Hospital orthopedic consumable inventory management system and method based on behavior recognition

Abstract

The invention relates to the technical field of inventory management, in particular to a hospital orthopaedic consumable inventory management system and method based on behavior recognition, and the method achieves the real-time monitoring of the taking and supplement of consumables through the behavior recognition technology: when a medical worker enters a consumable warehouse, the behavior of the medical worker is automatically captured; and analyzing actions in real time through a built-in behavior identification model, identifying the operation type, determining the type and the number of specifically taken consumables through association with RFID tags on the consumables, then generating a consumable operation information group, generating an operation identifier and a second identifier auxiliary generation factor, and calculating an identifier auditing factor by the system, and the operation behavior of the medical personnel is audited through the relationship between the second identification auxiliary generation factor and the auditing factor, and the inventory information is automatically updated. According to the invention, real-time and automatic inventory updating is realized, manual intervention is not needed, operation errors are greatly reduced, and the efficiency and accuracy of hospital orthopaedic consumable management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of inventory management, and in particular to a hospital orthopedic consumables inventory management system and method based on behavior recognition. Background Art

[0002] With the continuous advancement of modern medical technology, hospital consumables management has become a critical part of ensuring the quality of medical services. This is especially true in orthopedic surgery, where various high-precision, high-cost consumables (such as bone screws, steel plates, artificial joints, etc.) are frequently used and come in a wide variety. The accuracy of inventory management directly affects the smooth progress of surgery and the hospital's operating cost control. However, traditional consumables management methods have many problems, including reliance on manual records, opaque consumable usage, and delayed inventory updates. These problems result in inefficient use of consumables and may even lead to shortages, waste, or improper use.

[0003] A Chinese invention patent with publication number CN111145885A discloses a method for managing orthopedic medical consumables. The method includes obtaining surgical site information and an electronic human model, obtaining relevant consumables requirements from the electronic human model based on the surgical site information to form a surgical plan package, generating a configuration requirement table based on the surgical plan package, generating an order set based on the configuration requirement table, screening out orders whose inventory meets the requirements based on the order set to obtain shippable orders, generating a shipping notice based on the shippable orders to enable dealers to ship the goods; generating relevant traceable information corresponding to the consumables, and having the hospital conduct acceptance inspection. The present invention realizes automated warehousing management, reduces consumables configuration costs, improves the accuracy of orthopedic consumables procurement, and improves procurement efficiency.

[0004] However, actual inventory updates often lag behind actual operations, making real-time monitoring impossible. This can easily lead to untimely inventory information. When dealing with complex scenarios, such as multiple people taking or returning consumables at the same time, it is difficult to effectively distinguish and track each operation, resulting in unclear operation records, which in turn affects the overall efficiency and safety of hospital consumables management. Summary of the Invention

[0005] The purpose of the present invention is to address the problems existing in the background technology and propose a hospital orthopedic consumables inventory management system and method based on behavior recognition.

[0006] The technical solution of the present invention is a method for managing hospital orthopedic consumables inventory based on behavior recognition, which includes the following specific implementation steps: S1. During the system initialization phase, the inventory management module generates inventory list audit information, constructs an inventory management audit information group, and counts the hospital's orthopedic consumables inventory, enters information on various consumables used in the hospital's orthopedic department, equips consumables with exclusive RFID tags, and sets minimum thresholds for various types of consumables; S2. Collect video data of actual operations of orthopedic surgeons, nurses, and other medical staff when taking and replenishing consumables, and carefully annotate these videos to construct a dataset. Then, build an action recognition model based on the YOLOv5n network, C3Ghost network, and SE attention mechanism. S3. During the inventory management phase, when any medical staff member registers their identity at the entrance to the consumables inventory area and enters the consumables inventory area, the behavior data collection module begins to capture their behavior through the camera installed in the consumables inventory area and transmits the captured video data in real time to the behavior recognition module and the inventory management log library; S4. The behavior recognition module analyzes the body movements of the characters in the video using a pre-trained behavior recognition model, determines the type of behavior data of the medical staff, and triggers the RFID scanner in the behavior data collection module to read the label information of the consumables in the hands of the medical staff. It also generates an operation identifier for the inventory list review information, constructs an operation information group, and then transmits the constructed operation information group to the inventory management module; S5. The inventory management module reviews the operation information group, determines the operator's operation type, confirms the quantity of consumables taken or replenished, automatically updates the consumables inventory, and records the confirmation information group {consumable name, replenishment quantity or withdrawal quantity, operator identification, operation time} in the inventory management log library; S6. The inventory management module monitors the inventory data of consumables in real time. If the inventory of a certain type of consumables approaches the set minimum threshold, the inventory management module automatically reminds the management personnel and generates replenishment suggestions, indicating that replenishment is needed.

[0007] Preferably, the specific implementation steps of the inventory management module to construct the inventory management audit information group are as follows: S2-1. The inventory management module selects a prime number p=521, which makes n=2 p -1 is a Mersenne prime number, and the inventory management module then performs the following operations: S2-2. Calculate the p-th order irreducible primitive polynomial q=x 521 +x 32 +1; Among them, x is the indeterminate variable of the polynomial; S2-3, randomly select an element a∈ , satisfying a n mod q=1; in, is a finite field The multiplicative group of S2-4. Select a hash function H(); S2-5. Define the operation type type, the access operation is defined as 0x00, and the supplement operation is defined as 0x01; S2-6. Generate inventory list audit information m={0, 1} * , and disclose the inventory management audit information group {p, q, H, a, m, type}.

[0008] Preferably, the operation information group is divided into a consumables use information group and a consumables replenishment information group.

[0009] Preferably, the construction process of the operation information group is as follows: S4-1. The behavior recognition module randomly selects a number k i ∈Z n * ={1, 2, ..., n-1}, calculate the first identification auxiliary generation factor AcⅠfactor i , calculated as follows: ; S4-2. Calculation of the second marker auxiliary generation factor AcⅡfactor i =H(AcⅠfactor i ||m); Among them, || represents string concatenation; S4-3. Select a random number x i ∈Z n * , calculate the identification factor y i : ; S4-4. Calculation operation identifier AcID i =(k i +Aufactor i ×x i ) mod n; S4-5, generate operation information group {operation type type i , operation identifier AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, quantity to be taken or replenished num, operator identification ID i , operation time T i}.

[0010] Preferably, the implementation process of the inventory management module reviewing the operation information group is as follows: S5-1, from the received operation information group {operation type type i , operation identifier AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor yi , consumables name, quantity to be taken or replenished num, operator identification ID i , operation time T i} to extract the parameters: Operation type i , Operation ID AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, quantity to be taken or replenished, operator identification ID i , Operation time T i ; S5-2. Calculate the auxiliary audit factor AcAfactor i : ; S5-3. Calculate the Aufactor i =H(AcAfactor i ||m); S5-4, if the equation Aufactor i =AcⅡfactor i If established, the inventory management module confirms the medical staff person i operating behavior.

[0011] Preferably, the behavior detection model replaces the C3 module in the YOLOv5n backbone network with the C3Ghost module, and adds the SE attention module before the first C3 module in the feature fusion network part.

[0012] Preferably, the early warning and automatic replenishment process for orthopedic high-frequency consumables is as follows: S7-1. Build a behavior-driven consumables consumption prediction model. By performing time series statistics on medical staff's use behavior, we can build a consumables usage time series, which is recorded as: ; Among them, U t represents the predicted value of consumable usage at time t; B t Indicates the flow of behavioral events; H t Indicates the actual consumption data of consumables in adjacent historical time periods; P t represents the intensity of the surgical plan; f() represents the weighted prediction function, which is the LSTM model; S7-2, automatic calculation of dynamic safety stock S s : ; Among them, S s represents the lower limit of safety stock; Z represents the set service level factor; Indicates the standard deviation of consumables demand, that is, U t The variance estimate of the series; L represents the replenishment lead time; S7-3, after each consumable is used, update the real-time inventory I t , and compare it with the dynamic threshold S s :If the real-time inventory quantity I t ≤ dynamic threshold S s , it triggers the consumables warning; S7-4. When the warning is triggered, the recommended replenishment quantity Q is automatically calculated: ; in, Indicates the average usage in the past N cycles; represents the regulating factor; Indicates the standard deviation of the demand per unit time in the consumables consumption forecast model.

[0013] The technical solution of the present invention is a hospital orthopedic consumables inventory management system based on behavior recognition, which is used to implement the above-mentioned hospital orthopedic consumables inventory management method based on behavior recognition, including: Behavior data collection module, equipped with a high-definition camera and RFID scanner, is used to collect personnel operation data; Behavior recognition module, which uses computer vision algorithms to identify people's operating behaviors; Inventory management module, used to monitor and update inventory information of consumables in real time; Inventory management log library, used to store data generated during the management of orthopedic consumables in the hospital; The visualization platform is used to display the status of the hospital's orthopedic consumables inventory area in real time, graphically display the current inventory change trend, and display key inventory warning information.

[0014] Preferably, the inventory management module is linked to the electronic health record system and the supply chain management system, thereby completing the matching of surgical scheduling with consumables demand, dynamically adjusting inventory strategies, associating consumables usage records with patient files, and intelligent procurement and automatic replenishment.

[0015] Compared with the prior art, the above technical solution of the present invention has the following beneficial technical effects: The present invention designs a hospital orthopedic consumables inventory management system and method based on behavior recognition. The method realizes real-time monitoring of consumables acquisition and replenishment through behavior recognition technology: when medical staff enter the consumables warehouse to operate, the camera will automatically capture their behavior, and the system analyzes the action in real time through the built-in behavior recognition model, and identifies the operation type based on the YOLOv5n network, C3Ghost network and SE attention mechanism, and determines the specific type and quantity of consumables taken by associating with the RFID tag on the consumables. Then, a consumables operation information group is generated, and an operation identifier and a second identifier auxiliary generation factor are generated. The system calculates the identifier audit factor through the operation identifier, and audits the medical staff's operation behavior through the relationship between the second identifier auxiliary generation factor and the audit factor, and integrates the behavior recognition data flow with the multi-dimensional inventory dynamic modeling, introduces the behavior flow Bt as the direct driving factor, and the parameters are predicted by the behavior recognition feedback drive, and are dynamically updated. , significantly improving the "sensitivity and adaptability" of safety stock and introducing volatility adjustment items , taking into account the excess protection mechanism when supply is unstable, the replenishment algorithm has "scenario adaptability", realizing real-time and automatic inventory updates without human intervention, greatly reducing operational errors and improving the efficiency and accuracy of the hospital's orthopedic consumables management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is an architectural diagram of a hospital orthopedic consumables inventory management system based on behavior recognition proposed by the present invention; Figure 2 This is a network structure diagram of the behavior recognition model proposed in the present invention; Figure 3 This is the network structure diagram of the SE module; Figure 4 Flowchart of compression and excitation operations in the SE module. DETAILED DESCRIPTION

[0017] Example 1, as Figure 1 As shown, the present invention proposes a hospital orthopedic consumables inventory management system based on behavior recognition, which includes: a behavior data acquisition module, a behavior recognition module, an inventory management module, an inventory management log library and a visualization platform.

[0018] The behavior data collection module is equipped with a high-definition camera and an RFID scanner to collect personnel operation data; High-definition cameras are used to capture people’s actions of storing and retrieving goods; RFID scanner is used to scan consumables information; The behavior recognition module uses computer vision algorithms to identify personnel's operating behaviors, including but not limited to: taking consumables and registering them in the warehouse; The inventory management module updates the inventory information of consumables in real time, and automatically updates the inventory quantity whenever it identifies medical staff taking or replenishing supplies; The inventory management log library is used to store data generated during the management of orthopedic consumables in the hospital; The visualization platform is used to display the status of the hospital's orthopedic consumables inventory area in real time, and graphically display the current inventory change trend and key inventory warning information.

[0019] In the second embodiment, a method for managing hospital orthopedic consumables inventory based on behavior recognition is proposed in the present invention. The method is applicable to the hospital orthopedic consumables inventory management system based on behavior recognition proposed in the first embodiment, and specifically includes the following implementation steps: System initialization phase: S1. Conduct environmental surveys of key areas in the consumables inventory area to determine the installation locations of cameras and RFID scanners to ensure the accuracy of behavior recognition. S2. Install the camera in a place that can fully cover the consumables inventory area, such as directly above the consumables storage rack. The RFID scanner can be installed near the consumables storage area. When wiring, ensure that the power and data cables are stably connected to the system host.

[0020] S3. Connect hardware devices such as cameras and RFID scanners to the hospital's internal network to ensure that the devices can transmit data to the behavior recognition module in real time. Perform preliminary equipment debugging to ensure that the clarity of the video stream and the sensitivity of the RFID scanner meet the requirements.

[0021] S4. The inventory management module selects a prime number p=521, which makes n=2 p -1 is a Mersenne prime number, and the inventory management module then performs the following operations: (1) Calculate the p-th order irreducible primitive polynomial q = x 521 +x 32 +1; Among them, x is the indeterminate variable of the polynomial; (2) Randomly select an element a∈ , satisfying a n mod q=1; in, is a finite field The multiplicative group of (3) Select the hash function H(); (4) Define the operation type type, the access operation is defined as 0x00, and the supplement operation is defined as 0x01; (5) Generate inventory list audit information m={0, 1} * , and disclose the inventory management audit information group {p, q, H, a, m, type}.

[0022] S5. The inventory management module counts the hospital's orthopedic consumables inventory and performs the following operations: (1) Enter the information of various consumables used by the hospital's orthopedics department, including but not limited to the category, specifications, inventory, production batch and expiration date of the consumables; (2) Equip consumables with exclusive RFID tags. The tags must contain the unique identification information of the consumables to ensure that the system can identify the consumables through the identification tags every time they are taken or replenished; (3) Verify that the RFID scanner can accurately read the unique RFID tag of the consumables and match it with the consumables information in the system to ensure that the consumables tag is consistent with the system record; (4) Set the minimum threshold for each type of consumables.

[0023] Behavior recognition model training and deployment phase: S1. Behavioral data collection and annotation: Collect actual operation video data of orthopedic surgeons, nurses and other medical staff when taking and replenishing consumables, and carefully annotate these videos. The annotated content includes the specific type of operation, including but not limited to "taking consumables", "replenishing consumables", and "moving and replenishing goods".

[0024] S2. Training the behavior recognition model: Based on the labeled dataset, use a deep learning algorithm to train the behavior recognition model. The model must be able to accurately identify actions in different scenarios and be able to adapt to different operating styles.

[0025] S3. Model testing and optimization: Test the trained behavior detection model in real-world scenarios to identify actions such as retrieval and replenishment. If the model's recognition accuracy is low, optimize it by adding training data or adjusting model parameters. It should be noted that if Figure 2 As shown in the figure, the behavior detection model introduces the SE (Squeeze-and-Excitation) module before the first C3 module in the feature fusion network based on the YOLOv5n model, and replaces the C3 module in the YOLOv5n backbone network with the C3Ghost module; In the figure, Conv represents the convolution operation. C3Ghost is a lightweight convolutional neural network structure consisting of the C3 structure and the GhostConv module. C3 convolution is a convolution module that combines depthwise separable convolution and dilated convolution. Concat represents the splicing operation, Upsample represents the upsampling operation, and SE represents SE attention. The Detect module completes the classification and detection of human behavior in operation video data through multi-scale target detection, anchor box and prediction box generation, category prediction and confidence evaluation. It should be noted that if Figure 3 As shown in , the SE module consists of two main parts: Squeeze and Excitation. The first step is the compression operation. The compression operation process is to input a W×H×C feature map, where W is the width of the feature map, H is the height of the feature map, and C is the number of channels. After an average pooling operation, the feature map is compressed into a 1×1×C vector. The second step is the activation operation. The activation operation consists of two fully connected layers and two activation functions. The first fully connected layer has C×SERatio neurons. After the input 1×1×C passes through the first fully connected layer, the output becomes 1×1×C×SERatio. SERatio is the scaling parameter. After this operation, the number of channels is reduced, thereby reducing the amount of calculation. The second fully connected layer parameter is 1×1×C, which converts the input into 1×1×C again. The last step is the scale operation. The scale operation is to multiply the weights. The weight parameters calculated by the SE module are multiplied by the channels corresponding to the original feature map to obtain the final output result. The compression and excitation operations are as follows Figure 4 shown.

[0026] Inventory management stage: S1. When any medical staff i Register your ID at the entrance to the consumables inventory area i When the vehicle enters the consumables inventory area, the behavior data collection module starts capturing its behavior through the camera installed in the consumables inventory area, and transmits the captured video data to the behavior recognition module and inventory management log library in real time.

[0027] S2. The behavior recognition module uses a pre-trained behavior recognition model to analyze the body movements of people in the video and determine whether medical staff are performing "taking consumables" or "replenishing consumables". The specific detection process is as follows: S2-1. When a medical staff member reaches out to a consumables rack and picks up a certain type of consumable, the behavior recognition model identifies the person's posture, tracks their movement, and identifies the "taking" behavior based on their arm extension and grasping movements. For example, if a medical staff member takes a box from a supplies rack, the system can track its entire retrieval process to ensure that all details are recorded; S2-2. When the behavior recognition model identifies the "take" action, the behavior recognition module triggers the RFID scanner in the behavior data collection module to read the label information of the consumables in the medical staff's hand, including but not limited to the name and quantity of the consumables; S2-3. The behavior recognition module generates an operation identifier AcID for the inventory list audit information m. i , generating a consumables access information group; The implementation process of the above-mentioned behavior recognition module generating the consumables use information group is as follows: (1) Randomly select a number k i ∈Z n * ={1, 2, ..., n-1}, calculate the first identification auxiliary generation factor AcⅠfactor i , calculated as follows: ; (2) Calculate the second marker auxiliary generation factor AcⅡfactor i =H(AcⅠfactor i ||m); Among them, || represents string concatenation; (3) Select a random number x i ∈Z n * , calculate the identification factor y i : ; (4) Calculation operation identifier AcID i =(k i +Aufactor i ×x i ) mod n; (5) Generate consumables access information group {operation type type i , operation identifier AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, quantity to be taken (-num), operator identification ID i , operation time T i}; S2-4, when the behavior recognition module recognizes the medical staff's use behavior and confirms the specific consumables information, the behavior recognition module sets the consumables use information group {operation identifier AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, quantity to be taken (-num), operator identification ID i , operation time T i}Transfer to inventory management module; It should be noted that the replenishment action recognition is similar to the retrieval action. When medical staff replenish consumables to the warehouse or storage area, the behavior recognition model automatically recognizes the "replenishment" action characteristics through the personnel behavior action data captured by the camera. After recognizing the "replenishment" action, the behavior recognition module reads the replenished consumables label through the RFID scanner, confirms the name and quantity of the replenished consumables, generates a consumables replenishment information group, and transmits the consumables replenishment information group to the inventory management module. The generation method of the above consumables replenishment information group is similar to the generation method of the consumables withdrawal information group. The specific implementation process is as follows: (1) Randomly select a number k i ∈Z n * ={1, 2, ..., n-1}, calculate the first identification auxiliary generation factor AcⅠfactor i , calculated as follows: ; (2) Calculate the second marker auxiliary generation factor AcⅡfactor i =H(AcⅠfactor i ||m); (3) Select a random number x i ∈Z n * , calculate the identification factor y i : ; (4) Calculation operation identifier AcID i =(k i +Aufactor i ×x i ) mod n; (5) Generate consumables supplement information group {operation type type i , operation identifier AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, replenishment quantity (+num), operator identification ID i , operation time T i}; It should be noted that in some complex scenarios, multiple medical staff may enter the consumables warehouse at the same time and take different consumables. The behavior recognition module uses multi-target tracking technology to simultaneously identify multiple operators and create independent records for each person's behavior. The videos captured by the camera from different angles will be merged into the behavior recognition model to accurately distinguish the actions of different people.

[0028] S3. The inventory management module performs the following operations upon receiving the consumables use information group and the consumables replenishment information group: S3-1, from the received consumables use information group {operation type type i , operation identifier AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, quantity to be taken (-num), operator identification ID i , operation time T i} or consumables replenishment information group {operation type type i , operation identifier AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, replenishment quantity (+num), operator identification ID i , operation time T i} to extract the parameters: Operation ID AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, take quantity (-num) or replenish quantity (+num), operator identification ID i , Operation time T i ; S3-2. Calculate the auxiliary audit factor AcAfactor i : ; S3-3. Calculate the Aufactor i =H(AcAfactor i ||m); S3-4, if the equation Aufactor i =AcⅡfactor i If established, the inventory management module confirms the medical staff person i Take or replenish consumables and identify the type of operation: (1) If the operation type is type i = 0x00, the operation type is to take and the quantity to be taken is num, the inventory management module automatically deducts the corresponding num number of consumables according to the consumable name and the quantity to be taken, updates the inventory data in real time, and sets the consumables taking confirmation information group {operation type type i, consumables name, quantity to be taken (-num), operator identification ID i , operation time T i}Record in the inventory management log library; (2) If the operation type is type i =0x01, the operation type is replenishment and the replenishment quantity is num. The inventory management module updates the inventory record according to the type and quantity of the replenished consumables, adds the quantity of the consumables in the inventory to num, and sets the consumable replenishment confirmation information group {operation type type i , consumables name, replenishment quantity (+num), operator identification ID i , operation time T i}Record in the inventory management log library.

[0029] S4. The inventory management module is based on an intelligent early warning and automatic replenishment mechanism, integrating behavior recognition data streams with multi-dimensional inventory dynamic modeling. Through a time series prediction model driven by consumables usage behavior, combined with a multi-factor weighted safety stock early warning algorithm, it achieves accurate early warning and automated replenishment control for high-frequency orthopedic consumables. Specifically: S4-1. Build a behavior-driven consumables consumption prediction model. By performing time series statistics on medical staff's access behaviors ("access behaviors" identified by the behavior recognition module), we can build a time series of consumables usage, which is recorded as: ; Among them, U t represents the predicted value of consumable usage at time t; B t represents the flow of behavioral events (the number of consumables-taking behaviors per unit time); H t Represents the actual consumption data of consumables in adjacent historical time periods (smoothed statistics within the time window); P t represents the surgical plan intensity; f() represents the weighted prediction function, which is an LSTM model in this embodiment; S4-2. Automatic calculation of dynamic safety stock S s : ; Among them, S s represents the lower limit of safety stock; Z represents the service level factor (selected according to the set out-of-stock risk tolerance, such as Z=1.65 corresponds to 95% service level); Indicates the standard deviation of consumables demand (derived from U t Variance estimation of the series); L represents the replenishment lead time (determined by the average response time of the consumables supplier); S4-3, after each consumable is used, update the real-time inventory I t , and compare it with the dynamic threshold S s :If the real-time inventory quantity I t≤ dynamic threshold S s , it triggers the consumables warning; S4-4. When the warning is triggered, the recommended replenishment quantity Q is automatically calculated: ; in, Indicates the average usage in the past N cycles; Represents the adjustment factor (dynamically adjusted according to the historical out-of-stock rate, initially set to 1); Indicates the standard deviation of the demand per unit time in the consumables consumption forecast model.

[0030] S5, the visualization platform calls the consumables use confirmation information group or consumables replenishment confirmation information group in the inventory management log library, and displays the medical staff person i This operation data can also display personnel behavior data.

[0031] Example 3 is a hospital orthopedic consumables inventory management system based on behavior recognition. Unlike Example 2, the inventory management module is linked to the electronic health record system (EHR) and supply chain management system. The functions of the integrated system after linking are as follows: (1) Matching surgical schedules with consumables requirements: The EHR system records the schedule of each surgery and the specific patient's condition. The inventory management module automatically generates a list of consumables required for the surgery based on this data. If the consumables actually used during the surgery do not match the list, the hospital's orthopedic consumables inventory management system, based on behavior recognition, will automatically adjust inventory consumption and update the forecasting model. For example, a patient is about to undergo fracture repair surgery. The hospital's orthopedic consumables inventory management system, based on behavioral recognition, automatically matches the required orthopedic consumables (including but not limited to plates, screws, and surgical blades) based on the surgical plan and standard operating procedures recorded in the EHR, and locks in inventory in advance. (2) Dynamically adjust inventory strategies: By obtaining real-time surgical schedules from the EHR system, the inventory management module dynamically adjusts the inventory strategy for consumables based on the surgical schedules for the next few days. For some emergency surgeries, the inventory management module can promptly adjust the priority order of consumables to ensure that the consumables needed for emergency surgeries are not exhausted. For example, the inventory management module determines that a large number of orthopedic screws or surgical instruments will be needed in the next week based on the schedule. It will prioritize ensuring sufficient inventory of these consumables to reduce the risk of consumable shortages. (3) Consumables usage records are linked to patient health records: The inventory management module automatically links the consumables usage of each operation with the patient's health record; For example, the specific types of steel plates and screws used during surgery can be automatically recorded in the patient's health record for future follow-up. If the patient requires subsequent surgery or rehabilitation examinations, the doctor can quickly understand the consumables used through the EHR system, ensuring the continuity of the medical process. (4) Intelligent procurement and automatic replenishment: The supply chain management system is responsible for the hospital's procurement, supplier management, order processing, and other aspects. It integrates the inventory management module with the supply chain system to automate the entire process of consumables, from demand forecasting to procurement and warehousing, improving efficiency and reducing errors caused by manual operations. When the inventory management module detects that a certain type of consumables is about to run out, the inventory management module can automatically generate a replenishment plan and send a purchase order to the supplier through the supply chain management system.

[0032] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited thereto. Various changes can be made within the scope of knowledge possessed by those skilled in the art without departing from the spirit of the present invention.

Claims

1. A hospital orthopedic consumables inventory management method based on behavior recognition, characterized in that: The specific implementation steps include the following: S1. During the system initialization phase, the inventory management module generates inventory list audit information, constructs an inventory management audit information group, and counts the hospital's orthopedic consumables inventory, enters information on various consumables used in the hospital's orthopedic department, equips consumables with exclusive RFID tags, and sets minimum thresholds for various types of consumables; S2. Collect video data of actual operations of orthopedic surgeons, nurses, and other medical staff when taking and replenishing consumables, and carefully annotate these videos to construct a dataset. Then, build an action recognition model based on the YOLOv5n network, C3Ghost network, and SE attention mechanism. S3. During the inventory management phase, when any medical staff member registers their identity at the entrance to the consumables inventory area and enters the consumables inventory area, the behavior data collection module begins to capture their behavior through the camera installed in the consumables inventory area and transmits the captured video data in real time to the behavior recognition module and the inventory management log library; S4. The behavior recognition module analyzes the body movements of the characters in the video using a pre-trained behavior recognition model, determines the type of behavior data of the medical staff, triggers the RFID scanner, reads the label information of the consumables in the hands of the medical staff, generates an operation identifier for the inventory list review information, constructs an operation information group, and then transmits the constructed operation information group to the inventory management module; S5. The inventory management module reviews the operation information group, determines the operator's operation type, confirms the quantity of consumables taken or replenished, automatically updates the consumables inventory, and records the confirmation information group {consumable name, replenishment quantity or withdrawal quantity, operator identification, operation time} in the inventory management log library; S6. The inventory management module integrates behavior recognition data streams with multi-dimensional inventory dynamic modeling. Through a time series prediction model driven by consumables usage behavior and a multi-factor weighted safety stock warning algorithm, it provides early warning and automatic replenishment of high-frequency orthopedic consumables.

2. The method for managing hospital orthopedic consumables inventory based on behavior recognition according to claim 1, characterized in that: The specific implementation steps for the inventory management module to construct the inventory management review information group are as follows: S2-1. The inventory management module selects a prime number p=521, which makes n=2 p -1 is a Mersenne prime number, and the inventory management module then performs the following operations: S2-2. Calculate the p-th order irreducible primitive polynomial q=x 521 +x 32 +1; Among them, x is the indeterminate variable of the polynomial; S2-3, randomly select an element a∈ , satisfying a n mod q=1; in, is a finite field The multiplicative group of S2-4. Select a hash function H(); S2-5. Define the operation type type, the access operation is defined as 0x00, and the supplement operation is defined as 0x01; S2-6. Generate inventory list audit information m={0, 1} * , and disclose the inventory management audit information group {p, q, H, a, m, type}.

3. The method for managing hospital orthopedic consumables inventory based on behavior recognition according to claim 2, characterized in that: The operation information group is divided into a consumables taking information group and a consumables replenishing information group.

4. The method for managing hospital orthopedic consumables inventory based on behavior recognition according to claim 3, characterized in that: The construction process of the operation information group is as follows: S4-1. The behavior recognition module randomly selects a number k i ∈Z n * ={1, 2, ..., n-1}, calculate the first identification auxiliary generation factor AcⅠfactor i , calculated as follows: ； S4-2. Calculation of the second marker auxiliary generation factor AcⅡfactor i =H(AcⅠfactor i ||m); Among them, || represents string concatenation; S4-3. Select a random number x i ∈Z n * , calculate the identification factor y i : ； S4-4. Calculation operation identifier AcID i =(k i +Aufactor i ×x i ) mod n; S4-5, generate operation information group {operation type type i , operation identifier AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, quantity to be taken or replenished num, operator identification ID i , operation time T i }.

5. The method for managing hospital orthopedic consumables inventory based on behavior recognition according to claim 4, characterized in that: The implementation process of the inventory management module audit operation information group is as follows: S5-1, from the received operation information group {operation type type i , operation identifier AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, quantity to be taken or replenished num, operator identification ID i , operation time T i } to extract the parameters: Operation type i , Operation ID AcID i , the second marker auxiliary generation factor AcⅡfactor i , identification factor y i , consumables name, quantity to be taken or replenished, operator identification ID i , Operation time T i ; S5-2. Calculate the auxiliary audit factor AcAfactor i : ； S5-3. Calculate the Aufactor i =H(AcAfactor i ||m); S5-4, if the equation Aufactor i =AcⅡfactor i If established, the inventory management module confirms the medical staff person i operating behavior.

6. The method for managing hospital orthopedic consumables inventory based on behavior recognition according to claim 1, characterized in that: The behavior detection model replaces the C3 module in the YOLOv5n backbone network with the C3Ghost module, and adds the SE attention module before the first C3 module in the feature fusion network part.

7. The method for managing hospital orthopedic consumables inventory based on behavior recognition according to claim 1, characterized in that: The early warning and automatic replenishment process for orthopedic high-frequency consumables is as follows: S7-1. Build a behavior-driven consumables consumption prediction model. By performing time series statistics on medical staff's use behavior, we can build a consumables usage time series, which is recorded as: ; Among them, U t represents the predicted value of consumable usage at time t; B t Indicates the flow of behavioral events; H t Indicates the actual consumption data of consumables in adjacent historical time periods; P t represents the intensity of the surgical plan; f() represents the weighted prediction function, which is the LSTM model; S7-2, automatic calculation of dynamic safety stock S s : ; Among them, S s represents the lower limit of safety stock; Z represents the set service level factor; Indicates the standard deviation of consumables demand, that is, U t The variance estimate of the series; L represents the replenishment lead time; S7-3, after each consumable is used, update the real-time inventory I t , and compare it with the dynamic threshold S s :If the real-time inventory quantity I t ≤ dynamic threshold S s , it triggers the consumables warning; S7-4. When the warning is triggered, the recommended replenishment quantity Q is automatically calculated: ; in, Indicates the average usage in the past N cycles; represents the regulating factor; Indicates the standard deviation of the demand per unit time in the consumables consumption forecast model.

8. A hospital orthopedic consumables inventory management system based on behavior recognition, which is used to implement the hospital orthopedic consumables inventory management method based on behavior recognition according to any one of claims 1 to 7, characterized in that: include: Behavior data collection module, equipped with a high-definition camera and RFID scanner, is used to collect personnel operation data; Behavior recognition module, which uses computer vision algorithms to identify people's operating behaviors; Inventory management module, used to monitor and update inventory information of consumables in real time; Inventory management log library, used to store data generated during the management of orthopedic consumables in the hospital; The visualization platform is used to display the inventory status of the hospital's orthopedic consumables in real time, graphically display the current inventory change trend, and display key inventory warning information.

9. The hospital orthopedic consumables inventory management system based on behavior recognition according to claim 8, characterized in that: The inventory management module is linked to the electronic health record system and supply chain management system to match surgical schedules with consumables demand, dynamically adjust inventory strategies, link consumables usage records with patient files, and implement intelligent procurement and automatic replenishment.

Images