Methods, systems, and media for biological resource identification based on Internet of Things (IoT) technology

Abstract

This invention relates to the field of biological resource identification technology, specifically to a method, system, and medium for biological resource identification based on Internet of Things (IoT) technology. It includes the following steps: S1, collecting online biological resources from a biological resource bank, obtaining online resource information, and simultaneously extracting historical usage records of historical biological resources; S2, collecting patient information from within the hospital, and performing predictive analysis of biological resource usage based on the patient information; by prioritizing allocation based on expiration dates and accurately predicting replenishment, waste caused by expired or improperly matched biological resources is reduced, aligning with the goal of economical management of medical resources. Based on accurate matching of blood type and quality grade and real-time status monitoring, the risk of transfusion errors is reduced, ensuring patient treatment safety. Simultaneously, by predicting in advance, delays in blood use during surgery or emergency scenarios are reduced, improving medical efficiency and reducing the current biological resource expiration rate from 5%-8% under traditional management to below 1%.

Description

Technical Field

[0001] This invention relates to the field of biological resource identification technology, and more specifically, to biological resource identification methods, systems, and media based on Internet of Things (IoT) technology. Background Technology

[0002] In the medical field, the safe management and efficient utilization of biological resources are key to ensuring the effectiveness of clinical treatment and the rational allocation of medical resources. Current technologies mainly manage biological resources through manual registration, periodic inventory, and experience-based demand prediction.

[0003] However, manual classification and matching can easily lead to two situations: one is the reverse consumption of "near-expiration blood stockpiling and long-expiration blood priority use," and the other is "near-expiration blood priority use and long-expiration blood stockpiling." The quality of blood products is related to storage time; the shorter the storage time of blood products, the higher the quality. If only long-expiration blood is used first, the quality of blood products used by patients cannot reach the optimal level. Conversely, if near-expiration blood is used first, it will lead to a large-scale expiration of blood. According to statistics, the expiration rate of biological resources in traditional management is as high as 5%-8%. In view of this, the present invention provides a biological resource identification method, system, and medium based on Internet of Things technology. Summary of the Invention

[0004] The purpose of this invention is to provide a method, system, and medium for identifying biological resources based on Internet of Things (IoT) technology, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention aims to provide a method for identifying biological resources based on Internet of Things (IoT) technology, comprising the following steps:

[0006] S1. Collect online biological resources from the biological resource bank, obtain online resource information of online biological resources, and extract historical usage records of historical biological resources;

[0007] S2. Collect patient information of inpatients in the hospital, conduct predictive analysis of biological resource usage based on patient information, and combine the patient information of predicted users with historical usage records and online resource information to conduct demand matching analysis.

[0008] S3. Obtain real-time usage requirements and match them with online biological resources to obtain online biological resources that meet the real-time usage requirements.

[0009] S4. Compare the online biological resources corresponding to the predicted users and the online biological resources corresponding to the real-time usage needs with the biological resource bank. When the comparison results show that the predicted usage biological resources combined with the real-time usage biological resources are greater than the amount in the biological resource bank, identify and plan for the real-time usage needs combined with the predicted users. S5.

[0010] S5. Predict the replenishment trend of biological resources for this category by combining online resource information and historical usage records. At the same time, extract the prediction data of each predicted user. Combine the predicted replenishment trend with the prediction data, real-time usage needs, and online resource information to identify the best use of biological resources. Match biological resources to real-time usage needs based on the identification results.

[0011] As a further improvement to this technical solution, step S1 is as follows:

[0012] S1.1 Establish an information sharing module in the biological resource bank, obtain relevant data from the biological resource bank through the information sharing module, and then divide the biological resources of the biological resource bank into online biological resources and historical biological resources based on the relevant data of the biological resource bank;

[0013] S1.2 Obtain online resource information of online biological resources, and extract historical usage records of historical biological resources.

[0014] As a further improvement to this technical solution, the online biological resources in S1 are the biological resources currently stored in the biological resource bank, and the historical biological resources are the biological resources that have already been used.

[0015] Online resource information includes images received, receipt date, expiration date, and product category data;

[0016] Historical usage records include patient information and historical resource information.

[0017] As a further improvement to this technical solution, step S2 is as follows:

[0018] S2.1 Utilize IoT technology to connect the information sharing module with the hospital's data center, obtain all patient information through the data center, perform predictive analysis of biological resource usage based on the patient information, and obtain the usage prediction rate for each patient;

[0019] S2.2 Set a usage prediction threshold, compare the usage prediction rate of each patient with the usage prediction threshold, and select patients whose usage prediction rate is greater than the usage prediction threshold as predicted users, and vice versa. When the patient information is updated, the comparison is performed again.

[0020] S2.3. Combine the patient information of the predicted users with historical usage records to conduct usage demand analysis, obtain the predicted users' usage demand for biological resources, and then combine the usage demand with online resource information to match online biological resources to obtain online biological resources that match the predicted users.

[0021] As a further improvement to this technical solution, step S3 is as follows:

[0022] S3.1 Obtain real-time usage requirements and extract the patient information corresponding to those requirements;

[0023] S3.2. Match the patient information corresponding to the real-time usage needs with online biological resources to obtain online biological resources that meet the real-time usage needs.

[0024] As a further improvement to this technical solution, step S4 is as follows:

[0025] S4.1 Extract the categories of online biological resources corresponding to real-time usage needs, then extract the predicted users of the same category, and then compare the number of online biological resources corresponding to the predicted users with the number of online biological resources corresponding to real-time usage needs and the biological resource database.

[0026] S4.2 When the predicted number of online biological resources corresponding to the patient and the number of online biological resources corresponding to the real-time usage demand are greater than the number of online biological resources in the biological resource bank, then identification and planning S5 shall be performed.

[0027] S4.3 If the number of online biological resources corresponding to the predicted user patient and the number of online biological resources corresponding to the real-time usage demand are less than the number of online biological resources in the biological resource library, then after excluding the online biological resources corresponding to the predicted user patient from the online biological resources in the biological resource library, the online biological resource with the shortest storage time is selected for matching for the real-time demand.

[0028] As a further improvement to this technical solution, step S5 is as follows:

[0029] S5.1, Receive the signal from S4.2;

[0030] S5.2 Combine online resource information in the biological resource bank with historical usage records to predict the replenishment trend of each type of biological resource, obtain the predicted replenishment trend of each type of biological resource, and then extract the predicted replenishment trend of the same type of biological resource with real-time usage demand.

[0031] S5.3 Extract the predicted data for each patient, combine the extracted predicted supply trend with the predicted data, real-time demand, and online resource information to identify the best use of biological resources, and match biological resources to the real-time use demand based on the identification results.

[0032] The second objective of this invention is to provide a biological resource identification system based on Internet of Things (IoT) technology, including any one of the above-mentioned biological resource identification methods based on IoT technology, comprising a matching analysis module, a demand analysis module, and an optimal identification module;

[0033] The matching analysis module is used to collect online biological resources from the biological resource bank, obtain online resource information of online biological resources, extract historical usage records of historical biological resources, perform predictive analysis of biological resource usage based on patient information, and combine the patient information of the predicted users with historical usage records and online resource information to perform usage demand matching analysis.

[0034] The demand analysis module is used to obtain real-time usage demand, and to match the real-time usage demand with online biological resources to obtain online biological resources that meet the real-time usage demand. The module also performs a quantity comparison analysis between the online biological resources corresponding to the predicted user and the online biological resources corresponding to the real-time usage demand and the biological resource library.

[0035] The optimal identification module is used to predict the replenishment trend of biological resources of this category by combining online resource information and historical usage records. At the same time, it extracts the prediction data of each predicted user, combines the predicted replenishment trend with the prediction data, real-time usage needs, and online resource information to identify the optimal use of biological resources, and matches biological resources to real-time usage needs based on the identification results.

[0036] A third objective of this invention is that it discloses a readable storage medium, including a memory storing execution instructions, wherein when a processor executes the execution instructions stored in the memory, the processor hardware executes the biological resource identification method based on Internet of Things technology as described in the first aspect.

[0037] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0038] The biological resource identification method, system, and medium based on Internet of Things (IoT) technology can reduce waste caused by expired or improperly matched biological resources through priority allocation based on expiration date and accurate replenishment prediction. This aligns with the goal of saving medical resources. Based on accurate matching of blood type and quality grade and real-time status monitoring, it can reduce the risk of transfusion errors and ensure patient treatment safety. At the same time, it can reduce blood use delays in surgical or emergency scenarios by predicting in advance, thereby improving medical efficiency and reducing the current biological resource expiration rate from 5%-8% under traditional management to below 1%. Attached Figure Description

[0039] Figure 1 This is an overall flowchart of the present invention;

[0040] Figure 2This is a flowchart illustrating the process of extracting historical usage records of biological resources according to the present invention.

[0041] Figure 3 The flowchart for obtaining the usage prediction rate for each patient in this invention;

[0042] Figure 4 This is a flowchart illustrating the process of extracting and acquiring patient information corresponding to real-time usage needs in this invention.

[0043] Figure 5 This is a flowchart illustrating the process of matching online biological resources with the shortest storage time to meet real-time needs according to the present invention.

[0044] Figure 6 This is a flowchart illustrating the process of matching biological resources to real-time usage needs based on the identification results according to the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] Please see Figure 1 - Figure 6 As shown, one of the objectives of this invention is to provide a method for identifying biological resources based on Internet of Things (IoT) technology, comprising the following steps:

[0047] S1. Collect online biological resources from the biological resource bank, obtain online resource information of online biological resources, and extract historical usage records of historical biological resources;

[0048] Biological resources can be represented by blood products;

[0049] The steps for S1 are as follows:

[0050] S1.1 Establish an information sharing module in the biological resource bank, obtain relevant data from the biological resource bank through the information sharing module, and then divide the biological resources of the biological resource bank into online biological resources and historical biological resources based on the relevant data of the biological resource bank;

[0051] S1.2 Obtain online resource information of online biological resources, and extract historical usage records of historical biological resources. The specific steps are as follows:

[0052] Establish an information sharing module: The information sharing module connects with the biobank to obtain relevant data from the biobank. This data includes detailed information on all biological resources, such as resource categories, status, and historical records. The information sharing module acts as an intermediary, connecting the biobank with other systems (such as hospitals, analysis systems, etc.) and extracting relevant data from the biobank through APIs, database queries, or other data communication protocols.

[0053] Based on the data in the resource database, biological resources are classified according to their current status and usage. Online biological resources are those currently stored in the database and available for use, and their status is "online," meaning they have not been consumed. Historical biological resources are those that have been used or expired, meaning that these resources have been allocated to patients and consumed, or have expired and can no longer be used for new patients.

[0054] Extracting online resource information: Extracting relevant information from online biological resources, including image data or description information of the resource, the date the resource entered the biological resource bank, the validity period or expiration date of the resource, and the type of resource (such as mainly including red blood cell suspension, platelet suspension, fresh frozen plasma and plasma products, etc.).

[0055] Extract historical usage records: Extract relevant historical records from used biological resources, including, for example, patient ID, usage time, treatment type, ID of each historical resource, entry date, usage status, and expiration date.

[0056] In S1, online biological resources are the biological resources currently preserved in the biological resource bank, while historical biological resources are biological resources that have already been used.

[0057] Online resource information includes images received, receipt date, expiration date, and product category data;

[0058] Historical usage records include patient information and historical resource information.

[0059] S2. Collect patient information of inpatients in the hospital, conduct predictive analysis of biological resource usage based on patient information, and combine the patient information of predicted users with historical usage records and online resource information to conduct demand matching analysis.

[0060] The steps for S2 are as follows:

[0061] S2.1. Utilize IoT technology to establish a connection between the information sharing module and the hospital's data center. Obtain all patient information through the hospital's data center, perform predictive analysis of biological resource usage based on the patient information, and obtain the predicted usage rate for each patient. The specific steps are as follows:

[0062] Various IoT devices are deployed in hospitals, including patient monitors, health monitoring devices, and mobile medical terminals, to collect patients' physiological data in real time (such as body temperature, blood pressure, heart rate, and blood oxygen concentration). The IoT devices upload the patients' real-time data to the hospital's data center via wireless network, including monitors in wards, laboratory data, imaging examination results, and medical records.

[0063] By integrating real-time patient data with historical health records through the interface between the hospital data center and the IoT platform, the data center can provide a unified interface to achieve the integration and synchronization of different data sources, ensuring that all patient information can be updated synchronously at different points in time, so as to carry out real-time prediction and analysis.

[0064] 52, 59, and 62: Biological resource usage prediction analysis is performed based on patient information (including historical and real-time data) to obtain the biological resource usage prediction rate for each patient, using the following formula:

[0065] ;

[0066] Among them, P i (t+1) represents the predicted utilization rate of biological resources by patient i at a future time point, where t is the time point, and X1, X2, ..., X... n For patient characteristic variables (such as age, sex, weight, etc.), Z1, Z2, ..., Z M For real-time health data (such as hemoglobin concentration, type of surgery, blood pressure, etc.), f is a machine learning algorithm. By learning from a large amount of historical data, the machine learning algorithm can adaptively find the complex relationships between various factors affecting the demand for blood products. In practical applications, the machine learning model needs to be trained with a large amount of historical data, including the patient's historical demand, feature variables, and health data. By learning the relationships between these data, the model can obtain the relationship between each input variable (such as age, gender, blood pressure, etc.) and the demand for blood products. When the model has completed training, it can use real-time data (i.e., the patient's current health data and feature variables) to make predictions. For example, when a patient's hemoglobin concentration decreases and blood pressure fluctuates in real time after surgery, the model can predict future blood product demand based on these input features.

[0067] S2.2 Set a usage prediction threshold. Compare the usage prediction rate of each patient with the usage prediction threshold. Patients with a usage prediction rate greater than the usage prediction threshold are predicted to use the service; conversely, patients with a usage prediction rate less than the usage prediction threshold are not. When patient information is updated, the comparison is performed again. The specific steps are as follows:

[0068] Threshold setting: Set a prediction threshold T for biological resource use, for example, it can be set to 0.7;

[0069] If a patient’s predictive use rate is <0.7, then the patient is not considered to need biological resources.

[0070] A patient is considered to require biological resources when the predictive use rate is ≥0.7.

[0071] Thresholds are dynamically adjusted based on historical data usage to adapt to the needs of different time periods or different patient groups.

[0072] An automated system is set up to automatically recalculate the patient's prediction rate and perform threshold comparisons when patient information or condition changes. If the patient's resource needs change, the prediction status is updated in a timely manner to ensure dynamic adjustment of resource allocation.

[0073] S2.3. Combine the patient information of the predicted users with historical usage records to conduct a usage demand analysis, obtain the predicted users' usage demand for biological resources, and then combine the usage demand with online resource information to match online biological resources to obtain online biological resources that match the predicted users. The specific steps are as follows:

[0074] Demand analysis is conducted by combining historical usage records: Detailed records of previous blood transfusions are obtained, including transfusion volume, type, time, and frequency. Historical demand is analyzed based on the patient's treatment plan (e.g., surgery, chemotherapy) and disease type (e.g., anemia, surgery). A demand forecasting model is established by statistically analyzing past transfusion needs, using the following formula:

[0075] ;

[0076] Among them, D i (t+1) represents the biological resource demand of patient i at a future time point, where X1, X2, ..., X... n For the patient's characteristics and history (such as past transfusion volume, disease type, etc.), α1, α2, ..., α n Here, ε represents the regression coefficients, and ε represents the error term.

[0077] Matching biological resources with online resource information: Based on the patient's needs analysis results (such as required quantity, type, etc.), select biological resources from the inventory that meet the patient's needs. The matching rules include type, required quantity, and expiration date, as shown in the following formula:

[0078] ;

[0079] Among them, M i，j K represents the degree of matching between patient i and biological resource j. jLet Q be the inventory of biological resource j. i The demand of patient i for biological resources j.

[0080] S3. Obtain real-time usage requirements and match them with online biological resources to obtain online biological resources that meet the real-time usage requirements.

[0081] The steps for S3 are as follows:

[0082] S3.1 Obtain real-time usage requirements and extract the patient information corresponding to those requirements;

[0083] S3.2. Match the patient information corresponding to the real-time usage needs with online biometric resources to obtain online biometric resources that meet the real-time usage needs. The specific steps are as follows:

[0084] Real-time usage needs: Real-time acquisition of patients' physiological data and health status through IoT devices, patient monitoring systems, laboratory equipment, etc. Based on the patients' real-time data and condition assessment, certain conditions (such as bleeding exceeding a certain threshold, hemoglobin below a certain level, etc.) are set to determine whether there is a need for biological resources;

[0085] Demand matching is achieved by combining online biological resources: By querying the hospital's biological resource bank in real time, the inventory information of biological resources can be obtained, including the type of biological resource (such as red blood cells, plasma, platelets, etc.), inventory quantity, expiration date, etc., and the quality grade of each biological resource (such as whether it is type A blood, whether it is rare blood, etc.) and whether it meets the patient's blood type, required quantity, etc.

[0086] Based on the patient's blood type and required amount (such as the amount required for each transfusion), rules for matching biological resources are set. Then, based on the patient's biological resource requirements (such as required amount and blood type) and the matching degree with the inventory, the matching degree of each biological resource is calculated. The higher the matching degree, the more suitable the biological resource is for the patient. Biological resources with higher matching degrees are selected based on the calculated matching degree. If there are multiple biological resources that meet the conditions, they are sorted according to the priority of inventory or required amount.

[0087] S4. Compare the online biological resources corresponding to the predicted users and the online biological resources corresponding to the real-time usage needs with the biological resource bank. When the comparison results show that the predicted usage biological resources combined with the real-time usage biological resources are greater than the amount in the biological resource bank, identify and plan for the real-time usage needs combined with the predicted users. S5.

[0088] The steps for S4 are as follows:

[0089] S4.1 Extract the categories of online biological resources corresponding to real-time usage demand, then extract the predicted users of the same category, and then compare the number of online biological resources corresponding to the predicted users with the number of online biological resources corresponding to real-time usage demand in the biological resource database, using the following formula:

[0090] ;

[0091] Among them, T j Let D be the total demand for biological resource category j, n be the number of patients, and D be the total demand for biological resource category j. i To predict the amount of biological resources required by patient i, R j The quantity of biological resources required for real-time use;

[0092] When T j >The quantity of biological resources possessed will trigger S5 planning;

[0093] When T j If the biological resource bank has sufficient reserves, then proceed to the next step of optimizing and matching biological resources.

[0094] S4.2 When the predicted number of online biological resources corresponding to the patient and the number of online biological resources corresponding to the real-time usage demand are greater than the number of online biological resources in the biological resource bank, then identification and planning S5 shall be performed.

[0095] S4.3 If the number of online biological resources corresponding to the predicted user patient and the number of online biological resources corresponding to the real-time usage demand are less than the number of online biological resources in the biological resource library, then after excluding the online biological resources corresponding to the predicted user patient from the online biological resources in the biological resource library, the online biological resource with the shortest storage time is selected for matching for the real-time demand.

[0096] Based on the expiration date of each biological resource in the inventory, the biological resource with the shortest storage time is selected for allocation, and priority is given to allocating the biological resource with the shortest storage time to patients in need. Finally, based on the inventory and demand, a biological resource allocation plan for each patient is determined and allocated in real time.

[0097] S5. Predict the replenishment trend of biological resources for this category by combining online resource information and historical usage records. At the same time, extract the prediction data of each predicted user. Combine the predicted replenishment trend with the prediction data, real-time usage needs, and online resource information to identify the best use of biological resources. Match biological resources to real-time usage needs based on the identification results.

[0098] The steps for S5 are as follows:

[0099] S5.1, Receive the signal from S4.2;

[0100] S5.2 Combine online resource information in the biological resource bank with historical usage records to predict the replenishment trend of each type of biological resource, obtain the predicted replenishment trend of each type of biological resource, and then extract the predicted replenishment trend of the same type of biological resource with real-time usage demand.

[0101] S5.3 Extract the predicted data for each patient, combine the extracted predicted supply trends with the predicted data, real-time demand, and online resource information to identify the optimal use of biological resources, and match biological resources to the real-time demand based on the identification results. The specific steps are as follows:

[0102] Predictive use of patient data extraction: Machine learning models are used to predict each patient's demand for biological resources in the future. The biological resource demands of each patient are aggregated to obtain the total future demand for each type of biological resource. By analyzing historical data and trends, the demand and replenishment of each biological resource in the future are predicted.

[0103] ;

[0104] in, Let C be the predicted inventory of biological resource j over the next k days. j Y(t) represents the inventory of biological resource j at the current time t, and YS(t+k) represents the projected production of biological resource j in the next k days. Let the demand forecast for biological resource j be the amount to be generated in the next k days.

[0105] By calculating the remaining useful life of each biological resource, we assess whether it can meet future demand. If the remaining useful life of biological resource j is greater than the predicted demand for biological resource j in the next k days, it is determined that it can meet the demand.

[0106] Optimal biological resource utilization identification: Query biological resource inventory. To avoid selecting biological resources nearing expiration, prioritize those with longer remaining validity periods to ensure demand is met and waste is avoided. Obtain the online resource quantity for each biological resource category. Combine real-time demand, predicted replenishment trends, predicted patient demand, and current inventory, and determine the optimal allocation scheme using an optimization algorithm. The formula is as follows:

[0107] ;

[0108] Among them, A j (t) represents the amount of biological resource j allocated to the real-time demand, C j (t) represents the current inventory level of product category j, and D j (t) represents the real-time demand of biological resource j at the current time t, and min is a function. min is used to ensure that the constraints of actual available resources are followed during the allocation of biological resources.

[0109] The second objective of this invention is to provide a biological resource identification system based on Internet of Things (IoT) technology, including any of the above-mentioned biological resource identification methods based on IoT technology, comprising a matching analysis module, a demand analysis module, and an optimal identification module;

[0110] The matching analysis module is used to collect online biological resources from the bioresource bank, obtain online resource information of online biological resources, extract historical usage records of historical biological resources, perform predictive analysis of biological resource usage based on patient information, and combine the patient information of predicted users with historical usage records and online resource information to perform usage demand matching analysis.

[0111] The demand analysis module is used to obtain real-time usage demand and match it with online biological resources to obtain online biological resources that meet the real-time usage demand. The module also performs a quantity comparison analysis between the online biological resources corresponding to the predicted users and the online biological resources corresponding to the real-time usage demand and the biological resource library.

[0112] The optimal identification module is used to predict the replenishment trend of biological resources for this category by combining online resource information and historical usage records. At the same time, it extracts the prediction data of each predicted user, combines the predicted replenishment trend with the prediction data, real-time usage needs, and online resource information to identify the optimal use of biological resources, and matches biological resources to real-time usage needs based on the identification results.

[0113] To this end, embodiments of this application also provide a readable storage medium storing a plurality of instructions that can be loaded by a processor to execute the steps in the low-power control method provided in embodiments of this application.

[0114] Optionally, the readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static access-at-any-time memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0115] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely preferred examples and are not intended to limit the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A biological resource identification method based on Internet of Things (IoT) technology, characterized in that: Includes the following steps: S1. Collect online biological resources from the biological resource bank, obtain online resource information of online biological resources, and extract historical usage records of historical biological resources; S2. Collect patient information of inpatients in the hospital, conduct predictive analysis of biological resource usage based on patient information, and combine the patient information of predicted users with historical usage records and online resource information to conduct demand matching analysis. S2.

1. Utilize Internet of Things (IoT) technology to establish a connection between the information sharing module and the hospital's data center. Obtain all patients' historical health records and real-time physiological data through the hospital's data center. Integrate the historical health records and real-time physiological data to conduct predictive analysis of biological resource usage and obtain the usage prediction rate for each patient. Historical health records include past blood transfusion history and disease type, while real-time physiological data includes hemoglobin concentration, blood pressure, blood oxygen concentration, and type of surgery. ； Among them, P i (t+1) represents the predicted utilization rate of biological resources by patient i at a future time point, where t is the time point, and X1, X2, ..., X... n For the patient's characteristic variables, Z1, Z2, ..., Z M For real-time health data, f represents the machine learning algorithm; S2.2 Set a usage prediction threshold. Compare the usage prediction rate of each patient with the usage prediction threshold. Patients with a usage prediction rate greater than the usage prediction threshold are predicted to use the service; conversely, patients with a usage prediction rate less than the usage prediction threshold are not. When patient information is updated, the comparison is performed again. The specific steps are as follows: Threshold setting: Set a prediction threshold T for biological resource use, which is set to 0.7; If a patient’s predictive use rate is <0.7, then the patient is not considered to need biological resources. A patient is considered to require biological resources when the predictive use rate is ≥0.

7. Thresholds are dynamically adjusted based on historical data usage to adapt to the needs of different time periods or different patient groups. An automated system is set up to automatically recalculate the patient's prediction rate and perform threshold comparisons when patient information or condition changes. If the patient's resource needs change, the prediction status is updated in a timely manner to ensure dynamic adjustment of resource allocation. S2.

3. Combine the patient information of the predicted user with the previous blood transfusion volume, blood transfusion type and blood transfusion frequency in the historical usage records to analyze the usage needs of the predicted user for biological resources. Then, combine the usage needs with online resource information to match online biological resources to obtain online biological resources that meet the predicted user's needs. ； Among them, D i (t+1) represents the biological resource demand of patient i at a future time point, where X1, X2, ..., X... n For the patient's characteristics and history, α1, α2, ..., α n Here, ε represents the regression coefficients, and ε represents the error term. ； Among them, M i，j K represents the degree of matching between patient i and biological resource j. j Let Q be the inventory of biological resource j. i The demand of patient i for biological resources j; S3. Obtain real-time usage requirements and match them with online biological resources to obtain online biological resources that meet the real-time usage requirements. S4. Compare the online biological resources corresponding to the predicted users and the online biological resources corresponding to the real-time usage needs with the biological resource bank. When the comparison results show that the predicted usage biological resources combined with the real-time usage biological resources are greater than the amount in the biological resource bank, identify and plan for the real-time usage needs combined with the predicted users. S5. S5. Based on online resource information and historical usage records, predict the replenishment trend of biological resources for each category. At the same time, extract the prediction data of each predicted user. Combine the predicted replenishment trend with the prediction data, real-time usage needs, and online resource information to identify the best use of biological resources. Match biological resources to real-time usage needs based on the identification results.

2. The biological resource identification method based on Internet of Things technology according to claim 1, characterized in that: The steps in S1 are as follows: S1.1 Establish an information sharing module in the biological resource bank, obtain relevant data from the biological resource bank through the information sharing module, and then divide the biological resources of the biological resource bank into online biological resources and historical biological resources based on the relevant data of the biological resource bank; S1.2 Obtain online resource information of online biological resources, and extract historical usage records of historical biological resources.

3. The biological resource identification method based on Internet of Things technology according to claim 1, characterized in that: In S1, online biological resources are the biological resources currently stored in the biological resource bank, and historical biological resources are biological resources that have already been used. Online resource information includes images received, receipt date, expiration date, and product category data; Historical usage records include patient information and historical resource information.

4. The biological resource identification method based on Internet of Things technology according to claim 1, characterized in that: The steps in S3 are as follows: S3.1 Obtain real-time usage requirements and extract the patient information corresponding to those requirements; S3.

2. Match the patient information corresponding to the real-time usage needs with online biological resources to obtain online biological resources that meet the real-time usage needs.

5. The biological resource identification method based on Internet of Things technology according to claim 1, characterized in that: The steps in S4 are as follows: S4.1 Extract the categories of online biological resources corresponding to real-time usage needs, then extract the predicted users of the same category, and then compare the number of online biological resources corresponding to the predicted users with the number of online biological resources corresponding to real-time usage needs and the biological resource database. S4.2 When the predicted number of online biological resources corresponding to the patient and the number of online biological resources corresponding to the real-time usage demand are greater than the number of online biological resources in the biological resource bank, then identification and planning S5 shall be performed. S4.3 If the number of online biological resources corresponding to the predicted user patient and the number of online biological resources corresponding to the real-time usage demand are less than the number of online biological resources in the biological resource library, then after excluding the online biological resources corresponding to the predicted user patient from the online biological resources in the biological resource library, the online biological resource with the shortest storage time is selected for matching for the real-time demand.

6. The biological resource identification method based on Internet of Things technology according to claim 5, characterized in that: The steps in S5 are as follows: S5.1, Receive the signal from S4.2; S5.2 Combine online resource information in the biological resource bank with historical usage records to predict the replenishment trend of each type of biological resource, obtain the predicted replenishment trend of each type of biological resource, and then extract the predicted replenishment trend of the same type of biological resource with real-time usage demand. S5.3 Extract the predicted data for each patient, combine the extracted predicted supply trend with the predicted data, real-time demand, and online resource information to identify the best use of biological resources, and match biological resources to the real-time use demand based on the identification results.

7. A biological resource identification system based on Internet of Things (IoT) technology, wherein the biological resource identification system based on IoT technology is used to execute the biological resource identification method based on IoT technology as described in any one of claims 1-6, characterized in that: It includes a matching analysis module, a requirements analysis module, and an optimal identification module; The matching analysis module is used to collect online biological resources from the biological resource bank, obtain online resource information of online biological resources, extract historical usage records of historical biological resources, perform predictive analysis of biological resource usage based on patient information, and combine the patient information of the predicted users with historical usage records and online resource information to perform usage demand matching analysis. The demand analysis module is used to obtain real-time usage demand, and to match the real-time usage demand with online biological resources to obtain online biological resources that meet the real-time usage demand. The module also performs a quantity comparison analysis between the online biological resources corresponding to the predicted user and the online biological resources corresponding to the real-time usage demand and the biological resource library. The optimal identification module is used to predict the replenishment trend of biological resources of this category by combining online resource information and historical usage records. At the same time, it extracts the prediction data of each predicted user, combines the predicted replenishment trend with the prediction data, real-time usage needs, and online resource information to identify the optimal use of biological resources, and matches biological resources to real-time usage needs based on the identification results.

8. A readable storage medium, including a memory storing executable instructions, wherein when a processor executes the executable instructions stored in the memory, the processor hardware performs the biological resource identification method based on Internet of Things technology as described in any one of claims 1-6.

Images