Biological sample mobile phone terminal intelligent management system

Abstract

The invention discloses a biological sample mobile phone terminal intelligent management system, and aims to solve the technical problems of low tracking efficiency, environment monitoring lagging, unreasonable storage distribution, tedious approval process and the like in traditional biological sample management. The system is composed of a mobile terminal application, a cloud server and an Internet of Things equipment layer, and through integration of technologies such as RFID, Internet of Things sensing and an AI algorithm, intelligent management of the whole life cycle of a sample is achieved.

Description

Technical Field:

[0001] The present invention relates to the technical field of biological sample management, and specifically relates to an intelligent management system for biological samples on a mobile phone terminal, aiming to improve the storage efficiency, security, and traceability of biological samples. It is mainly applied to scenarios such as research institutions, hospitals, biotechnology and pharmaceutical companies that require efficient management of biological samples. Background Art:

[0002] In the field of biological sample management, the existing technologies have the following deficiencies:

[0003] Low sample tracking efficiency: Traditional sample management methods rely on manual records and paper labels, which are prone to information entry errors and difficult queries, resulting in low sample tracking efficiency.

[0004] Non-real-time environmental monitoring: The monitoring of the sample storage environment (such as temperature, humidity, light, etc.) mostly uses manual inspections or simple sensors, which cannot collect and transmit data in real time, making it difficult to detect and handle abnormal situations in a timely manner.

[0005] Unreasonable storage allocation: The allocation of sample storage locations lacks a scientific basis, often resulting in waste of storage space or inconvenience in sample access and storage.

[0006] Complicated approval process: The sample in-and-out approval process involves multiple links and departments, with high communication costs and low approval efficiency. Summary of the Invention:

[0007] The present invention provides an intelligent management system for biological samples on a mobile phone terminal, including a mobile application, a cloud server, and an Internet of Things device layer. The system uses technical means such as RFID, Internet of Things, and AI algorithms to achieve intelligent management of samples, real-time monitoring of environmental parameters, and optimized allocation of storage space. Improve sample tracking efficiency: Achieve rapid identification and tracking of samples through RFID and two-dimensional code technologies, reducing manual records and query errors. Realize real-time environmental monitoring: Real-time collect and transmit environmental parameters through Internet of Things sensors, detect and handle abnormal situations in a timely manner, and ensure the safe storage of samples. Optimize storage space allocation: Achieve intelligent matching of samples and storage locations through AI algorithms, improving storage space utilization and sample access efficiency. Simplify the approval process: Realize the functions of online application, review, and record of sample in-and-out through the mobile application, reducing communication costs and approval time. Brief Description of the Drawings:

[0008] To fully clarify the technical concept, solution architecture, and innovative advantages of the embodiments of this application, the following will conduct a systematic discussion based on the accompanying drawings of the embodiments. It should be particularly noted that the implementation forms described herein are only presented as representative technical solutions and do not exhaust all technical paths of this application. The core purpose of these embodiments is to explain the technical principles and does not constitute a limitation on the protection scope. Based on the technical inspiration of this application, those skilled in the art can derive other equivalent implementation forms without creative breakthroughs, and such derivative solutions are all within the scope of protection of the claims of this application.

[0009] For those with ordinary skills in this technical field, the professional terms (including technical terms and scientific concepts) used in this article adopt the prevailing definition standards in this field. It is particularly pointed out that relevant terms should be interpreted according to the general understanding at the current stage of technological development. Unless specifically defined in this article, idealized interpretations that go beyond the actual technical scenario should be avoided. For terms included in general dictionaries, their definitions should be consistent with the conventional meanings in the current technical context.

[0010] Figure 1 It is a flowchart of a mobile - end intelligent management system for biological samples in an embodiment of the present invention; Specific implementation manners:

[0011] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present invention.

[0012] As described above, the mobile - end application of the software design is developed based on the React Native framework, supports cross - platform operation, integrates the Zxing library to implement the function of QR code / RFID scanning, and uses the WebSocket protocol to communicate with the cloud server in real - time. The core functions include modules such as sample tracking, environmental monitoring, and approval process. The sample tracking module supports researchers to query the location and status information of samples in real - time by scanning sample labels; the environmental monitoring module can remotely view environmental parameters such as temperature, humidity, and light in the storage area; the approval process module realizes the functions of online application, review, and record of sample inbound and outbound. The mobile - end application interface is simple and clear, and the operation process conforms to user habits, ensuring that researchers can efficiently and conveniently manage biological samples.

[0013] As described above, the cloud server runs AI algorithms, such as storage allocation algorithms and sample recommendation algorithms, and manages the database. The storage allocation algorithm uses the Java language to implement the K-means clustering algorithm. Based on attributes of samples such as the preservation temperature range, volume, usage frequency, etc., and data such as the available space of the storage location and the distance to the adjacent operation area, it outputs suggestions for the optimal storage location. The sample recommendation algorithm constructs a deep learning model based on the TensorFlow framework, integrates scientific research requirements (such as disease types, gene targets) and sample characteristics (such as pathological indicators, collection time), generates a personalized recommendation list, and provides accurate sample selection for scientific researchers. The database uses a MySQL cluster to store sample metadata to ensure data integrity and security; Redis caches frequently queried data to improve data access efficiency; Elasticsearch supports complex retrievals to meet the diverse query needs of scientific researchers.

[0014] As described above, the Internet of Things device layer includes RFID readers, environmental sensors, and automated storage devices, and preprocesses data through edge computing nodes to achieve intelligent management of the devices. The RFID reader communicates with the edge node using the EPC C1G2 protocol to achieve fast identification and tracking of sample tags; environmental sensors (such as DHT22 temperature and humidity sensors, BH1750 light sensors) transmit data through the Modbus RTU protocol to collect environmental parameters of the storage area in real time; automated storage devices (such as intelligent storage cabinets, liquid nitrogen tanks) integrate a stepper motor drive system to achieve automatic access and precise positioning of sample boxes. The Internet of Things device layer communicates with the cloud server in real time through a 4G / 5G network to ensure timely data transmission and stable control of the devices.

[0015] As described above, the input parameters of the algorithm implementation storage allocation algorithm include the preservation temperature range, volume, usage frequency of the sample, and the available space of the storage location, the distance to the adjacent operation area, etc. The processing process includes three stages: data standardization, clustering analysis, and result output. In the data standardization stage, qualitative indicators such as the preservation temperature range of the sample are converted into quantitative values for subsequent calculations; in the clustering analysis stage, the K-means algorithm is used to cluster sample and storage location data to find the optimal storage location; in the result output stage, according to the clustering analysis results, the storage location number and operation path that best match the sample characteristics are output, providing a scientific basis for sample storage.

[0016] As described above, the sample recommendation algorithm is based on the Wide&Deep model, integrating scientific research needs and sample features to generate a recommendation list. The model training uses a database containing 100,000 sample records, and the network structure includes a Wide part and a Deep part. The Wide part processes discrete features (such as disease type, sample source), and the Deep part learns continuous features (such as gene expression values, pathological indicators). During real-time reasoning, the scientific research demand vector (such as "Lung Cancer PD-1 Inhibitor Research") is input, and a Top-10 sample list is output, sorted by matching degree, and the storage location and validity period are marked to provide researchers with accurate sample selection. The sample recommendation algorithm regularly updates the model parameters to ensure the accuracy and timeliness of the recommendation results.

[0017] As described above, when the data flow samples are put into storage, the metadata (such as source, type, collection time, etc.) is bound by scanning the tag through the RFID handheld terminal after the sample is collected. The system calls the storage allocation algorithm to recommend the storage location and automatically allocates it, and updates the inventory database. The whole process realizes the accurate entry of sample information and the reasonable allocation of storage locations. After the sample is put into storage, the system automatically generates a storage record, including sample number, storage time, storage location and other information, which is convenient for subsequent query and management.

[0018] As mentioned above, when samples are released from the warehouse, researchers submit applications on the mobile terminal to specify required parameters (such as disease type, gene target, sample size, etc.). The AI ​​recommendation algorithm generates a candidate list to display information such as matching degree, storage location and validity period. After approval, the system automatically records the release log and updates the sample status to "in use". The entire process realizes the rapid approval and accurate recording of sample release, ensuring the rational use and traceability management of samples.

[0019] As described above, during environmental monitoring, the sensor node collects environmental parameters such as temperature, humidity, and light every 5 seconds and uploads them to the edge node for preprocessing. The cloud server analyzes the data and triggers a mobile alarm when an abnormality occurs. The administrator can remotely adjust the device parameters (such as air conditioning settings, lighting control, etc.) through the APP to ensure the stability and security of the storage environment. The environmental monitoring process realizes real-time supervision and intelligent regulation of the storage area, providing a strong guarantee for the safe storage of biological samples.

[0020] As mentioned above, the security and rights management data encryption uses the TLS1.3 protocol to encrypt the transport layer data to ensure the security of the data during transmission. At the same time, the AES-256 algorithm is used to encrypt sensitive fields in the storage layer (such as patient names, gene sequences, etc.) to prevent data leakage and tampering. The data encryption scheme complies with industry security standards to ensure the secure storage and transmission of biological sample data.

[0021] Specifically, the permission control defines roles (such as sample library administrators, researchers, visitors) based on the RBAC (Role-Based Access Control) model and assigns permissions (such as "query all samples", "modify environmental parameters", "approve outbound applications", etc.). It finely controls data access, device operations, and approval processes to ensure the security and compliance of the system. The permission control scheme supports dynamic adjustment of roles and permissions to meet the needs of system expansion and changes.

[0022] As mentioned above, the audit trail uses the ELK (Elasticsearch, Logstash, Kibana) stack to record operation logs, including information such as operation time, user ID, operation content, IP address, etc. It regularly generates audit reports to identify abnormal operations (such as accessing during non-working hours, frequently querying sensitive data, etc.), providing strong support for the security audit and compliance review of the system. The audit trail scheme ensures the transparency and traceability of system operations, and timely discovers and prevents security risks.

[0023] Based on the preferred embodiments of the present invention as inspiration, through the foregoing detailed description, those skilled in the relevant art can fully implement various changes and adjustments without departing from the basic technical concept of the present invention. The technical protection scope of the present invention is not limited to the specific description of this specification, but should be defined by the scope defined in the claims.

Claims

1. A biological sample mobile terminal intelligent management system, characterized in that: It includes mobile applications, cloud servers and IoT device layers; the mobile application is developed based on the React Native framework, integrates the Zxing library to realize the QR code / RFID scanning function, and uses the WebSocket protocol to communicate with the cloud server in real time; the cloud server runs AI algorithms, including storage allocation algorithms and sample recommendation algorithms, and manages the database; the IoT device layer includes RFID readers, environmental sensors and automated storage devices, and pre-processes data through edge computing nodes to realize intelligent management of equipment.

2. The system according to claim 1, characterized in that The RFID reader is deployed at the entrance, exit and key operation areas of the sample library, using high frequency or ultra-high frequency bands to ensure that the sample tags are stably read during movement.

3. The system according to claim 1, characterized in that The environmental sensor covers each shelf and refrigeration equipment in the sample storage area, adopts DHT22 temperature and humidity sensor and BH1750 light sensor, and transmits environmental parameters to the cloud server in real time through ZigBee protocol networking.

4. The system according to claim 1, characterized in that The smart storage cabinet is equipped with a facial recognition camera and a fingerprint module to support dual identity authentication. A stepper motor drive system is integrated in the cabinet to achieve automatic storage and retrieval of sample boxes.

5. The system according to claim 1, characterized in that The liquid nitrogen tank monitoring unit uses a PT100 temperature sensor and an ultrasonic level meter. The data is transmitted to the edge computing node through the RS485 interface and is equipped with a redundant power supply module to ensure continuous monitoring in the event of a power outage.

6. The system according to claim 1, characterized in that The storage allocation algorithm uses the Java language to implement the K-means clustering algorithm, and outputs the optimal storage location recommendation based on parameters such as the sample's storage temperature range, volume, usage frequency, available space in the storage location, and distance to adjacent operating areas.

7. The system according to claim 1, characterized in that The sample recommendation algorithm builds a deep learning model based on the TensorFlow framework, integrating scientific research needs and sample characteristics to generate a personalized recommendation list.

8. The system according to claim 1, characterized in that The data encryption uses the TLS1.3 protocol to encrypt the transport layer data and the AES-256 algorithm to encrypt the sensitive fields of the storage layer.

9. The system according to claim 1, characterized in that The permission control defines roles and assigns permissions based on the RBAC model, and controls data access, device operation and approval processes in a fine-grained manner.

10. The system according to claim 1, characterized in that The audit trail uses the ELK stack to record operation logs and regularly generates audit reports to identify abnormal operations.

Images