Pathological specimen intelligent management system and method based on Internet of Things

Abstract

The invention relates to the technical field of pathological specimen management, in particular to an intelligent pathological specimen management system and method based on the Internet of Things. The method comprises the following steps: acquiring a pathological specimen, performing specimen injection molding and sealing treatment by using a closed injection molding machine, storing the specimen in a pathological specimen storage cabinet, performing RFID identification marking by using an RFID technology, and transmitting RFID automatic identification information corresponding to the pathological specimen to an Internet of Things platform; temperature data and humidity data corresponding to a pathological specimen are monitored in real time, specimen temperature calibration and specimen temperature anomaly response management are carried out, and a pathological specimen storage temperature anomaly control instruction is generated to execute storage condition automatic adjustment management work; and carrying out specimen state real-time monitoring and specimen state decay analysis on the pathological specimen, and carrying out specimen state matching abnormity response alarm so as to carry out pathological specimen state abnormity automatic notification work. The pathological specimen storage and use efficiency can be improved.

Description

Technical Field

[0001] This invention relates to the field of pathological specimen management technology, and in particular to an intelligent management system and method for pathological specimens based on the Internet of Things. Background Technology

[0002] In recent years, the rapid development of the Internet of Things (IoT) technology has provided new solutions for the intelligent management of pathological specimens. By comprehensively applying IoT technology during the collection, storage, and transportation of pathological specimens, and utilizing sensors to monitor environmental parameters (such as temperature and humidity) in real time, specimens are ensured to be stored under suitable conditions. Simultaneously, installing RFID tags on each specimen container enables automatic collection and tracking of specimen information. Furthermore, by building a centralized management platform to integrate data from various stages, real-time information sharing and analysis are achieved. This platform can automatically generate specimen lifecycle records, facilitating timely access to specimen information for medical personnel, improving work efficiency. Through big data analysis, the usage of pathological specimens can be predicted and optimized, ensuring the rational allocation of resources. However, traditional pathological specimen management methods often lack real-time monitoring of storage conditions, failing to effectively prevent specimen deterioration due to improper storage environments, thus reducing the efficiency and accuracy of abnormal pathological specimen management. Summary of the Invention

[0003] Therefore, it is necessary for the present invention to provide an intelligent management system and method for pathological specimens based on the Internet of Things, in order to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, an intelligent management method for pathological specimens based on the Internet of Things (IoT) includes the following steps: Step S1: Obtain pathological specimen samples and use a closed injection molding machine with a built-in ventilation system and gas purification filtration system to perform specimen injection molding and sealing treatment to obtain pathological injection-molded specimens; store the pathological injection-molded specimens in a pathological specimen storage cabinet with a built-in constant temperature control device, video recognition system, and Internet of Things platform. The constant temperature control device includes a temperature monitoring unit, a humidity monitoring unit, and a control unit. RFID technology is used to identify and mark the pathological injection-molded specimens in the pathological specimen storage cabinet to obtain pathological RFID-tagged specimens; use an RFID reader / writer fixed on the pathological specimen storage cabinet to automatically identify the pathological RFID-tagged specimens and transmit the corresponding RFID automatic identification information to the Internet of Things platform. The RFID automatic identification information includes specimen sampling time, specimen storage conditions, and specimen type. Step S2: The temperature and humidity data corresponding to the pathological specimens with RFID tags in the pathological specimen storage cabinet are monitored in real time using the temperature monitoring unit and humidity monitoring unit in the constant temperature control device. The temperature data is then calibrated based on the humidity data to obtain the calibrated temperature data of the pathological specimens and uploaded to the Internet of Things (IoT) platform. The IoT platform is used to manage the abnormal response of the specimen storage conditions and the calibrated temperature data of the pathological specimens, and to generate abnormal control commands for the storage temperature of the pathological specimens to execute the automatic adjustment and management of the storage conditions of the pathological specimens corresponding to the adjustment and control unit in the constant temperature control device. Step S3: Use a video recognition system to monitor the real-time status of the corresponding pathological RFID-tagged specimens in the pathological specimen storage cabinet to obtain real-time video image frames of the pathological specimens; perform specimen status decay analysis on the corresponding pathological RFID-tagged specimens in the pathological specimen storage cabinet based on the specimen sampling time and specimen storage conditions to obtain the ideal change state of normal decay of the pathological specimens; perform specimen status matching anomaly response alarm on the real-time status video image frames of the pathological specimens based on the ideal change state of normal decay of the pathological specimens to generate an abnormal alarm signal for the change state of the pathological specimens. Step S4: Apply the abnormal status alarm signal of the pathological specimen to the Internet of Things platform to send abnormal pathological specimen alarm information and automatically notify the abnormal status of the pathological specimen.

[0005] Furthermore, step S1 includes the following steps: Step S11: Obtain pathological specimen samples; Step S12: Perform surface impurity pretreatment on the pathological specimen samples to obtain standardized pretreated specimen samples; Step S13: Based on the specimen type corresponding to the standardized pre-treated specimen samples, design the internal environment control of the closed injection molding machine with built-in ventilation system and gas purification and filtration system to generate a closed injection molding internal environment control setting report; activate the ventilation system and gas purification and filtration system according to the specimen injection molding environment parameters in the closed injection molding internal environment control setting report to perform specimen injection molding and sealing treatment on the corresponding standardized pre-treated specimen samples to obtain pathological injection-molded specimens; Step S14: Store the pathological injection-molded specimens in a pathological specimen storage cabinet with a built-in constant temperature control device, video recognition system and Internet of Things platform, and use RFID technology to identify and mark the pathological injection-molded specimens in the pathological specimen storage cabinet to obtain pathological RFID-tagged specimens. Step S15: Use an RFID reader / writer fixed on the pathological specimen storage cabinet to automatically identify the pathological RFID-tagged specimens and transmit the corresponding RFID automatic identification information to the Internet of Things platform. The RFID automatic identification information includes the specimen sampling time, specimen storage conditions, and specimen type.

[0006] Furthermore, step S2 includes the following steps: Step S21: Use the temperature monitoring unit in the constant temperature control device to monitor the temperature of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time, so as to obtain the temperature data of the pathological RFID tag specimens. Step S22: Use the humidity monitoring unit in the constant temperature control device to monitor the humidity of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time, so as to obtain the humidity data of the pathological RFID tag specimens. Step S23: Based on the humidity data corresponding to the pathological RFID tag specimen, perform specimen temperature calibration on the temperature data corresponding to the pathological RFID tag specimen to obtain pathological specimen calibration temperature data and upload it to the Internet of Things platform; Step S24: Use the IoT platform to compare and judge the specimen temperature of the pathological specimen storage temperature standard and the pathological specimen calibration temperature data within the specimen storage conditions. If the pathological specimen calibration temperature data is equal to the pathological specimen storage temperature standard, continue to monitor the storage temperature of the storage cabinet corresponding to the calibrated pathological specimen in real time; if the pathological specimen calibration temperature data is greater than or less than the pathological specimen storage temperature standard, determine the pathological specimen calibration temperature data as an abnormal storage temperature. Step S25: Utilize the Internet of Things platform to perform abnormal response control analysis on the abnormal storage temperature to generate abnormal control instructions for pathological specimen storage temperature; apply the abnormal control instructions for pathological specimen storage temperature to the regulating control unit in the constant temperature regulating device to perform abnormal temperature regulation management, so as to execute the automatic regulation management of pathological specimen storage conditions corresponding to the regulating control unit in the constant temperature regulating device.

[0007] Furthermore, step S23 includes the following steps: Step S231: Perform time-series synchronization processing on the temperature and humidity data corresponding to the pathological RFID tag specimens to obtain the pathological specimen temperature and humidity data under the same time-series change dimension; Step S232: Perform baseline identification and analysis of humidity changes in pathological specimens to obtain the time-series baseline of humidity changes in pathological specimens; Step S233: Based on the baseline of the time-series change in the humidity of pathological specimens, perform temperature and humidity interaction analysis on the temperature data of pathological specimens under the same time-series change dimension to obtain the nonlinear interaction relationship between the humidity change and temperature of pathological specimens. Step S234: Based on the nonlinear interaction between pathological specimen humidity change and temperature, conduct humidity impact assessment analysis on pathological specimen temperature data and pathological specimen humidity data to obtain the specimen temperature interaction factor corresponding to pathological specimen humidity change. Step S235: Based on the specimen temperature interaction factor corresponding to the humidity change of the pathological specimen, perform specimen temperature calibration on the temperature data corresponding to the pathological RFID tag specimen to obtain the pathological specimen calibration temperature data and upload it to the Internet of Things platform.

[0008] Furthermore, step S233 includes the following steps: Short-term fluctuation smoothing was applied to the baseline of temporal changes in the humidity of pathological specimens to obtain a smoothed baseline of stable changes in the humidity of pathological specimens. The smoothed baseline of stable changes in pathological specimen humidity and the temperature data of pathological specimens under the same time-series change dimension are divided into time periods to obtain the corresponding baseline of pathological specimen humidity change and the temperature data of pathological specimens under each time period. Based on the baseline of humidity change of pathological specimens in each time period, nonlinear correlation fitting analysis was performed on the corresponding temperature data of pathological specimens in each time period to obtain the nonlinear correlation fitting coefficient between humidity change and temperature of pathological specimens in each time period. Based on the nonlinear correlation fitting coefficient between the humidity change and temperature of pathological specimens at different time periods, the interaction influence between the corresponding baseline humidity change and temperature data of pathological specimens was analyzed to obtain the nonlinear influence relationship between humidity change and temperature of pathological specimens.

[0009] Furthermore, step S3 includes the following steps: Step S31: Use a video recognition system to monitor the real-time status of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet, so as to obtain real-time video image frames of the pathological specimen status. Step S32: Perform video image detail contrast enhancement processing on the real-time status video image frames of the pathological specimen to obtain the pathological specimen status video contrast enhancement image frames; Step S33: Perform time-segmented specimen status recognition and analysis on the video contrast enhancement image frames of the pathological specimen status to obtain the real-time status of the pathological specimen within each time segment. Step S34: Based on the specimen sampling time and specimen storage conditions, perform specimen state decay analysis on the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet to obtain the ideal change state of normal decay of the pathological specimens. Step S35: Based on the ideal change state of normal decay of the pathological specimen, perform specimen status matching and abnormal response alarm for the real-time status of the pathological specimen within each time period range to generate an abnormal alarm signal for the change state of the pathological specimen.

[0010] Furthermore, step S34 includes the following steps: Step S341: Based on the specimen sampling time, evaluate the impact of sampling time on the specimen status of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet, and obtain the specimen status impact factor of storage sampling time; Step S342: Based on the specimen storage conditions, evaluate the impact of storage conditions on the specimen status of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet, and obtain the pathological specimen status impact factors corresponding to each storage condition, wherein each storage condition includes temperature, humidity and light intensity. Step S343: Based on the storage sampling time specimen state influence factor and the pathological specimen state influence factor corresponding to each storage condition, use the pathological specimen state decay index calculation formula to calculate the specimen state decay of the corresponding pathological RFID tag specimen in the pathological specimen storage cabinet, and obtain the pathological specimen change state decay index. Step S344: Based on the decay index of the pathological specimen change state, perform normal decay change identification and analysis on the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet to obtain the ideal normal decay change state of the pathological specimen.

[0011] Furthermore, the formula for calculating the pathological specimen state decay index in step S343 is as follows: ; In the formula, In time The decay index of the pathological specimen at the site. For time-varying parameters, This refers to the initial state measurement value of the specimen corresponding to the pathological RFID tag specimen. The coefficient representing the influence of the decay of the pathological specimen's condition. To store the sampling duration and the influence factors of the specimen state, For the time of specimen sampling, The factors affecting the condition of pathological specimens corresponding to temperature. For temperature, Humidity is a factor affecting the condition of pathological specimens. For humidity, The factors influencing the state of pathological specimens are light intensity. Light intensity, This is the correction factor for the decay index of pathological specimen changes.

[0012] Furthermore, step S35 includes the following steps: Step S351: Based on the real-time status of the pathological specimen within each time period, perform time period status synchronization matching and division of the ideal change status of the normal decay of the pathological specimen, so as to obtain the real-time status of the pathological specimen and the ideal normal status of the pathological specimen within the same time period. Step S352: Based on the normal ideal state of the pathological specimen within the same time period, identify and judge the real-time state of the corresponding pathological specimen. If the identification and judgment shows that the real-time state of the pathological specimen within the corresponding time period matches the normal ideal state of the pathological specimen, continue to identify and judge the next time period. If the identification and judgment shows that the real-time state of the pathological specimen within the corresponding time period does not match the normal ideal state of the pathological specimen, perform abnormal response alarm processing on the real-time state of the pathological specimen within that time period to generate an abnormal alarm signal for the change in the state of the pathological specimen.

[0013] Furthermore, for implementing the IoT-based intelligent management method for pathological specimens as described above, the IoT-based intelligent management system for pathological specimens includes: The pathological specimen RFID identification and tagging module is used to acquire pathological specimen samples and perform specimen injection molding and sealing treatment on the samples using a closed injection molding machine with a built-in ventilation system and gas purification and filtration system to obtain pathological injection-molded specimens. These specimens are then stored in a pathological specimen storage cabinet equipped with a built-in constant temperature control device, video recognition system, and IoT platform. The constant temperature control device includes a temperature monitoring unit, a humidity monitoring unit, and a control unit. RFID technology is used to identify and tag the pathological injection-molded specimens in the storage cabinet, resulting in pathological RFID-tagged specimens. An RFID reader / writer fixed to the storage cabinet automatically identifies the RFID-tagged specimens and transmits the corresponding RFID automatic identification information to the IoT platform. This RFID automatic identification information includes the specimen sampling time, specimen storage conditions, and specimen type. The pathological specimen storage temperature anomaly control module is used to monitor the temperature and humidity data of the pathological specimens with RFID tags in the storage cabinet in real time using the temperature monitoring unit and humidity monitoring unit in the constant temperature control device. Based on the humidity data, the module calibrates the temperature data of the specimens to obtain the calibrated temperature data of the pathological specimens and uploads it to the Internet of Things (IoT) platform. The IoT platform is used to manage the abnormal response of specimen storage conditions and the calibrated temperature data of pathological specimens, and generate abnormal control commands for pathological specimen storage temperature to execute the automatic adjustment and management of the pathological specimen storage conditions corresponding to the adjustment and control unit in the constant temperature control device. The pathological specimen status abnormality alarm module is used to monitor the status of corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time using a video recognition system to obtain real-time video image frames of the pathological specimen status; to perform specimen status decay analysis on the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet based on the specimen sampling time and specimen storage conditions to obtain the ideal change state of normal decay of the pathological specimen; and to generate an alarm signal for abnormal change of pathological specimen status by matching the specimen status abnormality to the real-time video image frames of the pathological specimen based on the ideal change state of normal decay of the pathological specimen. The pathological specimen status abnormality notification management module is used to send pathological specimen abnormality alarm signals to the Internet of Things platform and automatically notify the pathological specimen status abnormality.

[0014] The beneficial effects of this invention are: 1. The intelligent management method for pathological specimens based on the Internet of Things proposed in this invention, compared with the prior art, has the following advantages: It obtains relevant pathological specimen samples, which not only involves the source and quality of the samples but also forms the basis for ensuring the accuracy of subsequent analysis. Through a rigorous sampling process, the representativeness and integrity of the specimens are ensured. After collection, the pathological specimen samples are sealed using a closed injection molding machine with a built-in ventilation system and a gas purification and filtration system. This allows for strict control of the gas composition, pressure, and temperature of the pathological specimens during the sealing process, ensuring that the specimens are not adversely affected during the injection molding process. Injection molding not only effectively prevents contamination but also preserves the biological characteristics of the samples, making them suitable for subsequent research. The successful implementation of this process greatly improves the preservation quality and stability of pathological specimens, thus providing highly reliable samples for subsequent storage. By storing molded pathological specimens in a storage cabinet equipped with a built-in temperature control device, video recognition system, and IoT platform, and using RFID technology to identify and tag the molded specimens within the cabinet, the location, status, and related information of the specimens can be tracked in real time. The key to this step lies in the digitalization and automation of data management, which not only improves the security of specimen storage but also significantly enhances the efficiency of information retrieval. RFID tags make the management of pathological specimens more intelligent, facilitating the recording of specimen sampling time, storage conditions, and type information, ensuring the accuracy and traceability of all data, and making sample storage, use, and preparation more efficient and reliable. Simultaneously, by using RFID readers fixed to the storage cabinet, the system automatically identifies RFID-tagged specimens and transmits the information to the IoT platform. The key to this step is the real-time monitoring and automatic updating of specimen RFID tag information, which not only reduces the burden of manual operation but also greatly improves the accuracy and timeliness of information management. Through the IoT platform, researchers can obtain detailed information about specimens at any time, such as sampling time, storage conditions, and specimen type, further optimizing specimen use and management. This systematic management ensures the integrity and safety of pathological specimens, reduces management risks, and provides stronger data support for the subsequent intelligent management of pathological samples in the storage cabinet. Secondly, by using the temperature monitoring unit within the thermostatic device to monitor the temperature of the corresponding pathological RFID-tagged specimens in the storage cabinet in real time, researchers can continuously track temperature changes within the cabinet and obtain temperature data for each specimen in a timely manner. This provides dynamic feedback on the specimen storage environment, enabling researchers to promptly detect temperature anomalies and take appropriate measures to prevent sample deterioration or damage.By using a humidity monitoring unit within the thermostatic control system to monitor the humidity of corresponding RFID-tagged specimens within the pathological specimen storage cabinet in real time, humidity data is acquired to ensure that each specimen is in an optimal preservation environment. This step, through real-time humidity monitoring, helps prevent biological specimens from drying out or becoming too wet, maintains the biological activity and chemical stability of the samples, avoids potential damage, and ensures a high standard and high safety in the specimen preservation process. This provides a foundational data guarantee for subsequent temperature calibration. Furthermore, specimen temperature calibration is performed based on humidity data. By combining humidity and temperature data, more realistic storage temperature parameters can be obtained, ensuring that specimens are preserved under ideal conditions. Temperature calibration not only improves the scientific rigor of specimen storage but also provides a more solid foundation for subsequent data analysis. Furthermore, by utilizing an IoT platform to manage abnormal specimen temperature responses based on corresponding temperature standards and pathological specimen calibration temperature data within the specimen storage conditions, abnormal temperature control commands for pathological specimen storage are generated. When the system detects a temperature abnormality—that is, when the calibration temperature is greater than or less than the temperature standard—the rapidly generated control command can automatically act on the temperature control unit of the thermostat to adjust the temperature. The key to this process is its ability to respond to changes in storage conditions in real time, ensuring that specimens are properly managed under any circumstances, thereby improving the management capabilities of the storage cabinet and the quality of specimen preservation. Then, by using a video recognition system to monitor the status of corresponding pathological RFID-tagged specimens within the pathological specimen storage cabinet in real time, comprehensive supervision of the pathological specimens within the cabinet can be achieved. This process, through real-time acquisition of video image frames, allows researchers to understand the specific status of the specimens at any time, including changes in appearance, storage location, and surrounding environment. This monitoring not only helps ensure the integrity and safety of the specimens but also effectively prevents the specimens from being affected by external storage environmental factors during storage. By performing specimen decay analysis on corresponding pathological RFID-tagged specimens in the pathological specimen storage cabinet based on specimen sampling time and storage conditions, this step allows us to understand the ideal decay pattern of specimens under specific conditions and identify the decay trend under normal circumstances. Establishing this ideal decay state can provide a benchmark reference for subsequent anomaly detection. Through scientific decay analysis, researchers can formulate reasonable storage strategies, extend the preservation period of specimens, and effectively avoid specimen damage or data distortion caused by improper storage, thereby ensuring the reliability and validity of research results.Furthermore, by matching the real-time changes of pathological specimens within corresponding frames of real-time video images based on their ideal decay state during normal decay, anomaly response alarms are generated. This enables the detection and timely alarm of pathological specimen anomalies. This mechanism, through real-time monitoring of specimen state changes, quickly identifies situations inconsistent with normal decay patterns. Once an anomaly is detected, an alarm signal is automatically generated, promptly notifying relevant personnel for intervention. This process not only improves the safety of pathological specimens but also enables real-time monitoring of storage conditions, effectively preventing specimen deterioration due to improper storage environments. Finally, by applying the pathological specimen anomaly alarm signal to an IoT platform, the system also enables the automatic transmission and notification of pathological specimen anomaly alarm information. By transmitting anomaly signals to the IoT platform in real time, relevant personnel receive timely notifications and take necessary measures to prevent potential losses or risks. This automatic notification function significantly improves the efficiency of specimen management, ensuring that any anomalies are handled quickly, thereby greatly enhancing the efficiency and accuracy of pathological specimen anomaly management.

[0015] 2. The IoT-based intelligent management system for pathological specimens proposed in this invention consists of a pathological specimen RFID identification and marking module, a pathological specimen storage temperature anomaly control module, a pathological specimen status anomaly alarm module, and a pathological specimen status anomaly notification management module. It can realize any IoT-based intelligent management method for pathological specimens described in this invention. It uses the combined operations of computer programs running on each module to achieve IoT-based intelligent management of pathological specimens. The internal structure of the system collaborates with each other, which greatly reduces repetitive work and manpower input, and can quickly and effectively provide a more accurate and efficient IoT-based intelligent management process for pathological specimens, thereby simplifying the operation process of the IoT-based intelligent management system for pathological specimens. Attached Figure Description

[0016] Other features, objects, and advantages of the invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings: Figure 1 This is a schematic diagram of the steps of the intelligent management method for pathological specimens based on the Internet of Things according to the present invention; Figure 2 for Figure 1 A detailed flowchart of step S1; Figure 3 for Figure 1 A detailed flowchart of step S2. Detailed Implementation

[0017] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0018] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0019] It should be understood that although the terms "first," "second," etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are used merely to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0020] To achieve the above objectives, please refer to Figures 1 to 3 This invention provides an intelligent management method for pathological specimens based on the Internet of Things, the method comprising the following steps: Step S1: Obtain pathological specimen samples and use a closed injection molding machine with a built-in ventilation system and gas purification filtration system to perform specimen injection molding and sealing treatment to obtain pathological injection-molded specimens; store the pathological injection-molded specimens in a pathological specimen storage cabinet with a built-in constant temperature control device, video recognition system, and Internet of Things platform. The constant temperature control device includes a temperature monitoring unit, a humidity monitoring unit, and a control unit. RFID technology is used to identify and mark the pathological injection-molded specimens in the pathological specimen storage cabinet to obtain pathological RFID-tagged specimens; use an RFID reader / writer fixed on the pathological specimen storage cabinet to automatically identify the pathological RFID-tagged specimens and transmit the corresponding RFID automatic identification information to the Internet of Things platform. The RFID automatic identification information includes specimen sampling time, specimen storage conditions, and specimen type. Step S2: The temperature and humidity data corresponding to the pathological specimens with RFID tags in the pathological specimen storage cabinet are monitored in real time using the temperature monitoring unit and humidity monitoring unit in the constant temperature control device. The temperature data is then calibrated based on the humidity data to obtain the calibrated temperature data of the pathological specimens and uploaded to the Internet of Things (IoT) platform. The IoT platform is used to manage the abnormal response of the specimen storage conditions and the calibrated temperature data of the pathological specimens, and to generate abnormal control commands for the storage temperature of the pathological specimens to execute the automatic adjustment and management of the storage conditions of the pathological specimens corresponding to the adjustment and control unit in the constant temperature control device. Step S3: Use a video recognition system to monitor the real-time status of the corresponding pathological RFID-tagged specimens in the pathological specimen storage cabinet to obtain real-time video image frames of the pathological specimens; perform specimen status decay analysis on the corresponding pathological RFID-tagged specimens in the pathological specimen storage cabinet based on the specimen sampling time and specimen storage conditions to obtain the ideal change state of normal decay of the pathological specimens; perform specimen status matching anomaly response alarm on the real-time status video image frames of the pathological specimens based on the ideal change state of normal decay of the pathological specimens to generate an abnormal alarm signal for the change state of the pathological specimens. Step S4: Apply the abnormal status alarm signal of the pathological specimen to the Internet of Things platform to send abnormal pathological specimen alarm information and perform automatic notification of abnormal status of pathological specimen.

[0021] In the embodiments of this invention, please refer to Figure 1 The diagram shown is a flowchart illustrating the steps of the IoT-based intelligent management method for pathological specimens according to the present invention. In this example, the IoT-based intelligent management method for pathological specimens includes the following steps: Step S1: Obtain pathological specimen samples and use a closed injection molding machine with a built-in ventilation system and gas purification filtration system to perform specimen injection molding and sealing treatment to obtain pathological injection-molded specimens; store the pathological injection-molded specimens in a pathological specimen storage cabinet with a built-in constant temperature control device, video recognition system, and Internet of Things platform. The constant temperature control device includes a temperature monitoring unit, a humidity monitoring unit, and a control unit. RFID technology is used to identify and mark the pathological injection-molded specimens in the pathological specimen storage cabinet to obtain pathological RFID-tagged specimens; use an RFID reader / writer fixed on the pathological specimen storage cabinet to automatically identify the pathological RFID-tagged specimens and transmit the corresponding RFID automatic identification information to the Internet of Things platform. The RFID automatic identification information includes specimen sampling time, specimen storage conditions, and specimen type. In this embodiment of the invention, the required tissue sample is extracted from the patient using a precision biopsy needle. The sample is then immediately placed in a pre-prepared saline solution or other preservative solution to maintain its biological activity, thereby obtaining a pathological specimen sample. By determining the specimen type corresponding to the pathological specimen sample, such as a frozen specimen or a routine specimen, and designing the environmental operating parameters of the built-in ventilation system and gas purification and filtration system according to the corresponding specimen type, for example, for samples requiring a low-oxygen environment, the control system is set to reduce the oxygen concentration inside the machine to a specific range, while simultaneously activating the gas purification filter to ensure that external pollutants do not affect the quality of the specimen. A detailed internal environmental control setting report is generated, listing the specific temperature, humidity, and gas composition control parameters for the corresponding specimen type. By combining the previously designed internal environmental control setting report, the relevant systems of the closed injection molding machine are activated to adjust the ventilation system and gas purification and filtration system to the set state according to the parameters in the report, ensuring that the internal environment of the machine meets the expected standards. By placing the standardized pre-treated specimen sample into the injection molding machine and performing sealing treatment, the injection molding machine will combine the biological material with the specific sealing material through heating and pressing to form a stable pathological injection-molded sealed specimen, ensuring that the biological characteristics of the specimen are effectively preserved, thus obtaining a pathological injection-molded sealed specimen. Meanwhile, the specimens, which have previously undergone injection molding and sealing, are stored in a dedicated pathological specimen storage cabinet. This cabinet is equipped with a built-in thermostat to maintain a suitable storage temperature. The cabinet is also equipped with a video recognition system to monitor changes in the storage status of the specimens in real time. It is also configured with a corresponding Internet of Things platform to transmit the monitored data in real time and manage any anomalies. Furthermore, RFID technology is used to attach RFID tags to each specimen in the pathological specimen storage cabinet. The tags store basic information about the specimen and its storage conditions. This process ensures that all specimens remain traceable and secure during storage, resulting in pathological RFID-tagged specimens. Then, by using a fixed RFID reader inside the pathology specimen storage cabinet, the RFID tags on each pathology RFID-tagged specimen are automatically identified. When a specimen is stored or retrieved, the RFID reader quickly reads the tag information, including the specimen sampling time, storage conditions, and specimen type. The identification information is transmitted in real time through the Internet of Things platform to ensure accurate recording and timely updates of the data. This automated management of information not only improves work efficiency but also reduces errors from manual operation, ensuring the intelligent and systematic management of pathology specimens. Ultimately, the corresponding RFID automatic identification information is obtained, including the specimen sampling time, specimen storage conditions, and specimen type.

[0022] Step S2: The temperature and humidity data corresponding to the pathological specimens with RFID tags in the pathological specimen storage cabinet are monitored in real time using the temperature monitoring unit and humidity monitoring unit in the constant temperature control device. The temperature data is then calibrated based on the humidity data to obtain the calibrated temperature data of the pathological specimens and uploaded to the Internet of Things (IoT) platform. The IoT platform is used to manage the abnormal response of the specimen storage conditions and the calibrated temperature data of the pathological specimens, and to generate abnormal control commands for the storage temperature of the pathological specimens to execute the automatic adjustment and management of the storage conditions of the pathological specimens corresponding to the adjustment and control unit in the constant temperature control device. In this embodiment of the invention, a temperature monitoring unit within the constant temperature control device is used to monitor the storage temperature of corresponding pathological RFID-tagged specimens within the pathological specimen storage cabinet in real time. This allows for the real-time acquisition of temperature data for each pathological RFID-tagged specimen within the cabinet. The data is uploaded to an IoT platform via a wireless communication module, forming a continuous temperature monitoring record, thereby obtaining the temperature data corresponding to each pathological RFID-tagged specimen. Furthermore, a humidity monitoring unit within the constant temperature control device is used to monitor the storage humidity of the corresponding pathological RFID-tagged specimens in real time. The humidity monitoring unit has a built-in humidity sensor to ensure accurate collection of humidity data for the environment in which each specimen is located. The acquired humidity data is also uploaded to the IoT platform via a wireless communication module, achieving synchronous recording with the temperature data. This prevents errors in specimen temperature monitoring due to humidity fluctuations, thus obtaining the humidity data corresponding to each pathological RFID-tagged specimen. Meanwhile, the temperature data obtained from the corresponding temperature monitoring unit is calibrated based on the humidity data obtained from the humidity monitoring unit. Using a preset calibration algorithm, the real-time humidity data and temperature data are compared to generate calibrated temperature data. The calibration process involves analyzing the nonlinear effect of humidity on temperature and adjusting it using a mathematical model to ensure the accuracy of the temperature data. These calibrated temperature data will be uploaded to the Internet of Things platform to obtain the calibrated temperature data of the pathological specimen. After receiving the calibrated temperature data of pathological specimens through an IoT platform, the system compares it with the pre-identified storage temperature standard for the specimens corresponding to the RFID tags. If the calibrated temperature data matches the storage standard, the system continues to monitor the storage cabinet temperature in real time. If the calibrated temperature data is greater than or less than the storage standard range, it is automatically identified as an abnormal storage temperature. Then, the IoT platform automatically performs anomaly response control analysis upon detecting the abnormal storage temperature, generating a corresponding abnormal control command for the pathological specimen storage temperature. This command is transmitted to the adjustment and control unit within the thermostat, and the command may include adjusting the temperature range, issuing an alarm, or activating the backup cooling system. The adjustment and control unit immediately adjusts according to the received control command to ensure that the pathological specimens are stored under suitable conditions. This process achieves automated management of the pathological specimen storage environment, enhances the real-time monitoring and control capabilities of storage conditions, and maximizes the safety and effectiveness of the specimens. Ultimately, it executes the automatic adjustment and management of the pathological specimen storage conditions corresponding to the adjustment and control unit within the thermostat.

[0023] Step S3: Use a video recognition system to monitor the real-time status of the corresponding pathological RFID-tagged specimens in the pathological specimen storage cabinet to obtain real-time video image frames of the pathological specimens; perform specimen status decay analysis on the corresponding pathological RFID-tagged specimens in the pathological specimen storage cabinet based on the specimen sampling time and specimen storage conditions to obtain the ideal change state of normal decay of the pathological specimens; perform specimen status matching anomaly response alarm on the real-time status video image frames of the pathological specimens based on the ideal change state of normal decay of the pathological specimens to generate an abnormal alarm signal for the change state of the pathological specimens. In this embodiment of the invention, a video recognition system configured in the pathological specimen storage cabinet is used to monitor the status of the corresponding pathological RFID tag specimens in the storage cabinet in real time. The system mainly consists of a high-definition camera, which continuously records video image frames corresponding to the status of the pathological specimens and transmits the video image frames to the central processing unit in real time to generate video image frames of the real-time status of the pathological specimens. These image frames include the appearance, position, and status changes of the specimens, thereby obtaining video image frames of the real-time status of the pathological specimens. This method enhances the detail contrast of real-time video images of pathological specimens obtained from previous real-time monitoring using image processing algorithms. Specifically, image processing tools such as OpenCV are used to preprocess the video frames, including denoising, sharpening, and contrast enhancement. The enhanced video images are then analyzed for specimen status across different time periods. By setting time intervals, the video images are divided into multiple time segments. Within each time segment, machine learning algorithms (such as convolutional neural networks) are used to classify the enhanced images and identify the real-time status of the specimens. The resulting analysis report records the real-time status of the pathological specimens within each time segment. Furthermore, by combining the previously recorded specimen sampling time and storage conditions, a state decay analysis is performed on the corresponding pathological RFID-tagged specimens in the storage cabinet. This involves collecting sampling time data and environmental monitoring data (such as temperature, humidity, and light intensity) for each specimen, integrating this data using statistical analysis methods, and combining it with the specimen decay index calculation method to analyze the decay trend of the specimens under different conditions, thereby obtaining the ideal state of normal decay of the pathological specimens. Then, by combining the ideal change state of normal decay of pathological specimens obtained from previous analysis, the real-time state of pathological specimens in each time period is matched and analyzed. Specifically, the real-time state of each time period is compared with the ideal change state, and a threshold is set to identify abnormal changes. Once the specimen state is found to deviate from the normal range, an alarm mechanism is immediately triggered to generate an abnormal change alarm signal for the pathological specimen state. This signal is notified to laboratory personnel through the Internet of Things platform to ensure that abnormal specimen situations can be handled in a timely manner, and finally, an abnormal change alarm signal for the pathological specimen state is generated.

[0024] Step S4: Apply the abnormal status alarm signal of the pathological specimen to the Internet of Things platform to send abnormal pathological specimen alarm information and automatically notify the abnormal status of the pathological specimen.

[0025] In this embodiment of the invention, an abnormal pathological specimen status alarm signal generated by a previous response is transmitted and applied to an IoT platform. Upon receiving the signal, the platform automatically sends abnormal pathological specimen alarm information to the devices of relevant management personnel, ensuring rapid information transmission. This process is completed through a set automatic notification system. Management personnel can respond and handle the received alarms in a timely manner. The IoT platform also records detailed information of the alarm events for subsequent analysis and auditing, ensuring transparency and traceability in the pathological specimen management process.

[0026] Furthermore, step S1 includes the following steps: Step S11: Obtain pathological specimen samples; Step S12: Perform surface impurity pretreatment on the pathological specimen samples to obtain standardized pretreated specimen samples; Step S13: Based on the specimen type corresponding to the standardized pre-treated specimen samples, design the internal environment control of the closed injection molding machine with built-in ventilation system and gas purification and filtration system to generate a closed injection molding internal environment control setting report; activate the ventilation system and gas purification and filtration system according to the specimen injection molding environment parameters in the closed injection molding internal environment control setting report to perform specimen injection molding and sealing treatment on the corresponding standardized pre-treated specimen samples to obtain pathological injection-molded specimens; Step S14: Store the pathological injection-molded specimens in a pathological specimen storage cabinet with a built-in constant temperature control device, video recognition system and Internet of Things platform, and use RFID technology to identify and mark the pathological injection-molded specimens in the pathological specimen storage cabinet to obtain pathological RFID-tagged specimens. Step S15: Use an RFID reader / writer fixed on the pathological specimen storage cabinet to automatically identify the pathological RFID-tagged specimens and transmit the corresponding RFID automatic identification information to the Internet of Things platform. The RFID automatic identification information includes the specimen sampling time, specimen storage conditions, and specimen type.

[0027] As an embodiment of the present invention, reference is made to... Figure 2 As shown, Figure 1 A detailed flowchart of step S1 is shown below. In this embodiment, step S1 includes the following steps: Step S11: Obtain pathological specimen samples; In this embodiment of the invention, the required tissue sample is extracted from the patient using a precision biopsy needle. The sample is then immediately placed in a pre-prepared saline solution or other preservative solution to maintain its biological activity, ultimately yielding a pathological specimen sample.

[0028] Step S12: Perform surface impurity pretreatment on the pathological specimen samples to obtain standardized pretreated specimen samples; In this embodiment of the invention, the previously extracted pathological specimen samples are pretreated to remove surface impurities. This is achieved by gently wiping the sample surface with sterile gauze to remove possible blood, cell debris, and other impurities. The treated samples are then placed in a sterile specimen container, and the container is labeled with sample information to ensure traceability in subsequent processing. This process ensures that the obtained samples meet the standardized requirements for subsequent analysis and operation, ultimately resulting in standardized pretreated specimen samples.

[0029] Step S13: Based on the specimen type corresponding to the standardized pre-treated specimen samples, design the internal environment control of the closed injection molding machine with built-in ventilation system and gas purification and filtration system to generate a closed injection molding internal environment control setting report; activate the ventilation system and gas purification and filtration system according to the specimen injection molding environment parameters in the closed injection molding internal environment control setting report to perform specimen injection molding and sealing treatment on the corresponding standardized pre-treated specimen samples to obtain pathological injection-molded specimens; In this embodiment of the invention, standardized pretreated pathological samples are classified to determine their specimen type, such as frozen specimens or routine specimens. Based on the specimen type corresponding to the standardized pretreated specimen samples, environmental operating parameters of the built-in ventilation system and gas purification and filtration system are designed. For example, for samples requiring a low-oxygen environment, the control system is set to reduce the oxygen concentration inside the machine to a specific range, while simultaneously activating the gas purification filter to ensure that external pollutants do not affect the quality of the specimen. A detailed internal environment control setting report is generated, listing the specific temperature, humidity, and gas composition control parameters for the corresponding specimen type, thereby generating a closed injection molding internal environment control setting report. Simultaneously, by combining the previously designed closed injection molding internal environment control setting report, the relevant systems of the closed injection molding machine are activated. Based on the parameters in the report, the ventilation system and gas purification and filtration system are adjusted to the set state to ensure that the internal environment of the machine meets the expected standards. Standardized pre-treated specimen samples are then placed into the injection molding machine for sealing. At this time, the injection molding machine uses heating and pressing to combine biological materials with specific sealing materials to form stable pathological injection-molded specimens. The entire process must be carried out in a strictly controlled environment to ensure that the biological characteristics of the specimens are effectively preserved, ultimately resulting in pathological injection-molded specimens.

[0030] Step S14: Store the pathological injection-molded specimens in a pathological specimen storage cabinet with a built-in constant temperature control device, video recognition system and Internet of Things platform, and use RFID technology to identify and mark the pathological injection-molded specimens in the pathological specimen storage cabinet to obtain pathological RFID-tagged specimens. In this embodiment of the invention, the specimens obtained after injection molding and sealing are stored in a dedicated pathological specimen storage cabinet. The cabinet is equipped with a built-in constant temperature control device to maintain a suitable storage temperature. At the same time, the storage cabinet is equipped with a video recognition system to monitor the changes in the storage status of the specimens in real time. It is also equipped with a corresponding Internet of Things platform to transmit the monitored data in real time and perform corresponding anomaly response management. Furthermore, RFID technology is used to affix RFID tags to each specimen in the pathological specimen storage cabinet. The tags store the basic information of the specimen and the storage conditions. This process ensures that all specimens remain traceable and secure during storage, ultimately resulting in pathological RFID-tagged specimens.

[0031] Step S15: Use an RFID reader / writer fixed on the pathological specimen storage cabinet to automatically identify the pathological RFID-tagged specimens and transmit the corresponding RFID automatic identification information to the Internet of Things platform. The RFID automatic identification information includes the specimen sampling time, specimen storage conditions, and specimen type.

[0032] In this embodiment of the invention, a fixed RFID reader is used in the pathological specimen storage cabinet to automatically identify the RFID tags on each pathological RFID-tagged specimen. When a specimen is stored or retrieved, the RFID reader quickly reads the tag information, including the specimen sampling time, storage conditions, and specimen type. The identification information is transmitted in real time through an Internet of Things platform to ensure accurate recording and timely updates of the data. This automated management of information not only improves work efficiency but also reduces errors from manual operation, ensuring the intelligent and systematic management of pathological specimens. Ultimately, the corresponding RFID automatic identification information is obtained, including the specimen sampling time, specimen storage conditions, and specimen type.

[0033] Furthermore, step S2 includes the following steps: Step S21: Use the temperature monitoring unit in the constant temperature control device to monitor the temperature of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time, so as to obtain the temperature data of the pathological RFID tag specimens. Step S22: Use the humidity monitoring unit in the constant temperature control device to monitor the humidity of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time, so as to obtain the humidity data of the pathological RFID tag specimens. Step S23: Based on the humidity data corresponding to the pathological RFID tag specimen, perform specimen temperature calibration on the temperature data corresponding to the pathological RFID tag specimen to obtain pathological specimen calibration temperature data and upload it to the Internet of Things platform; Step S24: Use the IoT platform to compare and judge the specimen temperature of the pathological specimen storage temperature standard and the pathological specimen calibration temperature data within the specimen storage conditions. If the pathological specimen calibration temperature data is equal to the pathological specimen storage temperature standard, continue to monitor the storage temperature of the storage cabinet corresponding to the calibrated pathological specimen in real time; if the pathological specimen calibration temperature data is greater than or less than the pathological specimen storage temperature standard, determine the pathological specimen calibration temperature data as an abnormal storage temperature. Step S25: Utilize the Internet of Things platform to perform abnormal response control analysis on the abnormal storage temperature to generate abnormal control instructions for pathological specimen storage temperature; apply the abnormal control instructions for pathological specimen storage temperature to the regulating control unit in the constant temperature regulating device to perform abnormal temperature regulation management, so as to execute the automatic regulation management of pathological specimen storage conditions corresponding to the regulating control unit in the constant temperature regulating device.

[0034] As an embodiment of the present invention, reference is made to... Figure 3 As shown, Figure 1 A detailed flowchart of step S2 is shown below. In this embodiment, step S2 includes the following steps: Step S21: Use the temperature monitoring unit in the constant temperature control device to monitor the temperature of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time, so as to obtain the temperature data of the pathological RFID tag specimens. In this embodiment of the invention, the temperature monitoring unit within the constant temperature control device is used to monitor the storage temperature of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time. This allows for the acquisition of temperature data for each pathological RFID tag specimen in the storage cabinet in real time. The data is uploaded to the Internet of Things platform via a wireless communication module, forming continuous temperature monitoring records. These records provide a basis for subsequent data analysis to ensure that pathological specimens are stored within a suitable temperature range, maintaining the integrity and validity of the specimens, and ultimately obtaining the temperature data corresponding to the pathological RFID tag specimens.

[0035] Step S22: Use the humidity monitoring unit in the constant temperature control device to monitor the humidity of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time, so as to obtain the humidity data of the pathological RFID tag specimens. In this embodiment of the invention, the humidity of the corresponding pathological RFID tag specimens is monitored in real time by using a humidity monitoring unit within a constant temperature control device. The humidity monitoring unit has a built-in humidity sensor to ensure that the humidity data of the environment in which each specimen is located is accurately collected. The acquired humidity data is also uploaded to the Internet of Things platform via a wireless communication module to achieve synchronous recording with temperature data, so as to prevent errors in specimen temperature monitoring due to humidity fluctuations. Finally, the humidity data corresponding to the pathological RFID tag specimens is obtained.

[0036] Step S23: Based on the humidity data corresponding to the pathological RFID tag specimen, perform specimen temperature calibration on the temperature data corresponding to the pathological RFID tag specimen to obtain pathological specimen calibration temperature data and upload it to the Internet of Things platform; In this embodiment of the invention, the temperature data obtained by the corresponding temperature monitoring unit is calibrated based on the humidity data obtained from the humidity monitoring unit. A preset calibration algorithm is used to compare the real-time humidity data with the temperature data to generate calibrated temperature data. The calibration process involves analyzing the nonlinear effect of humidity on temperature and adjusting it using a mathematical model to ensure the accuracy of the temperature data. These calibrated temperature data are uploaded to the Internet of Things platform to form a complete dataset of the specimen storage environment, and finally, the calibrated temperature data of the pathological specimen is obtained.

[0037] Step S24: Use the IoT platform to compare and judge the specimen temperature of the pathological specimen storage temperature standard and the pathological specimen calibration temperature data within the specimen storage conditions. If the pathological specimen calibration temperature data is equal to the pathological specimen storage temperature standard, continue to monitor the storage temperature of the storage cabinet corresponding to the calibrated pathological specimen in real time; if the pathological specimen calibration temperature data is greater than or less than the pathological specimen storage temperature standard, determine the pathological specimen calibration temperature data as an abnormal storage temperature. In this embodiment of the invention, after receiving the calibrated temperature data of the pathological specimen through the Internet of Things platform, it is compared with the pre-identified storage standard of the pathological specimen temperature within the storage conditions corresponding to the RFID tag. If the calibrated temperature data is consistent with the storage standard, the temperature of the storage cabinet corresponding to the specimen continues to be monitored in real time to ensure the stability of the environmental conditions. If the calibrated temperature data is greater than or less than the range of the storage standard, it is automatically determined to be an abnormal storage temperature, the abnormal situation is recorded, and subsequent processing is triggered. In this way, potential abnormal storage temperature situations can be detected and responded to in a timely manner to ensure the safety of the specimen.

[0038] Step S25: Utilize the Internet of Things platform to perform abnormal response control analysis on the abnormal storage temperature to generate abnormal control instructions for pathological specimen storage temperature; apply the abnormal control instructions for pathological specimen storage temperature to the regulating control unit in the constant temperature regulating device to perform abnormal temperature regulation management, so as to execute the automatic regulation management of pathological specimen storage conditions corresponding to the regulating control unit in the constant temperature regulating device.

[0039] In this embodiment of the invention, when the IoT platform identifies an abnormal storage temperature, it automatically performs anomaly response control analysis and generates a corresponding abnormal pathological specimen storage temperature control command. This command is transmitted to the adjustment and control unit within the constant temperature regulating device. The command includes adjusting the temperature range, issuing an alarm, or activating the backup cooling system. The adjustment and control unit immediately adjusts according to the received control command to ensure that the pathological specimen is stored under suitable conditions. This process realizes automated management of the pathological specimen storage environment, enhances the real-time monitoring and control capabilities of storage conditions, and maximizes the safety and effectiveness of the specimen. Finally, it executes the automatic adjustment and management of the pathological specimen storage conditions corresponding to the adjustment and control unit within the constant temperature regulating device.

[0040] Furthermore, step S23 includes the following steps: Step S231: Perform time-series synchronization processing on the temperature and humidity data corresponding to the pathological RFID tag specimens to obtain the pathological specimen temperature and humidity data under the same time-series change dimension; In this embodiment of the invention, the temperature and humidity data corresponding to the pathological RFID tag specimens obtained from previous real-time monitoring are synchronized using timestamps. This process integrates the temperature and humidity data onto the same time axis using a unified time format, ensuring that the temperature and humidity values ​​can be accessed simultaneously at the same time point. Data processing tools (such as Python's Pandas library) are used to perform data frame operations to ensure that all data points can be arranged in chronological order so that subsequent analysis can be performed under the same temporal change dimension, ultimately obtaining the pathological specimen temperature data and pathological specimen humidity data under the same temporal change dimension.

[0041] Step S232: Perform baseline identification and analysis of humidity changes in pathological specimens to obtain the time-series baseline of humidity changes in pathological specimens; In this embodiment of the invention, a baseline identification analysis of humidity changes is performed on the humidity data after time synchronization. Signal processing techniques, such as moving average or wavelet transform, are used to smooth the humidity data to remove short-term fluctuations and noise. During the analysis, the moving average of the humidity data is first calculated to determine the range of the baseline. Then, the standard deviation or other statistical methods are used to identify significant change points. This process generates a humidity time-series change baseline, providing a stable reference baseline for subsequent data analysis. The identification of the humidity change baseline ensures that subsequent analysis can effectively distinguish between normal and abnormal changes, and finally, the humidity time-series change baseline of the pathological specimen is obtained.

[0042] Step S233: Based on the baseline of the time-series change in the humidity of pathological specimens, perform temperature and humidity interaction analysis on the temperature data of pathological specimens under the same time-series change dimension to obtain the nonlinear interaction relationship between the humidity change and temperature of pathological specimens. In this embodiment of the invention, the interaction between humidity and temperature is analyzed by combining the previously generated baseline of humidity variation in pathological specimens with the temperature data of pathological specimens under the same time-series variation dimension. This step uses regression analysis or machine learning algorithms to evaluate the nonlinear relationship between humidity change and temperature. Specifically, the baseline of humidity change is used as the independent variable and the temperature data is used as the dependent variable. A model is established using methods such as multinomial regression or support vector machine. By fitting the model, the correlation coefficient between humidity and temperature is calculated, and the corresponding nonlinear influence relationship is revealed. Finally, the nonlinear interaction relationship between humidity change and temperature of pathological specimens is obtained.

[0043] Step S234: Based on the nonlinear interaction between pathological specimen humidity change and temperature, conduct humidity impact assessment analysis on pathological specimen temperature data and pathological specimen humidity data to obtain the specimen temperature interaction factor corresponding to pathological specimen humidity change. In this embodiment of the invention, the influence of humidity on the corresponding pathological specimen temperature data and humidity data is assessed by combining the nonlinear interaction relationship between humidity changes and temperature obtained from previous analysis. Specifically, the humidity change data and temperature data are input into the influence assessment model to calculate the interaction factor between humidity and temperature changes. Regression analysis or sensitivity analysis is then used to determine the specific degree of influence of humidity changes on temperature changes and generate a detailed report. This analysis provides a reference for subsequent management decisions, enabling the implementation of corresponding temperature control measures for different humidity levels during the preservation of pathological specimens, ultimately yielding the specimen temperature interaction factor corresponding to the humidity changes in pathological specimens.

[0044] Step S235: Based on the specimen temperature interaction factor corresponding to the humidity change of the pathological specimen, perform specimen temperature calibration on the temperature data corresponding to the pathological RFID tag specimen to obtain the pathological specimen calibration temperature data and upload it to the Internet of Things platform.

[0045] In this embodiment of the invention, the temperature data corresponding to the pathological RFID tag specimen is calibrated based on the specimen temperature interaction influencing factor corresponding to the humidity change of the pathological specimen obtained by previous evaluation and analysis. This process uses a determined influencing factor to adjust the original temperature data and generate calibrated temperature data. During the calibration process, a preset formula is used to apply the influencing factor to the original temperature value to improve the accuracy of the temperature data. The calibrated temperature data is uploaded to the Internet of Things platform to achieve real-time monitoring and data storage. This process ensures that the pathological specimen is always in the best environmental conditions during the preservation process, improves the level of intelligence in pathological specimen management, and finally obtains the calibrated temperature data of the pathological specimen.

[0046] Furthermore, step S233 includes the following steps: Short-term fluctuation smoothing was applied to the baseline of temporal changes in the humidity of pathological specimens to obtain a smoothed baseline of stable changes in the humidity of pathological specimens. In this embodiment of the invention, the short-term fluctuations of the humidity time-series change baseline of the previously analyzed pathological specimens are smoothed by using the moving average method or the exponential smoothing method. In specific implementation, a fixed time window is set, and the average value of the humidity value within the window is calculated to eliminate the random fluctuations of the humidity time-series change baseline in the short term, so as to provide a relatively stable humidity reference and finally obtain a smoothed baseline of stable humidity change of the pathological specimens.

[0047] Preferably, the smoothed baseline of stable changes in the humidity of pathological specimens and the temperature data of pathological specimens under the same time-series change dimension are divided into time periods to obtain the corresponding baseline of changes in the humidity of pathological specimens and the temperature data of pathological specimens under each time period. In this embodiment of the invention, the humidity stability change smoothing baseline of the pathological specimen obtained by previous smoothing is combined with the temperature data of the pathological specimen under the same time-series change dimension for synchronous segmentation processing. By determining the standard for time segmentation, such as generating a data point every hour or half hour, the humidity data and temperature data are then segmented into time periods according to the set time interval. For each time period, the humidity change baseline and temperature data within that segment are extracted to form the corresponding time series dataset. This process ensures that subsequent analysis can be carried out within the same time frame, enhances the comparability of the data, and finally obtains the corresponding pathological specimen humidity change baseline and pathological specimen temperature data for each time period.

[0048] Preferably, based on the baseline of humidity change of pathological specimens in each time period, a time-segmented nonlinear correlation fitting analysis is performed on the corresponding temperature data of pathological specimens to obtain the nonlinear correlation fitting coefficient between humidity change and temperature of pathological specimens in each time period. In this embodiment of the invention, nonlinear correlation fitting analysis is performed on the baseline humidity change and temperature data in each time period using statistical analysis software (such as Python's Scikit-learn library). The specific steps include selecting a suitable nonlinear model (such as multinomial regression or support vector regression), inputting the humidity change and the corresponding temperature data into the model for training, and calculating the nonlinear correlation fitting coefficients for each time period after fitting. These fitting coefficients reflect the nonlinear relationship between humidity and temperature, and finally obtain the nonlinear correlation fitting coefficients between humidity change and temperature of pathological specimens in each time period.

[0049] Preferably, based on the nonlinear correlation fitting coefficient between the humidity change and temperature of pathological specimens at each time period, an interaction analysis of temperature and humidity changes between the corresponding baseline humidity change and temperature data of pathological specimens is conducted to obtain the nonlinear influence relationship between humidity change and temperature of pathological specimens.

[0050] In this embodiment of the invention, the baseline humidity change and temperature data for each time period are analyzed in depth by combining the nonlinear correlation fitting coefficients between humidity changes and temperature of pathological specimens obtained from previous fitting analysis. This allows for the use of interaction models or other statistical analysis methods to explore the nonlinear influence relationship between humidity changes and temperature. Specifically, by comparing the changes in fitting coefficients in different time periods, the degree and direction of the influence of humidity on temperature changes are identified, thereby generating a detailed analysis report that describes the interaction relationship between humidity and temperature, ultimately yielding the nonlinear influence relationship between humidity changes and temperature of pathological specimens.

[0051] Furthermore, step S3 includes the following steps: Step S31: Use a video recognition system to monitor the real-time status of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet, so as to obtain real-time video image frames of the pathological specimen status. In this embodiment of the invention, a video recognition system configured in the pathological specimen storage cabinet is used to monitor the specimen status of the corresponding pathological RFID tag specimens in the storage cabinet in real time. The system mainly consists of a high-definition camera, which continuously records video image frames corresponding to the status of the pathological specimens and transmits the video image frames to the central processing unit in real time to generate video image frames of the real-time status of the pathological specimens. These image frames include the appearance, position, and status changes of the specimens, and finally, the real-time status video image frames of the pathological specimens are obtained.

[0052] Step S32: Perform video image detail contrast enhancement processing on the real-time status video image frames of the pathological specimen to obtain the pathological specimen status video contrast enhancement image frames; In this embodiment of the invention, image processing algorithms are used to enhance the detail contrast of the real-time status video image frames of pathological specimens obtained from previous real-time monitoring. In specific operations, image processing tools such as OpenCV are used to preprocess the video frames, including noise reduction, sharpening, and contrast enhancement. By comparing and analyzing the differences between the current image frame and the previous frame, key details such as color changes and shape deformations are extracted. This process ensures that subtle changes in the specimen status can be clearly identified, and finally, the pathological specimen status video contrast-enhanced image frames are obtained.

[0053] Step S33: Perform time-segmented specimen status recognition and analysis on the video contrast enhancement image frames of the pathological specimen status to obtain the real-time status of the pathological specimen within each time segment. In this embodiment of the invention, the specimen status identification and analysis is performed on the contrast-enhanced image frames of the pathological specimen status video obtained after contrast enhancement. By setting a time interval, the video image frames are divided into multiple time periods. Within each time period, the enhanced image is classified using a machine learning algorithm (such as a convolutional neural network) to identify the real-time status of the specimen. The identification results include features such as specimen integrity, color change, and liquid turbidity. The analysis report generated in this step records the real-time status of the pathological specimen within each time period, and finally obtains the real-time status of the pathological specimen within each time period.

[0054] Step S34: Based on the specimen sampling time and specimen storage conditions, perform specimen state decay analysis on the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet to obtain the ideal change state of normal decay of the pathological specimens. In this embodiment of the invention, the state decay analysis of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet is performed by combining the specimen sampling time and specimen storage conditions obtained from previous identification records. By collecting sampling time data and environmental monitoring data (such as temperature, humidity, light intensity, etc.) for each specimen, and integrating these data by using statistical analysis methods, combined with the specimen decay index calculation method, the decay trend of the specimen under different conditions is analyzed. The generated analysis results provide a quantitative basis for the ideal change state of normal decay of pathological specimens, and finally obtain the ideal change state of normal decay of pathological specimens.

[0055] Step S35: Based on the ideal change state of normal decay of the pathological specimen, perform specimen status matching and abnormal response alarm for the real-time status of the pathological specimen within each time period range to generate an abnormal alarm signal for the change state of the pathological specimen.

[0056] In this embodiment of the invention, the real-time status of the pathological specimen in each time period is matched and analyzed by combining the ideal change state of normal decay of the pathological specimen obtained by previous analysis. Specifically, the real-time status of each time period is compared with the ideal change state, and a threshold is set to identify abnormal changes. Once the specimen status is found to deviate from the normal range, an alarm mechanism is immediately triggered to generate an abnormal change state alarm signal for the pathological specimen. This signal is notified to laboratory personnel through the Internet of Things platform to ensure that abnormal specimen situations can be handled in a timely manner, and finally, an abnormal change state alarm signal for the pathological specimen is generated.

[0057] Furthermore, step S34 includes the following steps: Step S341: Based on the specimen sampling time, evaluate the impact of sampling time on the specimen status of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet, and obtain the specimen status impact factor of storage sampling time; In this embodiment of the invention, the impact of the sampling time obtained from previous RFID tag identification records on the specimen status of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet is evaluated and analyzed. By using specific evaluation and statistical methods to detect and evaluate the corresponding pathological RFID tag specimens, the specific degree of influence of the corresponding sampling time on subsequent specimen status changes is assessed. Based on data analysis, the specific influence factor of sampling time on specimen status is calculated, and finally the specimen status influence factor of storage sampling time is obtained.

[0058] Step S342: Based on the specimen storage conditions, evaluate the impact of storage conditions on the specimen status of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet, and obtain the pathological specimen status impact factors corresponding to each storage condition, wherein each storage condition includes temperature, humidity and light intensity. In this embodiment of the invention, the impact of the storage conditions obtained from previous identification records on the specimen status of corresponding pathological RFID-tagged specimens in the pathological specimen storage cabinet is evaluated and analyzed. Environmental monitoring equipment (such as temperature sensors, humidity sensors, and light intensity sensors) is used to continuously record the temperature, humidity, and light intensity in the storage cabinet. These data are correlated with the specimen information recorded by the RFID tags. The physical and chemical changes of the specimens under different storage conditions are tested through the standard operating procedures in the storage cabinet. Regression analysis is used to obtain the influence factors of the corresponding storage conditions on the status of the pathological specimens. These factors can be used to quantitatively evaluate the specific impact of storage conditions on the preservation of specimens. Finally, the influence factors of the pathological specimen status corresponding to each storage condition are obtained, where the storage conditions include temperature, humidity, and light intensity.

[0059] Step S343: Based on the storage sampling time specimen state influence factor and the pathological specimen state influence factor corresponding to each storage condition, use the pathological specimen state decay index calculation formula to calculate the specimen state decay of the corresponding pathological RFID tag specimen in the pathological specimen storage cabinet, and obtain the pathological specimen change state decay index. In this embodiment of the invention, a suitable formula for calculating the state decay index of pathological specimens is constructed by combining time variable parameters, initial state measurement values ​​of specimens, pathological specimen state decay influence coefficients, storage sampling duration specimen state influence factors, specimen sampling time, temperature, humidity, light intensity, corresponding pathological specimen state influence factors, and related parameters. The formula is used to calculate the state decay of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet, so as to quantitatively calculate the state decay index of the pathological RFID tag specimens in the storage cabinet. This calculation can be implemented using data processing software (such as Excel or professional statistical software). The analysis results will show the shelf life and decay degree of the specimen under the current conditions, and finally obtain the state decay index of the pathological specimens.

[0060] Step S344: Based on the decay index of the pathological specimen change state, perform normal decay change identification and analysis on the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet to obtain the ideal normal decay change state of the pathological specimen.

[0061] In this embodiment of the invention, the decay index of the pathological specimen change state obtained by previous quantitative calculation is used to identify and analyze the normal decay process of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet. The decay index is processed by using statistical analysis software, and a threshold is set to distinguish between normal decay and abnormal decay. During the analysis, the decay index of different batches of specimens is compared to draw a state change curve to identify the ideal change state and critical state of the specimen. This process can also be combined with machine learning algorithms to conduct in-depth analysis of the data, identify potential decay change processes, and finally obtain the ideal change state of normal decay of the pathological specimen.

[0062] Furthermore, the formula for calculating the pathological specimen state decay index in step S343 is as follows: ; In the formula, In time The decay index of the pathological specimen at the site. For time-varying parameters, This refers to the initial state measurement value of the specimen corresponding to the pathological RFID tag specimen. The coefficient representing the influence of the decay of the pathological specimen's condition. To store the sampling duration and the influence factors of the specimen state, For the time of specimen sampling, The factors affecting the condition of pathological specimens corresponding to temperature. For temperature, Humidity is a factor affecting the condition of pathological specimens. For humidity, The factors influencing the state of pathological specimens are light intensity. Light intensity, This is the correction factor for the decay index of pathological specimen changes.

[0063] This invention, through the use of a specific mathematical model and verification, derives a formula for calculating the state decay index of pathological specimens. This formula is used to calculate the state decay of corresponding RFID-tagged pathological specimens within a pathological specimen storage cabinet. It transforms the state decay of a specimen into an index, allowing for numerical assessment of state changes. This quantification makes comparisons between different specimens more intuitive and reliable. The formula considers not only time factors (sampling duration) but also the influence of storage conditions (temperature, humidity, light intensity), comprehensively reflecting the environmental impact on the state of pathological specimens. This multi-dimensional analysis method improves the accuracy of the assessment. By using time as a variable, the formula can be used to dynamically monitor changes in specimen state over time, helping researchers understand the state decay of specimens in real time and take timely measures to protect them. Furthermore, by analyzing the influencing factors corresponding to various storage conditions, optimization suggestions can be provided to laboratories to improve the storage conditions of pathological specimens, extending their shelf life and reliability. This calculation formula can serve as the basis for developing standardized procedures for specimen storage and management, providing a scientific basis for medical institutions to improve the management level of pathological specimens. Furthermore, the correction factor in this formula provides flexibility in the calculation, allowing adjustments to be made based on specific circumstances in practical applications to more closely approximate actual decay patterns. In summary, this formula fully considers the time... The decay index of the pathological specimen at the site Time variable parameter Initial state measurement value of the specimen corresponding to the pathological RFID tag specimen The influence coefficient of pathological specimen state decay Storage sampling duration and specimen status influence factors Specimen sampling time Factors affecting the state of pathological specimens corresponding to temperature ,temperature Humidity-related factors affecting the condition of pathological specimens ,humidity Factors affecting the state of pathological specimens corresponding to light intensity Light intensity Correction factor for the decay index of pathological specimen change state According to the time The decay index of the pathological specimen at the site The interrelationships between the above parameters constitute a functional relationship. This formula can calculate the specimen state decay of corresponding pathological RFID-tagged specimens in the pathological specimen storage cabinet. Simultaneously, it uses a correction coefficient for the pathological specimen state decay index. The introduction of this factor allows for adjustments based on errors that occur during the calculation process, thereby improving the accuracy and applicability of the formula for calculating the decay index of pathological specimens.

[0064] Furthermore, step S35 includes the following steps: Step S351: Based on the real-time status of the pathological specimen within each time period, perform time period status synchronization matching and division of the ideal change status of the normal decay of the pathological specimen, so as to obtain the real-time status of the pathological specimen and the ideal normal status of the pathological specimen within the same time period. In this embodiment of the invention, the normal decay ideal change state of the corresponding pathological specimen is synchronously matched and divided into time periods by combining the real-time status of the pathological specimen corresponding to each time period obtained in the previous division. By analyzing historical data and ideal state change curves, the normal change range of each time period is determined. Then, by using data analysis tools, such as the Pandas library in Python, the real-time status of the pathological specimen and its corresponding normal ideal state within the same time period are divided and generated to form a standardized state comparison benchmark. Finally, the real-time status of the pathological specimen and the normal ideal state of the pathological specimen within the same time period are obtained.

[0065] Step S352: Based on the normal ideal state of the pathological specimen within the same time period, identify and judge the real-time state of the corresponding pathological specimen. If the identification and judgment shows that the real-time state of the pathological specimen within the corresponding time period matches the normal ideal state of the pathological specimen, continue to identify and judge the next time period. If the identification and judgment shows that the real-time state of the pathological specimen within the corresponding time period does not match the normal ideal state of the pathological specimen, perform abnormal response alarm processing on the real-time state of the pathological specimen within that time period to generate an abnormal alarm signal for the change in the state of the pathological specimen.

[0066] In this embodiment of the invention, the real-time status of the corresponding pathological specimens is identified and judged based on the previously divided ideal normal state of the pathological specimens within the same time period. This process uses a designed intelligent algorithm to compare the real-time data with the ideal state to determine their consistency. During the judgment process, if the real-time status of the pathological specimen within the corresponding time period is found to be consistent with the ideal normal state of the pathological specimen, the monitoring of the next time period continues; if they are inconsistent, an abnormal response mechanism is immediately triggered to generate an alarm signal for abnormal specimen status. This alarm signal is sent to the relevant management terminal through the Internet of Things communication module to ensure that laboratory personnel can receive and handle abnormal situations in a timely manner. This process, through the configured alarm rules and thresholds, ensures rapid response to potential problems, reduces the risk of specimen damage, and ultimately generates an alarm signal for abnormal status of pathological specimen changes.

[0067] Furthermore, for implementing the IoT-based intelligent management method for pathological specimens as described above, the IoT-based intelligent management system for pathological specimens includes: The pathological specimen RFID identification and tagging module is used to acquire pathological specimen samples and perform specimen injection molding and sealing treatment on the samples using a closed injection molding machine with a built-in ventilation system and gas purification and filtration system to obtain pathological injection-molded specimens. These specimens are then stored in a pathological specimen storage cabinet equipped with a built-in constant temperature control device, video recognition system, and IoT platform. The constant temperature control device includes a temperature monitoring unit, a humidity monitoring unit, and a control unit. RFID technology is used to identify and tag the pathological injection-molded specimens in the storage cabinet, resulting in pathological RFID-tagged specimens. An RFID reader / writer fixed to the storage cabinet automatically identifies the RFID-tagged specimens and transmits the corresponding RFID automatic identification information to the IoT platform. This RFID automatic identification information includes the specimen sampling time, specimen storage conditions, and specimen type. The pathological specimen storage temperature anomaly control module is used to monitor the temperature and humidity data of the pathological specimens with RFID tags in the storage cabinet in real time using the temperature monitoring unit and humidity monitoring unit in the constant temperature control device. Based on the humidity data, the module calibrates the temperature data of the specimens to obtain the calibrated temperature data of the pathological specimens and uploads it to the Internet of Things (IoT) platform. The IoT platform is used to manage the abnormal response of specimen storage conditions and the calibrated temperature data of pathological specimens, and generate abnormal control commands for pathological specimen storage temperature to execute the automatic adjustment and management of the pathological specimen storage conditions corresponding to the adjustment and control unit in the constant temperature control device. The pathological specimen status abnormality alarm module is used to monitor the status of corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time using a video recognition system to obtain real-time video image frames of the pathological specimen status; to perform specimen status decay analysis on the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet based on the specimen sampling time and specimen storage conditions to obtain the ideal change state of normal decay of the pathological specimen; and to generate an alarm signal for abnormal change of pathological specimen status by matching the specimen status abnormality to the real-time video image frames of the pathological specimen based on the ideal change state of normal decay of the pathological specimen. The pathological specimen status abnormality notification management module is used to send pathological specimen abnormality alarm signals to the Internet of Things platform and automatically notify the pathological specimen status abnormality.

[0068] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0069] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. A method for intelligent management of pathological specimens based on the Internet of Things, characterized in that, Includes the following steps: Step S1: Obtain pathological specimen samples and use a closed injection molding machine with a built-in ventilation system and gas purification filtration system to perform specimen injection molding and sealing treatment to obtain pathological injection-molded specimens; store the pathological injection-molded specimens in a pathological specimen storage cabinet with a built-in constant temperature control device, video recognition system, and Internet of Things platform. The constant temperature control device includes a temperature monitoring unit, a humidity monitoring unit, and a control unit. RFID technology is used to identify and mark the pathological injection-molded specimens in the pathological specimen storage cabinet to obtain pathological RFID-tagged specimens; use an RFID reader / writer fixed on the pathological specimen storage cabinet to automatically identify the pathological RFID-tagged specimens and transmit the corresponding RFID automatic identification information to the Internet of Things platform. The RFID automatic identification information includes specimen sampling time, specimen storage conditions, and specimen type. Step S2: Use the temperature monitoring unit and humidity monitoring unit in the constant temperature control device to monitor the temperature and humidity data of the pathological specimens with RFID tags in the pathological specimen storage cabinet in real time, and perform specimen temperature calibration based on the humidity data to obtain the pathological specimen calibration temperature data and upload it to the Internet of Things platform. The Internet of Things platform is used to manage abnormal specimen temperature response by monitoring specimen storage conditions and pathological specimen calibration temperature data, and to generate abnormal pathological specimen storage temperature control commands to execute the automatic adjustment and management of pathological specimen storage conditions corresponding to the adjustment and control unit in the constant temperature regulation device. Step S3: Use a video recognition system to monitor the real-time status of the pathological specimens with corresponding RFID tags in the pathological specimen storage cabinet, so as to obtain real-time video image frames of the pathological specimens. Based on the specimen sampling time and specimen storage conditions, the specimen state decay analysis of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet was performed to obtain the ideal change state of normal decay of the pathological specimens. Based on the ideal change state of normal decay of pathological specimens, the real-time status video image frames of pathological specimens are matched with the specimen status to generate abnormal response alarm signals for abnormal changes in the status of pathological specimens. Step S4: Apply the abnormal status alarm signal of the pathological specimen to the Internet of Things platform to send abnormal pathological specimen alarm information and perform automatic notification of abnormal status of pathological specimen.

2. The method for intelligent management of pathological specimens based on the Internet of Things according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Obtain pathological specimen samples; Step S12: Perform surface impurity pretreatment on the pathological specimen samples to obtain standardized pretreated specimen samples; Step S13: Based on the specimen type corresponding to the standardized pre-treated specimen samples, design the internal environment control of the closed injection molding machine with built-in ventilation system and gas purification and filtration system to generate a closed injection molding internal environment control setting report; activate the ventilation system and gas purification and filtration system according to the specimen injection molding environment parameters in the closed injection molding internal environment control setting report to perform specimen injection molding and sealing treatment on the corresponding standardized pre-treated specimen samples to obtain pathological injection-molded specimens; Step S14: Store the pathological injection-molded specimens in a pathological specimen storage cabinet with a built-in constant temperature control device, video recognition system and Internet of Things platform, and use RFID technology to identify and mark the pathological injection-molded specimens in the pathological specimen storage cabinet to obtain pathological RFID-tagged specimens. Step S15: Use an RFID reader / writer fixed on the pathological specimen storage cabinet to automatically identify the pathological RFID-tagged specimens and transmit the corresponding RFID automatic identification information to the Internet of Things platform. The RFID automatic identification information includes the specimen sampling time, specimen storage conditions, and specimen type.

3. The method for intelligent management of pathological specimens based on the Internet of Things according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Use the temperature monitoring unit in the constant temperature control device to monitor the temperature of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time, so as to obtain the temperature data of the pathological RFID tag specimens. Step S22: Use the humidity monitoring unit in the constant temperature control device to monitor the humidity of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time, so as to obtain the humidity data of the pathological RFID tag specimens. Step S23: Based on the humidity data corresponding to the pathological RFID tag specimen, perform specimen temperature calibration on the temperature data corresponding to the pathological RFID tag specimen to obtain pathological specimen calibration temperature data and upload it to the Internet of Things platform; Step S24: Use the IoT platform to compare and judge the specimen temperature of the pathological specimen storage temperature standard and the pathological specimen calibration temperature data within the specimen storage conditions. If the pathological specimen calibration temperature data is equal to the pathological specimen storage temperature standard, continue to monitor the storage temperature of the storage cabinet corresponding to the calibrated pathological specimen in real time; if the pathological specimen calibration temperature data is greater than or less than the pathological specimen storage temperature standard, determine the pathological specimen calibration temperature data as an abnormal storage temperature. Step S25: Utilize the Internet of Things platform to perform abnormal response control analysis on the abnormal storage temperature to generate abnormal control instructions for pathological specimen storage temperature; apply the abnormal control instructions for pathological specimen storage temperature to the regulating control unit in the constant temperature regulating device to perform abnormal temperature regulation management, so as to execute the automatic regulation management of pathological specimen storage conditions corresponding to the regulating control unit in the constant temperature regulating device.

4. The intelligent management method for pathological specimens based on the Internet of Things according to claim 3, characterized in that, Step S23 includes the following steps: Step S231: Perform time-series synchronization processing on the temperature and humidity data corresponding to the pathological RFID tag specimens to obtain the pathological specimen temperature and humidity data under the same time-series change dimension; Step S232: Perform baseline identification and analysis of humidity changes in pathological specimens to obtain the time-series baseline of humidity changes in pathological specimens; Step S233: Based on the baseline of the time-series change in the humidity of pathological specimens, perform temperature and humidity interaction analysis on the temperature data of pathological specimens under the same time-series change dimension to obtain the nonlinear interaction relationship between the humidity change and temperature of pathological specimens. Step S234: Based on the nonlinear interaction between pathological specimen humidity change and temperature, conduct humidity impact assessment analysis on pathological specimen temperature data and pathological specimen humidity data to obtain the specimen temperature interaction factor corresponding to pathological specimen humidity change. Step S235: Based on the specimen temperature interaction factor corresponding to the humidity change of the pathological specimen, perform specimen temperature calibration on the temperature data corresponding to the pathological RFID tag specimen to obtain the pathological specimen calibration temperature data and upload it to the Internet of Things platform.

5. The method for intelligent management of pathological specimens based on the Internet of Things according to claim 4, characterized in that, Step S233 includes the following steps: Short-term fluctuation smoothing was applied to the baseline of temporal changes in the humidity of pathological specimens to obtain a smoothed baseline of stable changes in the humidity of pathological specimens. The smoothed baseline of stable changes in pathological specimen humidity and the temperature data of pathological specimens under the same time-series change dimension are divided into time periods to obtain the corresponding baseline of pathological specimen humidity change and the temperature data of pathological specimens under each time period. Based on the baseline of humidity change of pathological specimens in each time period, nonlinear correlation fitting analysis was performed on the corresponding temperature data of pathological specimens in each time period to obtain the nonlinear correlation fitting coefficient between humidity change and temperature of pathological specimens in each time period. Based on the nonlinear correlation fitting coefficient between the humidity change and temperature of pathological specimens at different time periods, the interaction influence between the corresponding baseline humidity change and temperature data of pathological specimens was analyzed to obtain the nonlinear influence relationship between humidity change and temperature of pathological specimens.

6. The method for intelligent management of pathological specimens based on the Internet of Things according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Use a video recognition system to monitor the real-time status of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet, so as to obtain real-time video image frames of the pathological specimen status. Step S32: Perform video image detail contrast enhancement processing on the real-time status video image frames of the pathological specimen to obtain the pathological specimen status video contrast enhancement image frames; Step S33: Perform time-segmented specimen status recognition and analysis on the video contrast enhancement image frames of the pathological specimen status to obtain the real-time status of the pathological specimen within each time segment. Step S34: Based on the specimen sampling time and specimen storage conditions, perform specimen state decay analysis on the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet to obtain the ideal change state of normal decay of the pathological specimens. Step S35: Based on the ideal change state of normal decay of the pathological specimen, perform specimen status matching and abnormal response alarm for the real-time status of the pathological specimen within each time period range to generate an abnormal alarm signal for the change state of the pathological specimen.

7. The method for intelligent management of pathological specimens based on the Internet of Things according to claim 6, characterized in that, Step S34 includes the following steps: Step S341: Based on the specimen sampling time, evaluate the impact of sampling time on the specimen status of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet, and obtain the specimen status impact factor of storage sampling time; Step S342: Based on the specimen storage conditions, evaluate the impact of storage conditions on the specimen status of the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet, and obtain the pathological specimen status impact factors corresponding to each storage condition, wherein each storage condition includes temperature, humidity and light intensity. Step S343: Based on the storage sampling time specimen state influence factor and the pathological specimen state influence factor corresponding to each storage condition, use the pathological specimen state decay index calculation formula to calculate the specimen state decay of the corresponding pathological RFID tag specimen in the pathological specimen storage cabinet, and obtain the pathological specimen change state decay index. Step S344: Based on the decay index of the pathological specimen change state, perform normal decay change identification and analysis on the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet to obtain the ideal normal decay change state of the pathological specimen.

8. The method for intelligent management of pathological specimens based on the Internet of Things according to claim 7, characterized in that, The specific formula for calculating the pathological specimen state decay index in step S343 is as follows: ； In the formula, In time The decay index of the pathological specimen at the site. For time-varying parameters, This refers to the initial state measurement value of the specimen corresponding to the pathological RFID tag specimen. The coefficient representing the influence of the decay of the pathological specimen's condition. To store the sampling duration and the influence factors of the specimen state, For the time of specimen sampling, The factors affecting the condition of pathological specimens corresponding to temperature. For temperature, Humidity is a factor affecting the condition of pathological specimens. For humidity, The factors influencing the state of pathological specimens are light intensity. Light intensity, This is the correction factor for the decay index of pathological specimen changes.

9. The method for intelligent management of pathological specimens based on the Internet of Things according to claim 6, characterized in that, Step S35 includes the following steps: Step S351: Based on the real-time status of the pathological specimen within each time period, perform time period status synchronization matching and division of the ideal change status of the normal decay of the pathological specimen, so as to obtain the real-time status of the pathological specimen and the ideal normal status of the pathological specimen within the same time period. Step S352: Based on the normal ideal state of the pathological specimen within the same time period, identify and judge the real-time state of the corresponding pathological specimen. If the identification and judgment shows that the real-time state of the pathological specimen within the corresponding time period matches the normal ideal state of the pathological specimen, continue to identify and judge the next time period. If the identification and judgment shows that the real-time state of the pathological specimen within the corresponding time period does not match the normal ideal state of the pathological specimen, perform abnormal response alarm processing on the real-time state of the pathological specimen within that time period to generate an abnormal alarm signal for the change in the state of the pathological specimen.

10. An intelligent management system for pathological specimens based on the Internet of Things, characterized in that, For executing the IoT-based intelligent management method for pathological specimens as described in claim 1, the IoT-based intelligent management system for pathological specimens includes: The pathological specimen RFID identification and tagging module is used to acquire pathological specimen samples and perform specimen injection molding and sealing treatment on the samples using a closed injection molding machine with a built-in ventilation system and gas purification and filtration system to obtain pathological injection-molded specimens. These specimens are then stored in a pathological specimen storage cabinet equipped with a built-in constant temperature control device, video recognition system, and IoT platform. The constant temperature control device includes a temperature monitoring unit, a humidity monitoring unit, and a control unit. RFID technology is used to identify and tag the pathological injection-molded specimens in the storage cabinet, resulting in pathological RFID-tagged specimens. An RFID reader / writer fixed to the storage cabinet automatically identifies the RFID-tagged specimens and transmits the corresponding RFID automatic identification information to the IoT platform. This RFID automatic identification information includes the specimen sampling time, specimen storage conditions, and specimen type. The pathological specimen storage temperature anomaly control module is used to monitor the temperature and humidity data of the pathological specimens with RFID tags in the storage cabinet in real time using the temperature monitoring unit and humidity monitoring unit in the constant temperature control device. Based on the humidity data, the module calibrates the temperature data of the specimens to obtain the calibrated temperature data of the pathological specimens and uploads it to the Internet of Things (IoT) platform. The IoT platform is used to manage the abnormal response of specimen storage conditions and the calibrated temperature data of pathological specimens, and generate abnormal control commands for pathological specimen storage temperature to execute the automatic adjustment and management of the pathological specimen storage conditions corresponding to the adjustment and control unit in the constant temperature control device. The pathological specimen status abnormality alarm module is used to monitor the status of corresponding pathological RFID tag specimens in the pathological specimen storage cabinet in real time using a video recognition system to obtain real-time video image frames of the pathological specimen status; to perform specimen status decay analysis on the corresponding pathological RFID tag specimens in the pathological specimen storage cabinet based on the specimen sampling time and specimen storage conditions to obtain the ideal change state of normal decay of the pathological specimen; and to generate an alarm signal for abnormal change of pathological specimen status by matching the specimen status abnormality to the real-time video image frames of the pathological specimen based on the ideal change state of normal decay of the pathological specimen. The pathological specimen status abnormality notification management module is used to send pathological specimen abnormality alarm signals to the Internet of Things platform and automatically notify the pathological specimen status abnormality.

Images