent determination module will temporarily ignore it and not perform intent determination, effectively avoiding repeated analysis of unchanging QR codes in the environment, thus further saving computing resources.

[0071] The dynamic intent judgment strategy described above can exhibit different sensitivity and response characteristics according to different application scenarios, which significantly improves the level of intelligence and overall user experience compared to solutions with fixed parameters.

[0072] Step S106: Trigger decoding and connection.

[0073] Once the intent determination module determines that the scanning intent conditions are met, it immediately sends a trigger decoding signal to the automatic connection module and transmits the current video frame image containing the clear QR code.

[0074] Upon receiving the signal, the automatic connection module immediately performs high-precision decoding on the QR code area located by the local detection module in the image frame and extracts the device identification information contained therein. Preferably, this device identification is the Bluetooth Media Access Control address of the medical device.

[0075] The automatic connection module automatically calls the system Bluetooth service of the bedside screen device, initiates a Bluetooth pairing request to the target medical device based on the obtained address, and completes the connection. The whole process is completed automatically without any clicking or confirmation operation.

[0076] In more preferred embodiments, the automatic connection module serves as a universal connection controller, supporting various wireless connection technologies, including: Wi-Fi network connection: Decode the QR code containing Wi-Fi credentials (such as SSID and password) and automatically call the Wi-Fi management interface to complete the network connection.

[0077] Near Field Communication (NFC) assisted secure connection: After decoding the QR code containing the device identifier, the system identifies the device type that requires NFC pairing, and securely exchanges keys or credentials through the NFC channel to complete the final wireless connection.

[0078] NearLink short-range wireless connection: After decoding the QR code containing the NearLink device identifier, service type, pairing parameters and / or connection credentials, the target device is identified as a device type that supports NearLink communication. The NearLink communication interface or NearLink protocol stack in the terminal device is called to search for the target device based on the NearLink device identifier to establish a NearLink wireless connection, or a data transmission link is established through the NearLink channel to achieve low latency and low power consumption short-range device connection.

[0079] Step S107: Provide feedback.

[0080] After successfully establishing a wireless connection with the target medical device, the system provides clear feedback to ensure that the operator is aware that the connection has been successful. The automatic connection module calls the system's audio and interface services.

[0081] Specifically, the automatic connection module controls the feedback module (such as a speaker) of the bedside screen device to emit a prompt tone, while simultaneously displaying a prompt message on the screen, such as "Thermometer connected" or "Bind established, measurement can be performed." This visual prompt message disappears automatically after a fixed duration to avoid obscuring the screen content for extended periods.

[0082] After the connection is established, the camera capture task will be automatically suspended, or the system will continue to maintain a low-power monitoring state to wait for the next connection task.

[0083] Those skilled in the art will understand that, besides implementing the system and its various devices, modules, and units provided by this invention in the form of purely computer-readable program code, the same functions can be achieved entirely through logical programming of the method steps, making the system and its various devices, modules, and units of this invention function as logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers. Therefore, the system and its various devices, modules, and units provided by this invention can be considered as a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; alternatively, the devices, modules, and units for implementing various functions can be considered as both software modules implementing the method and structures within the hardware component.

[0084] Specific embodiments of the present invention have been described above. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art can make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. Unless otherwise specified, the embodiments and features described in this application can be arbitrarily combined with each other.

Claims

1. A method for automatic QR code recognition based on intent judgment, applied to bedside or bedside smart terminal devices, characterized in that, include: When the terminal device is in a preset ready state, the camera module of the smart terminal device collects video streams in the background; Smart terminal devices process video streams and detect the presence of QR codes. When a QR code is detected, the system determines whether the preset scanning intent conditions are met based on the spatiotemporal stability of the QR code in the video stream. When the conditions for scanning are met, the QR code is automatically decoded to obtain the ID of the portable device, and a binding relationship is established between the portable device and the patient being measured based on the device ID. The processes of processing the video stream, detecting the QR code, and decoding are all performed locally on the smart terminal device, and the video stream is not uploaded to the cloud server.

2. The QR code automatic recognition method based on intent judgment according to claim 1, characterized in that, The preset ready states include: The screen of the smart terminal device is locked, or the smart terminal device displays a preset standby interface; The low-power preview mode includes: Set the camera module's capture frame rate to 5-30fps and / or set the capture resolution to a level lower than VGA.

3. The QR code automatic recognition method based on intent judgment according to claim 1, characterized in that, The scanning intent conditions include: The QR code remains in the preset central area of ​​the corresponding frame in the video stream for a period of time exceeding a preset duration threshold. and / or The QR code moves at a speed lower than a preset threshold in the image, and its trajectory conforms to a preset alignment mode.

4. The QR code automatic recognition method based on intent judgment according to claim 1, characterized in that, Feedback information is displayed through the feedback module; After the smart terminal device establishes a wireless connection with the portable device, or after the portable device establishes a wireless connection with other smart terminal devices or network devices, feedback prompts are provided through the speaker and / or display screen of the smart terminal device.

5. The QR code automatic recognition method based on intent judgment according to claim 1, characterized in that, When the smart terminal device detects a QR code, if the overlap rate of the outer rectangle is greater than a preset overlap threshold within a preset time window, then multiple QR code detection results are identified as continuous tracking of the same QR code target.

6. An intention-based automatic QR code recognition system, applied to smart terminal devices, characterized in that, include: The status monitoring module determines whether the smart terminal device is in a preset ready state; The camera driver management module controls the camera module of the smart terminal device to collect video streams in the background when the status monitoring module determines that the smart terminal device is in a preset ready state. The local detection module processes the video stream to detect the presence of QR codes. The intent determination module determines whether the preset scanning intent conditions are met when the local detection module detects a QR code, based on the spatiotemporal stability of the QR code in the video stream. The automatic connection module automatically decodes the QR code to obtain the device identifier when the intent judgment module determines that the scanning intent conditions are met, and establishes a binding relationship between the portable device and the measured patient ID based on the device identifier.

7. The QR code automatic recognition system based on intent determination according to claim 6, characterized in that, When the status monitoring module detects that the screen of the smart terminal device is locked or the smart terminal device displays a preset standby interface, it determines that the terminal device is in a preset ready state. The low-power preview mode includes: Set the camera module's capture frame rate to 5-30fps and / or set the capture resolution to a level lower than VGA.

8. The QR code automatic recognition system based on intent determination according to claim 6, characterized in that, The intent determination module identifies that the QR code remains in a preset central area of ​​the corresponding frame in the video stream for a duration exceeding a preset time threshold. and / or The intent determination module recognizes that the QR code's movement speed in the image is lower than a preset threshold, and the movement trajectory conforms to a preset alignment mode; Then it is determined that the scanning intent condition is met.

9. The QR code automatic recognition system based on intent determination according to claim 6, characterized in that, It also includes a feedback module; After the terminal device establishes a wireless connection with the target device, or after the portable device establishes a wireless connection with other smart terminal devices or network devices, it sends a feedback prompt on the connection result through the feedback module.

10. The QR code automatic recognition system based on intent determination according to claim 6, characterized in that, When the intent determination module detects a QR code, if the overlap rate of the outer rectangle is greater than a preset overlap threshold within a preset time window, then multiple QR code detection results are identified as continuous tracking of the same QR code target.

Images