Information processing method, program, information processing device, and sensing device

Abstract

To provide an information processing method, etc., that can acquire and store time-series sensor data from a sensor installed inside at least one of a plurality of containers for biological materials containing biological materials. [Solution] The information processing method relating to one aspect is characterized by acquiring time-series sensor data obtained during transport from multiple sensors installed inside at least one of a plurality of biological material containers (3, 4) containing biological material, and executing a process to store the acquired time-series sensor data in a storage unit.

Description

【Technical Field】 【0001】 The present invention relates to an information processing method, a program, an information processing apparatus, and a sensing apparatus. 【Background Art】 【0002】 In recent years, the development of technologies related to specimens such as blood has been actively promoted. For example, Patent Document 1 discloses a detection device (specimen container) for detecting information related to a specimen during transportation. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 International Publication No. 2020 / 181375 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 However, the invention according to Patent Document 1 has a problem that it is impossible to acquire and store time-series sensor data from a sensor provided inside one of a plurality of specimen containers that contain a specimen. 【0005】 On one aspect, it is to provide an information processing method or the like capable of acquiring and storing time-series sensor data from a sensor provided inside at least one of a plurality of containers for biological substances such as a plurality of specimen containers that contain a biological substance such as a specimen. 【Means for Solving the Problems】 【0006】 An information processing method according to one aspect is characterized by acquiring time-series sensor data obtained during transportation from a plurality of sensors provided inside at least one of a plurality of containers for biological substances that contain a biological substance, and causing a storage unit to execute a process of storing the acquired time-series sensor data. 【Effects of the Invention】 【0007】 In one respect, it becomes possible to acquire and store time-series sensor data from a sensor installed inside at least one of several containers for biological materials that contain biological materials. [Brief explanation of the drawing] 【0008】 [Figure 1] This is an explanatory diagram illustrating the overview of a system for measuring the degree of impact on samples within containers for biological materials. [Figure 2] This is a block diagram showing an example server configuration. [Figure 3] This is a block diagram showing an example configuration of a carrier terminal. [Figure 4] This is a block diagram showing an example of the configuration of a container for biomaterials, and a perspective view of a container for biomaterials. [Figure 5A] Figure 4 is a perspective view of a container for biological materials, specifically a view taken along the arrow VA. [Figure 5B] Figure 4 is a perspective view of a container for biological materials, taken from the direction of arrow VB. [Figure 6] This is an explanatory diagram showing an example of the record layout for the transport quality database and the sensor data database. [Figure 7] This is an explanatory diagram illustrating the process for evaluating the quality of blood in a container for biological materials. [Figure 8] This is an explanatory diagram regarding the quality evaluation model. [Figure 9] This flowchart shows the processing procedure for evaluating the quality of blood in a container for biological materials. [Figure 10] This is an explanatory diagram regarding the quality evaluation model in Modification Example 1. [Figure 11] This is an explanatory diagram regarding the quality evaluation model in modified example 2. [Figure 12] This is an explanatory diagram illustrating the first input data and the second input data. [Figure 13] This is an explanatory diagram showing an example of outputting quality scores on a chart. [Figure 14]It is an explanatory diagram showing an example of outputting a quality score based on sensor data per unit time on a graph. [Figure 15] It is a flowchart showing a processing procedure when outputting a chart diagram. [Figure 16] It is a flowchart showing a processing procedure when outputting a graph. 【Mode for Carrying Out the Invention】 【0009】 Hereinafter, the present invention will be described in detail based on the drawings showing its embodiments. 【0010】 (Embodiment 1) Embodiment 1 relates to a form of outputting a value related to the quality of conveyance (transportation) based on time-series sensor data obtained from a plurality of sensors provided inside at least one of a plurality of containers for biological substances (specimen tubes) containing biological substances. 【0011】 FIG. 1 is an explanatory diagram showing an overview of a system for measuring the degree of influence on a specimen inside a container for biological substances. The system of the present embodiment includes an information processing device 1, an information processing terminal 2, and a plurality of containers for biological substances. The container for biological substances is a container for containing biological substances such as blood, plasma, blood cells, serum, saliva, urine, cells, tissues, etc. These biological substances may be specimens used for examinations or biological materials used for medical treatments (e.g., regenerative medicine). In the present embodiment and other embodiments and modifications, although specimens are described as examples of biological substances, the same can be implemented in the case of biological materials such as cells and tissues. The container for biological substances includes a container for biological substances 3 provided with a plurality of sensors inside and a container for biological substances 4 not provided with sensors. The sensors include at least two of a temperature sensor located inside the specimen, an inertial sensor, a pressure sensor located inside the specimen, an optical sensor located inside the specimen, and a sensor for detecting the movement of the specimen liquid surface. 【0012】 The information processing device 1, the information processing terminal 2, and the plurality of sensors provided inside the container for biological substances 3 transmit and receive information via a network N such as the Internet. 【0013】 The information processing device 1 is an information processing device that performs processing, storage, transmission, and reception of various information. The information processing device 1 is, for example, a server device, a personal computer, or a general-purpose tablet PC (personal computer), etc. In this embodiment, the information processing device 1 is assumed to be a server device, and hereinafter it will be read as server 1 for simplicity. 【0014】 The information processing terminal 2 is a terminal device for a transporter that receives and displays values and warning information regarding the quality of the specimen during transportation. The transporter is a vendor who transports containers for biological substances. Note that the information processing terminal 2 is not limited to a terminal device for a transporter, and may be, for example, a terminal device for other related parties such as an administrator, a hospital, or the requester of the specimen. The information processing terminal 2 is an information processing device such as a personal computer terminal, a tablet, a smartphone, a mobile phone, or a wearable device such as a smartwatch. Hereinafter, for simplicity, the information processing terminal 2 will be read as transporter terminal 2. 【0015】 As shown in the figure, the biological substance container 3 and the biological substance container 4 are transported by the truck 91. The truck 91 can load a plurality of biological substance storage boxes (containers) 92, and each biological substance storage box 92 is packed with one biological substance container 3 and a plurality of biological substance containers 4. Note that it is not limited to the packing method of the biological substance container 4 described above. For example, each biological substance storage box 92 may be packed with two or more biological substance containers 3 and a plurality of biological substance containers 4. Or, each biological substance storage box 92 may be packed with only a plurality of biological substance containers 3. 【0016】 In addition, in FIG. 1, an example of the truck 91 has been described, but it is not limited to this, and other transportation means such as a car, a motorcycle, a bicycle, a ship, a drone, or an airplane may be used. 【0017】 Clinical specimens can be affected by external physical factors, such as during transport, which can impair their properties. Specifically, changes in temperature, vibration or micro-vibration, pressure fluctuations, turbulence of the liquid level, tipping, or acceleration during transport in containers for biological materials can cause specimen deterioration. For example, in the case of blood, blood cells may be destroyed. Changes in light intensity or pH value can also alter the composition of the specimen. Furthermore, changes in specific gravity can alter the properties of the specimen. Maintaining specimen quality is extremely important in clinical testing, and it is desirable to be able to start testing without deterioration while maintaining the properties immediately after specimen collection. It is also desirable to be able to directly or indirectly detect any changes in properties. 【0018】 Conventionally, the measurements of a device that measures and records temperature and other parameters, which is included in the biological material storage box 92, have been used as an indicator of the conditions during transport. However, this only indicates the physical state of the environment inside the box and has the problem of not being able to output values ​​related to the degree of influence on the specimen inside the biological material container, i.e., values ​​related to the quality of transport. 【0019】 To solve these problems, in this embodiment, the environment inside the biological material container 3 containing the sample is directly monitored using multiple sensors installed inside the container 3. Based on the time-series sensor data obtained from the multiple sensors, values ​​related to the quality of transport can be output using, for example, artificial intelligence (AI), and the quality of sample transport can be evaluated. 【0020】 In this embodiment, Server 1 acquires time-series sensor data obtained during transport from multiple sensors installed inside one of the multiple biological material containers (biological material container 3 and biological material container 4) containing the sample (biological material container 3). Server 1 stores the acquired time-series sensor data in a storage unit. Note that the biological material such as a sample contained in the biological material container 3 on which the sensors are installed may be a pseudo-biological material such as a simulated sample. For example, a simulated sample of human blood could be animal blood other than human blood. Therefore, in this patent application, the term "biological material" includes pseudo-biological materials that imitate biological materials (or have properties similar to biological materials). 【0021】 Server 1 acquires time-series sensor data stored in the memory unit. Server 1 inputs the acquired sensor data into a quality evaluation model that outputs values ​​related to transport quality when sensor data is input, and outputs values ​​related to transport quality. The quality evaluation model will be described later. 【0022】 Figure 2 is a block diagram showing an example configuration of Server 1. Server 1 includes a control unit 11, a storage unit 12, a communication unit 13, a reading unit 14, and a large-capacity storage unit 15. Each component is connected by bus B. 【0023】 The control unit 11 includes an arithmetic processing unit such as a CPU (Central Processing Unit), MPU (Micro-Processing Unit), GPU (Graphics Processing Unit), FPGA (Field Programmable Gate Array), DSP (Digital Signal Processor), or quantum processor. The control unit 11 reads and executes a control program 1P (program product) stored in the storage unit 12, thereby performing various information processing and control processing related to the server 1. 【0024】 Furthermore, the control program 1P can be deployed on a single computer, at a single site, or distributed across multiple sites and run on multiple computers interconnected by a communication network. 【0025】 In Figure 2, the control unit 11 is described as a single processor, but it may be a multi-processor system. Furthermore, the control unit 11 may perform various information processing or control processing on the same processor within the server 1, or it may perform these processes on different processors within the server 1. 【0026】 The storage unit 12 includes memory elements such as RAM (Random Access Memory) and ROM (Read Only Memory), and stores the control program 1P or data necessary for the control unit 11 to execute processing. The storage unit 12 also temporarily stores data necessary for the control unit 11 to execute arithmetic processing. The communication unit 13 is a communication module for performing communication-related processing, and transmits and receives information with the carrier terminal 2, etc., via the network N. 【0027】 The reading unit 14 reads a portable storage medium 1a, including a CD (Compact Disc)-ROM or DVD (Digital Versatile Disc)-ROM. The control unit 11 may read the control program 1P from the portable storage medium 1a via the reading unit 14 and store it in the large-capacity storage unit 15. Alternatively, the control unit 11 may download the control program 1P from another computer via a network N or the like and store it in the large-capacity storage unit 15. Furthermore, the control unit 11 may also read the control program 1P from the semiconductor memory 1b. 【0028】 The large-capacity storage unit 15 includes a recording medium such as an HDD (Hard disk drive) or an SSD (Solid State Drive). The large-capacity storage unit 15 includes a quality evaluation model 151, a transport quality database 152, and a sensor data database 153. 【0029】 The quality evaluation model 151 is an output device (estimator) that outputs values ​​related to the quality of transport based on time-series sensor data obtained during transport from multiple sensors installed inside the biological material container 3, and is a trained model generated by machine learning. The transport quality DB 152 stores the sample collection data. The sensor data DB 153 stores the time-series sensor data during transport and the values ​​related to the quality of transport output from the quality evaluation model 151. 【0030】 In this embodiment, the storage unit 12 and the large-capacity storage unit 15 may be configured as a single storage device. Furthermore, the large-capacity storage unit 15 may be composed of multiple storage devices. Moreover, the large-capacity storage unit 15 may be an external storage device connected to the server 1. 【0031】 Server 1 may perform various information processing and control processes as a single computer, or it may be performed in a distributed manner across multiple computers. Furthermore, Server 1 may be implemented using multiple virtual machines located within a single server, or it may be implemented using a cloud server. 【0032】 Figure 3 is a block diagram showing an example configuration of the carrier terminal 2. The carrier terminal 2 includes a control unit 21, a storage unit 22, a communication unit 23, an input unit 24, and a display unit 25. 【0033】 The control unit 21 includes a processing unit such as a CPU or MPU, and performs various information processing and control processing related to the transporter terminal 2 by reading and executing the control program 2P (program product) stored in the storage unit 22. 【0034】 In Figure 3, the control unit 21 is described as a single processor, but it may be a multi-processor system. Furthermore, the control unit 21 may perform various information processing or control processing using the same processor within the carrier terminal 2, or it may perform these processes using different processors within the carrier terminal 2. 【0035】 The storage unit 22 includes memory elements such as RAM or ROM, and stores the control program 2P or data necessary for the control unit 21 to execute processing. The storage unit 22 also temporarily stores data necessary for the control unit 21 to execute arithmetic processing. 【0036】 The communication unit 23 is a communication module for performing communication-related processing and sends and receives information with the server 1, etc., via the network N. The input unit 24 may be a keyboard, mouse, or a touch panel integrated with the display unit 25. The display unit 25 is a liquid crystal display or an organic EL (electroluminescence) display, etc., and displays various information according to the instructions of the control unit 21. 【0037】 Figure 4 is a block diagram showing an example configuration of the biomaterial container 3 and a perspective view of the biomaterial container. The biomaterial container 3 has the same shape and dimensions as the biomaterial container 4. The biomaterial container 3 has a tube section 41 for containing the sample and a lid section 42 that can be attached to and removed from the tube section 41. The presence of the lid section 42 prevents leakage of liquid samples and prevents contamination of the sample with foreign matter. 【0038】 The lid portion 42 has a roughly cylindrical internal cap portion 43 that is inserted inside the tube portion 41. The perspective view shown in the lower right of Figure 4 shows the container 3 for biological materials with the lid portion 42 fixed in place after a liquid sample has been injected into the tube portion 41. 【0039】 Furthermore, the biological material container 3 includes a control unit 31, a storage unit 32, a communication unit 33, an inertial sensor 34, a probe 35, a pressure sensor 36, a light sensor 37, a temperature sensor 38, a pH meter 39, and a hydrometer 40. The control unit 31, the storage unit 32, and the communication unit 33 are connected to the inertial sensor 34, the probe 35, the pressure sensor 36, the light sensor 37, the temperature sensor 38, the pH meter 39, and the hydrometer 40 via bus B. The control unit 31 receives sensor data from each sensor in real time. 【0040】 To sense environmental factors that may degrade the quality of a sample (e.g., blood) during transport, an inertial sensor 34, a probe 35, a pressure sensor 36, a light sensor 37, a temperature sensor 38, a pH meter 39, and a hydrometer 40 are installed inside the biomaterial container 3. These sensors can be used to monitor various effects on the sample inside the biomaterial container 3 during transport. 【0041】 The control unit 31 includes a processing unit such as a CPU or MPU, and performs various information processing and control processing related to the biological material container 3 by reading and executing the control program 3P (program product) stored in the storage unit 32. 【0042】 The storage unit 32 includes memory elements such as RAM or ROM, and stores control programs 3P or data necessary for the control unit 31 to execute processing. The storage unit 32 also temporarily stores data necessary for the control unit 31 to execute arithmetic processing. The communication unit 33 is a communication module for performing communication-related processing, and transmits and receives sensor data with the server 1, etc., via the network N. 【0043】 The inertial sensor 34 is a sensor for measuring the acceleration or angular velocity of the biological material container 3, and includes an acceleration sensor and a gyroscope sensor. The control unit 31, memory unit 32, communication unit 33 and inertial sensor 34 are embedded in the internal cap 43. 【0044】 The probe 35 is a floating sensor suspended from the internal cap portion 43, and is designed to float on the surface of the sample liquid using buoyancy. The probe 35 is used to measure the position and movement of the sample surface. A sensor element for sensing changes in the liquid level is located at the tip of the probe 35. The probe 35 partially penetrates the sample in the biological material container 3 and senses changes in the liquid level in real time. Depending on the characteristics or measurement accuracy, the probe 35 may penetrate the entire sample. 【0045】 In this embodiment, an example of a floating sensor is described, but it is not limited to this. For example, a sensor capable of detecting the movement of the liquid surface of a liquid sample, such as a capacitive sensor, ultrasonic sensor, laser sensor, or optical sensor, may be used. 【0046】 Figure 5A is a perspective view of the biological material container 3 shown in Figure 4, taken along the VA arrow. Figure 5B is a perspective view of the biological material container 3 shown in Figure 4, taken along the VB arrow. 【0047】 Three roughly U-shaped first holders 441 and three roughly U-shaped second holders 442 are provided on the inner surface of the tube section 41. The second holders 442 are smaller than the first holders 441. The three first holders 441 are evenly distributed at the same height. Above each first holder 441, the second holders 442 are positioned at the same height. 【0048】 The pressure sensor 36 is a sensor for measuring the pressure inside the container 3 for biological materials. The pressure sensor 36 has a first cylindrical portion 361 and a second cylindrical portion 362. The pressure sensor 36 is arranged approximately parallel to the central axis of the tube portion 41. The second cylindrical portion 362 is thinner than the first cylindrical portion 361 and protrudes coaxially from the lower end face of the first cylindrical portion 361. The end of the second cylindrical portion 362 is tapered. 【0049】 The pressure sensor 36 is fixed to the tube portion 41 by a first holder 441 at the boundary between the first cylindrical portion 361 and the second cylindrical portion 362. A pressure sensor cable 363 extends from the upper end face of the first cylindrical portion 361. The pressure sensor cable 363 is connected to electronic components such as a control unit 31 embedded inside the internal cap portion 43. The pressure sensor cable 363 is fixed to the inner surface of the tube portion 41 by a second holder 442 positioned directly above the first holder 441 that fixes the pressure sensor 36. 【0050】 The optical sensor 37 is a sensor for measuring the intensity, color, or other light-related properties of a sample in the biological material container 3. The optical sensor 37 has a roughly conical shape with a roughly hemispherical rounded base. The optical sensor 37 is positioned roughly parallel to the central axis of the tube section 41. The optical sensor 37 is fixed to the tube section 41 by a first holder 441 at its center in the height direction. An optical sensor cable 373 extends from the top of the optical sensor 37. The optical sensor cable 373 is connected to electronic components such as a control unit 31 embedded inside the internal cap section 43. The optical sensor cable 373 is fixed to the inner surface of the tube section 41 by a second holder 442 positioned directly above the first holder 441 that fixes the optical sensor 37 midway. 【0051】 Furthermore, the optical sensor 37 can be used to detect the number, size, shape, or concentration of solid matter in the sample. If the sample is blood, the solid matter refers to particles present in the blood (such as red blood cells, white blood cells, platelets, or lipids). The optical sensor 37 uses light to measure the presence or concentration of particles in order to detect solid matter in the blood. Note that the detection of solid matter is not limited to the optical sensor 37; for example, an ultrasonic sensor or imaging device may also be used. 【0052】 The temperature sensor 38 is a sensor for measuring the temperature of a sample in the biological material container 3, and incorporates, for example, a thermocouple, resistance thermometer, or thermistor. The temperature sensor 38 has a roughly conical shape with a roughly hemispherical rounded base. The temperature sensor 38 is positioned roughly parallel to the central axis of the tube section 41. The temperature sensor 38 is fixed to the tube section 41 by a first holder 441 at its center in the height direction. A temperature sensor cable 383 extends from the top of the temperature sensor 38. The temperature sensor cable 383 is connected to electronic components such as a control unit 31 embedded inside the internal cap section 43. The temperature sensor cable 383 is fixed to the inner surface of the tube section 41 by a second holder 442 positioned directly above the first holder 441 that fixes the temperature sensor 38. 【0053】 The pH meter 39 is a device for measuring the acidity and alkalinity of a sample. The pH meter 39 measures the pH value, which is expressed on a pH scale (ranging from 0 to 14). A value less than 7 indicates acidity, 7 indicates neutrality, and a value greater than 7 indicates alkalinity. 【0054】 The hydrometer 40 is a device for measuring the specific gravity (density) of a sample. For example, if the sample is blood, the hydrometer 40 measures the components in the blood (red blood cells, white blood cells, plasma, etc.). Although not shown in the perspective view, the pH meter 39 and hydrometer 40 are also positioned so as to be immersed in the sample. The pH meter 39 and hydrometer 40 may be integrated with, for example, a pressure sensor 36, a light sensor 37, or a temperature sensor 38. It is desirable that the hydrometer 40 be positioned, for example, in the center of the sample in the biological material container 3 (a position where the sample is evenly distributed). 【0055】 The sensors are not limited to those mentioned above. For example, a humidity sensor, GPS module, or imaging device may be installed inside the biological material container 3. 【0056】 Figure 6 is an explanatory diagram showing an example of the record layout for the transport quality DB152 and sensor data DB153. The transport quality DB152 includes columns for collection ID, transport method, transport distance, transport time, biological material container ID, number of samples, sample type, measurement items, weight, collection location, collection date and time, storage condition, temperature, humidity, weather, and quality evaluation. The collection ID column stores a uniquely identified ID for each collection data. 【0057】 The transport means column stores the transport means used to transport the biological material container 3. Transport means include automobiles, railways (e.g., electric trains), aircraft, ships, bicycles, boats, drones, motorcycles, or trucks. The transport distance column stores the distance over which the biological material container 3 is transported. The transport time column stores the time period (e.g., "9:00~9:30") over which the biological material container 3 is transported. 【0058】 The biomaterial container ID column stores the ID of a biomaterial container (i.e., a specimen container) 3 that contains a specimen as a biomaterial (e.g., blood), which is uniquely identified. The specimen count column stores the number of specimens packed into each collected biomaterial storage box 92. Specifically, the specimen count column stores the total number of biomaterial containers 3 and 4. The specimen type column stores the type of specimen. Specimen types include blood, plasma, blood cells, serum, saliva, urine, cells, or tissues, etc. 【0059】 The measurement item column stores the items to be measured for a sample. For example, measurements for blood may include blood components (e.g., red blood cell count, white blood cell count, or platelet count), biochemical items (e.g., glucose, electrolytes, liver function, or kidney function), or immunological items (e.g., antibody tests or C-reactive protein). 【0060】 The weight column stores the individual weight of each biological material container 3 containing a sample. For example, if the sample is blood, the weight column stores the weight of the biological material container 3 with the blood inside. The weight column may also store the total weight of the biological material containers 3 containing the samples, depending on the number of samples. 【0061】 The Collection Location column stores the location where the collection took place. The Collection Date and Time column stores the date and time information of the collection. The Storage Condition column stores the storage conditions of the sample. Storage conditions include, for example, light protection (storage in a dark place to avoid ultraviolet light or direct sunlight) or environmental conditions (e.g., refrigeration, freezing, drying, or vibration). 【0062】 The temperature column stores the temperature at predetermined time intervals (e.g., 10 minutes) during the transport period. The humidity column stores the humidity at predetermined time intervals during the transport period. The weather column stores the weather (e.g., sunny, cloudy, rainy, snowy, or windy) at predetermined time intervals during the transport period. Climate information, including temperature, humidity, and weather, is obtained from an external Japan Meteorological Agency server or weather data distribution system. The quality evaluation column stores the transport quality values ​​output from the quality evaluation model 151 as quality evaluation results. The transport quality values ​​will be described later. 【0063】 The sensor data DB153 includes columns for biological material container ID, temperature data, inertia data, pressure data, light data, motion data, pH value, specific gravity, solid matter, and measurement date and time. 【0064】 The biomaterial container ID column stores the biomaterial container ID for identifying the biomaterial container 3. The temperature data column stores temperature data from the sample acquired by the temperature sensor 38 at predetermined time intervals (e.g., 1 minute). The inertia data column stores inertia data (e.g., acceleration and angular velocity sensor data) of the biomaterial container 3 acquired by the inertia sensor 34 at predetermined time intervals (e.g., 100 milliseconds). 【0065】 The pressure data stream stores pressure data from within the sample acquired by the pressure sensor 36 at predetermined time intervals (e.g., 5 seconds). The light data stream stores light data from within the sample (e.g., light intensity) acquired by the light sensor 37 at predetermined time intervals (e.g., 1 second). 【0066】 The motion data column stores motion data within the sample acquired by a sensor (e.g., probe 35 in Figure 4) that detects the movement of the liquid surface in the sample at predetermined time intervals (e.g., 2 seconds). The pH value column stores the pH value of the sample acquired by a pH meter 39 at predetermined time intervals (e.g., 3 seconds). 【0067】 The specific gravity column stores specific gravity data of the sample acquired by the hydrometer 40 at predetermined time intervals (e.g., 10 seconds). The solid matter column stores data on solid matter in the sample (number, size, type, or shape, etc.) at predetermined time intervals (e.g., 1 minute). The measurement date and time column stores the measurement date and time when various sensor data were measured. 【0068】 In addition to the various sensor data sequences described above, if other types of sensors are installed inside the biological material container 3, sensor data sequences corresponding to those sensors may also be set. 【0069】 The storage configurations described above for each database are merely examples; other storage configurations are also acceptable as long as the relationships between the data are maintained. 【0070】 In this embodiment, we describe an example of a blood sample, but the same method can be applied to other types of samples. 【0071】 Figure 7 is an explanatory diagram illustrating the process for evaluating the quality of blood in a container for biological materials. Blood from a medical facility is collected by a transport company. Server 1 acquires blood collection data from the transporter's terminal 2. The collection data includes collection ID, means of transport, transport distance, biological material container ID for each blood sample, number of samples, type of sample (e.g., blood or urine), measurement items, weight, collection location, collection date and time, and storage conditions (e.g., light shielding). Server 1 stores the acquired collection data in the transport quality DB 152. 【0072】 First, let's explain the process of storing time-series sensor data. While truck 91 is transporting multiple biological material storage boxes 92, server 1 acquires time-series sensor data obtained during transport from multiple sensors (inertial sensor 34, probe 35, pressure sensor 36, optical sensor 37, temperature sensor 38, pH meter 39 or hydrometer 40, etc.) installed inside the biological material containers 3 packed in each biological material storage box 92. 【0073】 The sensor data is time-series data obtained at predetermined intervals during the target period of transport (for example, 9:00 to 9:30). As shown in Figure 4, the sensor data includes temperature data from a temperature sensor 38 located in the blood, inertial data from an inertial sensor 34, pressure data from a pressure sensor 36 located in the blood, optical data from an optical sensor 37 located in the blood, motion data from a probe 35, pH value from a pH meter 39, specific gravity data from a hydrometer 40, and solid matter data from the optical sensor 37. 【0074】 Server 1 stores the acquired time-series sensor data in the sensor data DB 153. Specifically, Server 1 stores the time-series sensor data and measurement date and time obtained from multiple sensors installed inside each biological material container 3, associated with the biological material container ID of each biological material container 3 containing blood, in the sensor data DB 153. 【0075】 Next, we will explain the quality evaluation process for transport based on time-series sensor data using the quality evaluation model 151. Figure 8 is an explanatory diagram of the quality evaluation model 151. Server 1 uses time-series sensor data obtained from multiple sensors installed inside the biological material container 3 to perform machine learning and generate the quality evaluation model 151. In this embodiment, the quality evaluation model 151 is a neural network related to LSTM (Long-Short Term Memory). LSTM is a type of RNN (Recurrent Neural Network) and is a neural network that takes time-series sensor data during transport as input and outputs values ​​related to the quality of transport. 【0076】 An LSTM has an input layer, a hidden layer, and an output layer. The input layer has multiple neurons, each receiving sensor data at each point in time in a time series. 【0077】 The hidden layer contains neurons that calculate predicted values ​​from the input values ​​to each neuron in the input layer. The neurons in the hidden layer are called LSTM blocks. The hidden layer calculates the value for the next time point from the time series data up to the most recent time point by using the calculation results based on past input values ​​(sensor data) to perform calculations on the input values ​​at the next time point. 【0078】 The output layer has neurons that calculate values ​​related to transport quality based on the calculation results in the intermediate layer, and outputs values ​​related to transport quality. 【0079】 Server 1 generates a quality evaluation model 151 using training data. The training data consists of combinations of time-series sensor data obtained from multiple sensors installed inside the biological material container 3 containing blood, and values ​​related to the quality of the blood (e.g., quality score). The training data is generated based on a large amount of time-series sensor data collected from multiple sensors installed inside the biological material container 3 containing blood. Note that the training data may also be data created manually. 【0080】 The input data included in the training dataset is a multidimensional array containing time-series sensor data, with each sensor data point arranged in chronological order. The sensor data includes, for example, temperature data, inertial data, pressure data, light data, motion data, pH value, specific gravity data, and solid matter data. Temperature data is denoted by "T", inertial data by "I", pressure data by "P", light data by "L", motion data by "M", pH value by "pH", specific gravity data by "S", and solid matter data by "F". 【0081】 For example, the format of the input data could be, for instance, [ [T1, I1, P1, L1, M1, pH1, S1, F1], [T2, I2, P2, L2, M2, pH2, S2, F2], ... It is also acceptable to have it as ]. 【0082】 Various sensor data are acquired at predetermined time intervals. For example, temperature data may be acquired every minute, inertial data every 100 milliseconds, pressure data every 5 seconds, optical data every second, motion data every 2 seconds, pH value every 3 seconds, specific gravity data every 10 seconds, and solid matter data every minute. If no sensor data is acquired, the corresponding element in the array will be set to "NULL" or "blank". 【0083】 Furthermore, the output data included in the training data is a value related to the quality of transport. The quality value is a quality score (e.g., in the range of 0 to 100) as a continuous value indicating quality. The quality value may also be determined by an evaluator who assesses the quality of the blood. For example, the evaluator may assign a quality score (e.g., "0 to 100") to the blood by performing a visual inspection of the blood (visual confirmation of color, transparency, presence of foreign matter, etc.). Alternatively, the evaluator may assign a quality score to the blood by performing biochemical tests. Biochemical tests are tests that measure specific chemical components (blood glucose levels and cholesterol levels, etc.) and evaluate quality based on the measurement results. Furthermore, the evaluator may assign a quality score to the blood by comparing it with standard values ​​for the components and characteristics of the blood and determining whether it meets the evaluation criteria. 【0084】 Note that the quality-related values ​​are not limited to quality scores; for example, they may also be class levels indicating quality (e.g., "good," "slightly poor," and "poor"). In this embodiment, an example of a quality score is described, but the same can be applied to other types of quality-related values. 【0085】 Specifically, Server 1 sequentially inputs the sensor data being transported to the corresponding neurons in the input layer in a time-series order and calculates a predicted quality score. Server 1 compares the predicted value with the quality score included in the training data as the ground truth and optimizes the parameters used in the calculations in the hidden layer so that the predicted value approximates the ground truth. These parameters include, for example, the weights (connection coefficients) between neurons and the coefficients of the activation function. The method of parameter optimization is not particularly limited, but for example, Server 1 uses backpropagation to optimize various parameters. Through the above process, Server 1 generates a quality evaluation model 151 using the training data. 【0086】 Server 1 uses the generated quality evaluation model 151 to predict (estimate) the quality score of the blood being transported. Specifically, based on the biological material container ID of the biological material container 3 containing each blood sample, Server 1 obtains time-series sensor data from multiple sensors installed inside each biological material container 3 during the target period of transport (e.g., 9:00 to 9:30) from the sensor data DB 153. Server 1 may also directly obtain time-series sensor data from multiple sensors. 【0087】 Server 1 inputs the acquired time-series sensor data into the quality evaluation model 151 and outputs a transport quality score. As shown in the figure, the output quality score is "65". 【0088】 Furthermore, the quality evaluation model 151 may be composed of algorithms other than LSTM, such as RNN (Recurrent Neural Network), SVM (Support Vector Machine), Transformer, Seq2Seq (Sequence to Sequence), Random Forest, and Decision Tree, or it may be composed of a combination of multiple algorithms. 【0089】 In this embodiment, an example of a quality evaluation process for transport using the quality evaluation model 151 has been described, but the invention is not limited to this. For example, rule-based quality evaluation can be implemented based on various sensor data. Specifically, the server 1 determines a transport quality score by comparing sensor data (temperature, pressure, vibration, or light intensity, etc.) obtained from various sensors with predetermined reference values. 【0090】 For example, if the temperature measured by the temperature sensor (e.g., 6°C) falls within a reference range (e.g., 2°C to 8°C), Server 1 will determine a quality score of "80" by referring to a pre-configured rule. The rule is a set of rules for weighting various sensor data or for determining a quality score under predetermined conditions. 【0091】 Alternatively, if the temperature measured by the temperature sensor (e.g., 9°C) exceeds a standard value, Server 1 determines a quality score based on the length of time the temperature has exceeded the standard value. For example, if the temperature is "9°C" and a predetermined time (e.g., 3 minutes) has elapsed, Server 1 refers to a pre-set rule and determines a quality score of "70" as a minor impact. Alternatively, if the temperature is "10°C" and a predetermined time (e.g., 3 minutes) has elapsed, Server 1 refers to a pre-set rule and determines a quality score of "60". 【0092】 Furthermore, a quality score can be determined based on a combination of temperature data and sensor data obtained from other sensors (e.g., pressure sensors). For example, if the temperature exceeds a reference value and the pressure is within a reference value, Server 1 will determine a quality score of "80" by referring to a pre-set rule. Alternatively, if the temperature exceeds a reference value and the pressure is outside the reference range, Server 1 will determine a quality score of "70" by referring to a pre-set rule. 【0093】 Next, returning to Figure 7, Server 1 stores the quality score of the blood in the transport quality DB 152, associating it with the biomaterial container ID of the biomaterial container 3 containing the blood. Server 1 determines whether the quality score output from the quality evaluation model 151 is below a predetermined threshold. If the quality score is below the predetermined threshold, Server 1 transmits (outputs) the biomaterial container ID, the sensor data corresponding to the quality score, and the date and time the sensor data was measured to the transporter terminal 2 of the transporter carrying the biomaterial container 3. 【0094】 Furthermore, if the quality score is below a predetermined threshold, Server 1 sends warning information to the carrier terminal 2. The warning information includes, for example, the container ID for biological materials, the quality score, and a message indicating an abnormality. The message may be, for example, "Warning: Continuing transport may affect quality," or "Pressure has fallen below the specified value (Data: 900 hPa)." 【0095】 Furthermore, if multiple thresholds are set, evaluation criteria corresponding to each threshold can be established in advance. For example, if the quality score is less than or equal to the first threshold (e.g., "80") and exceeds the second threshold (e.g., "70"), Server 1 sends a first warning (mild warning) to the carrier terminal 2. 【0096】 Furthermore, if the quality score falls below the second threshold and exceeds the third threshold (for example, "60"), Server 1 sends a second warning (a more serious warning than the first) to the carrier terminal 2. Additionally, if the quality score falls below the third threshold, Server 1 sends a third warning (an immediate emergency warning) to the carrier terminal 2. By setting multiple thresholds in this way, a gradual warning system for quality degradation can be implemented. 【0097】 The warning information may also include corrective action information. For example, corrective action information might be, "Check that the valve for regulating pressure is properly closed or open." By transmitting the warning information to the carrier terminal 2, the carrier can quickly understand the problem and take necessary measures. This ensures the quality of the blood. 【0098】 Furthermore, a report regarding the quality evaluation can be sent to the transporter terminal 2. Specifically, the server 1 generates a report that includes the biological material container ID, quality score, sensor data if the quality score is below a predetermined threshold, location information, and date and time. The location information may be obtained from a GPS module installed inside the biological material container 3, or through a GPS module mounted on the truck 91. 【0099】 Server 1 sends the generated report to carrier terminal 2. Carrier terminal 2 receives the report sent from server 1. Carrier terminal 2 displays the received report on its screen. 【0100】 Figure 9 is a flowchart showing the processing procedure for evaluating the quality of blood in a container for biological materials. The control unit 11 of the server 1 acquires time-series sensor data obtained during transport from multiple sensors (e.g., inertial sensor 34, probe 35, pressure sensor 36, optical sensor 37, temperature sensor 38, pH meter 39, and hydrometer 40) installed inside the biological material container 3 containing the blood, via the communication unit 13 (step S101). The sensor data includes at least two of the following: temperature data, inertial data, pressure data, optical data, motion data, pH value, specific gravity data, and solid matter data. 【0101】 The control unit 11 stores the time-series sensor data obtained from multiple sensors installed inside each biological material container 3, as well as the measurement date and time, in the sensor data DB 153 of the large-capacity storage unit 15, corresponding to the biological material container ID of each biological material container containing blood (step S102). 【0102】 The control unit 11 inputs time-series sensor data corresponding to each blood sample acquired during the target period into the quality evaluation model 151 (step S103) and outputs a quality score for each blood sample during the target period (step S104). The control unit 11 stores the quality score for each blood sample in the transport quality DB 152 of the large-capacity storage unit 15, associating it with the biomaterial container ID of the biomaterial container in which each blood sample is contained (step S105). 【0103】 The control unit 11 determines whether the quality score of each blood sample output from the quality evaluation model 151 is below a predetermined threshold (step S106). If all of the quality scores of the multiple blood samples exceed the predetermined threshold (NO in step S106), the control unit 11 terminates the process. 【0104】 If any of the quality scores among the multiple blood quality scores is below a predetermined threshold (YES in step S106), the control unit 11 transmits the corresponding biological material container ID, sensor data corresponding to the quality score, the date and time the sensor data was measured, and warning information (such as the quality score and a message indicating an abnormality) to the transporter terminal 2 via the communication unit 13 (step S107). 【0105】 In Figure 9, sensor data, date and time, and warning information are transmitted to the carrier terminal 2 simultaneously, but this is not the only option. The control unit 11 may transmit the sensor data and date and time, or the warning information, separately to the carrier terminal 2. 【0106】 The control unit 21 of the transporter terminal 2 receives sensor data, date and time, and warning information transmitted from the server 1 via the communication unit 23 (step S201). The control unit 21 displays the received sensor data, date and time, and warning information via the display unit 25 (step S202). The control unit 21 then terminates processing. 【0107】 According to this embodiment, it is possible to store time-series sensor data obtained during transport from multiple sensors installed inside multiple biological material containers 3 containing the samples. 【0108】 According to this embodiment, by inputting time-series sensor data corresponding to the sample into the quality evaluation model 151, it becomes possible to output values ​​related to the quality of the sample. 【0109】 According to this embodiment, if a quality-related value is below a predetermined threshold, the sensor data and date / time corresponding to that quality-related value can be output to the transporter terminal 2. 【0110】 According to this embodiment, if the quality value is below a predetermined threshold, warning information can be output to the carrier terminal 2. 【0111】 <Example 1> This section describes a process that outputs a quality-related value (e.g., a quality score) at predetermined time intervals by inputting sensor data at predetermined time intervals into the quality evaluation model 151. 【0112】 Figure 10 is an explanatory diagram of the quality evaluation model 151 in Modification 1. Note that the same reference numerals are used for parts that overlap with Figure 8, and their explanations are omitted. In this modification, the quality evaluation model 151 is a neural network that takes sensor data at predetermined time intervals during transport as input and outputs a quality score at each predetermined time interval. A predetermined time interval refers to a defined unit of time, set at a fixed cycle (for example, 1 minute, 10 minutes, 30 minutes, 1 hour, or 1 day). 【0113】 Server 1 generates a quality evaluation model 151 using training data. The training data is a combination of sensor data collected at predetermined time intervals (e.g., 10 minutes) during transport and the corresponding quality score for each predetermined time interval. For example, temperature data is represented by "T", inertial data by "I", pressure data by "P", optical data by "L", motion data by "M", pH value by "pH", specific gravity data by "S", and solids data by "F". 【0114】 For example, the format of the input data included in the training data could be, for instance, <9:00~9:10> [ [T1_1, I1_1, P1_1, L1_1, M1_1, pH1_1, S1_1, F1_1], [T1_2, I1_2, P1_2, L1_2, M1_2, pH1_2, S1_2, F1_2], ... ] <9:10~9:20> [[T2_1, I2_1, P2_1, L2_1, M2_1, pH2_1, S2_1, F2_1], [T2_2, I2_2, P2_2, L2_2, M2_2, pH2_2, S2_2, F2_2], ... ] <9:20~9:30> [ [T3_1, I3_1, P3_1, L3_1, M3_1, pH3_1, S3_1, F3_1], [T3_2, I3_2, P3_2, L3_2, M3_2, pH3_2, S3_2, F3_2], ... ] It could also be "." 【0115】 During each time period ("9:00-9:10", "9:10-9:20", and "9:20-9:30"), various sensor data are acquired at predetermined time intervals. For example, temperature data may be acquired every minute, inertial data every 100 milliseconds, pressure data every 5 seconds, light data every 1 second, motion data every 2 seconds, pH value every 3 seconds, specific gravity data every 10 seconds, and solid matter data every minute. If no sensor data is acquired, the corresponding element in the array will be set to "NULL" or "blank". 【0116】 Furthermore, the output data included in the training data is the quality score for each predetermined unit of time. The output data may also be a class level indicating quality, etc. The process for generating the quality evaluation model 151 using the training data is the same as in Embodiment 1, so the explanation is omitted. 【0117】 Server 1, based on the biological material container ID of the biological material container 3 containing the blood to be quality evaluated, acquires time-series sensor data from the sensor data DB 153 at predetermined intervals (e.g., every 10 minutes) during the target period of transport (e.g., 9:00 to 9:30). 【0118】 Server 1 inputs the acquired time-series sensor data for each predetermined unit time into the quality evaluation model 151 and outputs the blood quality score for each predetermined unit time. As shown in the figure, the quality score for <9:00~9:10> is "80", the quality score for <9:10~9:20> is "70", and the quality score for <9:20~9:30> is "69". 【0119】 Server 1 transmits the blood quality score for each predetermined unit time to the transporter terminal 2. Transporter terminal 2 receives the blood quality score for each predetermined unit time transmitted from Server 1. Transporter terminal 2 displays the received blood quality score for each predetermined unit time on its screen. 【0120】 Furthermore, a final quality score can be output based on multiple quality scores obtained during the transport period. For example, Server 1 may calculate the average or weighted average of multiple quality scores and output the calculated score as the final quality score to the transporter terminal 2. Alternatively, Server 1 may obtain the minimum value (lowest score) or maximum value (highest score) from the multiple quality scores and output the obtained minimum or maximum value as the final quality score. 【0121】 According to this modified version, by inputting sensor data at predetermined time intervals into the quality evaluation model 151, it becomes possible to output quality-related values ​​at those predetermined time intervals. 【0122】 <Modification 2> This section describes a process that outputs a value related to the quality of a sample by further inputting the sample type, climate information, or transport information into the quality evaluation model 151. In this embodiment, an example is described where the value related to quality is a "quality score," but the same method can be applied to other types of quality values. 【0123】 Figure 11 is an explanatory diagram of the quality evaluation model 151 in modified example 2. Content that overlaps with Figure 8 is denoted by the same reference numerals and its explanation is omitted. 【0124】 First, we will explain the process of outputting a value related to the quality of a sample (e.g., a quality score) by inputting time-series sensor data and the type of sample (e.g., blood) into the quality evaluation model 151. The types of samples include blood, plasma, blood cells, serum, saliva, urine, cells, or tissue. 【0125】 The quality evaluation model 151 is a neural network that takes time-series sensor data during transport and the type of sample as input and outputs a quality score for the sample. Server 1 generates the quality evaluation model 151 using training data. The training data is data of combinations in which time-series sensor data during transport, the type of sample, and the quality score of the sample are associated. Note that the process of generating the quality evaluation model 151 using the training data is the same as in Embodiment 1, so the explanation is omitted. 【0126】 Server 1 uses the generated quality evaluation model 151 to predict the quality score of the samples being transported. Specifically, based on the biological material container ID of the biological material container 3 in which each sample is contained, Server 1 obtains time-series sensor data from multiple sensors installed inside each biological material container 3 from the sensor data DB 153 during the target period of transport (e.g., 9:00 to 9:30). Server 1 may also directly obtain time-series sensor data from multiple sensors. 【0127】 Server 1 retrieves the type of sample from the transport quality DB 152 based on the container ID for each biological material. Server 1 inputs the retrieved time-series sensor data and the type of sample into the quality evaluation model 151 and outputs the quality score for the sample. 【0128】 Next, we will describe the process of outputting a sample quality score by inputting time-series sensor data and climate information into the quality evaluation model 151. The climate information includes at least one piece of information such as temperature, humidity, weather (e.g., sunny, cloudy, rainy, snowy, or windy), precipitation, wind speed, wind direction, sunshine duration, information on the occurrence of extreme weather events (e.g., typhoons, heavy rain, or heat waves), and weather forecasts (information that predicts future weather conditions). 【0129】 Server 1 acquires climate information at predetermined time intervals (e.g., every 10 minutes) during the target period (transport time period) from an external Japan Meteorological Agency server or a weather data distribution system. Server 1 stores the acquired climate information at predetermined time intervals in the transport quality DB 152, corresponding to the target period. 【0130】 The quality evaluation model 151 is a neural network that takes time-series sensor data during transport and climate information as input and outputs a quality score for the sample. Server 1 generates the quality evaluation model 151 using training data. The training data consists of time-series sensor data during transport, and data that associates climate information at predetermined time intervals during the target period with the quality score of the sample. The process for generating the quality evaluation model 151 using the training data is the same as in Embodiment 1, so the explanation is omitted. 【0131】 Server 1 uses the generated quality evaluation model 151 to predict the quality score of the samples being transported. Specifically, based on the biological material container ID of the biological material container 3 in which each sample is contained, Server 1 obtains time-series sensor data from the sensor data DB 153 obtained from multiple sensors installed inside each biological material container 3 during the target period of transport. 【0132】 Server 1 acquires climate information at predetermined time intervals from the transport quality DB 152 during the target period. Server 1 inputs the acquired time-series sensor data and climate information at predetermined time intervals into the quality evaluation model 151 and outputs a quality score for the sample. 【0133】 Finally, we will explain the process of outputting a sample quality score by inputting time-series sensor data and transport information indicating the transport status of the biological material container 3 into the quality evaluation model 151. 【0134】 Transportation information includes at least one piece of information, such as the means of transportation, transportation distance, transportation time, collection information, and storage status. Means of transportation include automobiles, railways (e.g., electric trains), aircraft, ships, bicycles, motorcycles, and trucks. Collection information includes the contents of collection (e.g., number and type of samples), collection date and time, and collection location. Transportation information may also include transportation status (progress or delay information, etc.) or tracking information (e.g., GPS location information). 【0135】 The quality evaluation model 151 is a neural network that takes time-series sensor data during transport and transport information of the biological material container 3 as input and outputs a quality score for the sample. Server 1 generates the quality evaluation model 151 using training data. The training data is data of combinations in which time-series sensor data during transport, transport information of the sample, and the quality score of the sample are associated. Note that the process of generating the quality evaluation model 151 using the training data is the same as in Embodiment 1, so the explanation is omitted. 【0136】 Server 1 uses the generated quality evaluation model 151 to predict the quality score of the samples being transported. Specifically, based on the biological material container ID of the biological material container 3 in which each sample is contained, Server 1 obtains time-series sensor data from the sensor data DB 153 obtained from multiple sensors installed inside each biological material container 3 during the target period of transport. 【0137】 Server 1 obtains transport information for each biological material container 3 (e.g., transport method, transport distance, and transport time) from the transport quality DB 152 based on the ID of each biological material container. Server 1 inputs the acquired time-series sensor data and the transport information for the biological material container 3 into the quality evaluation model 151 and outputs the quality score for the sample. 【0138】 Furthermore, the quality evaluation model 151 can output a quality score for a sample by inputting time-series sensor data and either the sample type, climate information, and / or a combination thereof. In this case, the server 1 generates the quality evaluation model 151 using training data. The training data consists of time-series sensor data during transport, and data of combinations in which the sample type, climate information, and / or a combination thereof (for example, sample type and climate information) are associated with the sample's quality score. The process for generating the quality evaluation model 151 using the training data is the same as in Embodiment 1, so a detailed explanation is omitted. 【0139】 Furthermore, the quality evaluation model 151 may be generated for each type of sample (blood or urine, etc.). For example, Server 1 may use time-series sensor data during blood transport to perform machine learning and generate a blood model for evaluating the quality of blood transport. Alternatively, Server 1 may use time-series sensor data during urine transport to perform machine learning and generate a urine model for evaluating the quality of urine transport. 【0140】 Alternatively, the quality evaluation model 151 may be generated for each means of transporting the sample (truck, car, or motorcycle, etc.). For example, Server 1 may use time-series sensor data during sample transport by truck to perform machine learning and generate a truck model for evaluating the quality of transport by truck. Alternatively, Server 1 may use time-series sensor data during sample transport by car to perform machine learning and generate a car model for evaluating the quality of transport by car. 【0141】 According to this modified version, by further inputting the type of sample into the quality evaluation model 151, it becomes possible to output values ​​related to quality. 【0142】 According to this modified version, by further inputting climate information into the quality evaluation model 151, it becomes possible to output values ​​related to quality. 【0143】 According to this modified version, by further inputting the transport means into the quality evaluation model 151, it becomes possible to output values ​​related to quality. 【0144】 (Embodiment 2) Embodiment 2 relates to a method for outputting (displaying) quality-related values ​​on a graph. Note that explanations of content that overlaps with Embodiment 1 will be omitted. 【0145】 Based on first input data containing multiple time-series sensor data obtained from multiple types of sensors, and second input data containing climate information or transport information indicating transport conditions, a quality evaluation model 151 can output a value related to the quality of a sample. While the following example describes a quality score as the value related to quality, the same method can be applied to other types of quality values. 【0146】 Climate information includes at least one piece of information such as temperature, humidity, weather (e.g., sunny, cloudy, rainy, snowy, or windy), precipitation, wind speed, wind direction, sunshine duration, information on the occurrence of extreme weather events (e.g., typhoons, heavy rain, or heat waves), and weather forecasts (information that predicts future weather conditions). 【0147】 Transportation information includes at least one piece of information such as the means of transportation, transportation distance, transportation time, collection information, and storage status. The means of transportation includes automobiles, railways (e.g., electric trains), aircraft, ships, bicycles, motorcycles, and trucks. Collection information includes the contents of the collection (e.g., number and type of samples), collection date and time, or collection location. Transportation information may also include transportation status (progress or delay information, etc.) or tracking information (e.g., GPS location information). 【0148】 Figure 12 is an explanatory diagram illustrating the first and second input data. The first input data, which consists of combinations of sensor types that differ from one another, is composed of two or more combinations of data from "liquid temperature," "vibration," "tipping," "acceleration," "liquid splashing," "light," "pH," "specific gravity," "solid matter," and "pressure." 【0149】 "Liquid temperature" refers to the temperature of the sample and is measured by the temperature sensor 38. "Vibration" refers to the phenomenon in which the sample or biological material container 3 shakes periodically due to external forces or influences. "Vibration" is measured by the inertia sensor 34. 【0150】 "Tipping" refers to the phenomenon where the biological material container 3 tilts from the horizontal or completely falls over. "Tipping" is detected by the inertial sensor 34 measuring acceleration and angular velocity (angle of tilt). For example, server 1 calculates the tilt of the biological material container 3 using the acceleration and angular velocity obtained by the inertial sensor 34. Server 1 compares the calculated tilt with a preset tilt threshold to determine how much the biological material container 3 is tilted. For example, server 1 may determine that the biological material container 3 has completely fallen over if it is tilted by 30 degrees or more. "Acceleration" refers to the rate of change in velocity during the movement of the sample. "Acceleration" is measured by the inertial sensor 34. 【0151】 "Splashing" refers to the phenomenon in which a sample moves due to an external force or vibration, producing waves or droplets. Splashing is measured by an inertial sensor 34 or a probe 35. The inertial sensor 34 can indirectly measure splashing, indicating the degree of splashing of the sample, by detecting vibration or acceleration. The probe 35 can measure the splashing pattern by detecting changes in liquid level, waves, or movement in real time using a sensor element positioned at its tip. 【0152】 "Light" refers to visible light, etc., irradiated onto the sample and is measured by the light sensor 37. "pH" is an indicator of the acidity or alkalinity of the sample and is measured by the pH meter 39. "Specific gravity" is an indicator of the density of the sample and is measured by the hydrometer 40. "Solid matter" refers to solid components (particles) present in the sample and is measured by the light sensor 37. "Pressure" refers to the force exerted by the sample on the inside of the biological material container 3 and is measured by the pressure sensor 36. 【0153】 The second input data consists of climate information including "temperature," "humidity," and "weather," or transport information such as "transport time," "collection information," and "storage conditions." Climate information and transport information are obtained from the transport quality DB152. 【0154】 Server 1 accepts the combination of the first input data and the second input data as attributes assigned to each quality evaluation model 151, for example, through the carrier terminal 2. As shown in the figure, Server 1 accepts the setting of attributes from the combination of the first input data and the second input data, including the first attribute being "protection from external influences," the second attribute being "freshness," the third attribute being "matching request information," the fourth attribute being "handling of luggage," and the fifth attribute being "careful driving." 【0155】 The first attribute is obtained from a combination of first input data including "liquid temperature," "light," and "pH," and second input data including "air temperature," "humidity," and "weather." The second attribute is obtained from a combination of first input data including "liquid temperature," "specific gravity," "solid matter," and "pressure," and second input data including "transport time." 【0156】 The third attribute is obtained from a combination of first input data including "light" and "pH" and second input data including "collection information". The fourth attribute is obtained from a combination of first input data including "liquid temperature", "tipping", and "liquid splashing" and second input data including "storage conditions". The fifth attribute is obtained from a combination of first input data including "vibration" and "acceleration" and second input data including "transport time". 【0157】 Server 1 generates a target quality evaluation model 151 that assigns each attribute using training data that associates combination data corresponding to each received attribute with the quality score of the sample. In other words, at least three or more types of quality evaluation models 151 are generated for combinations of first input data and second input data in which the combinations of sensor types are mutually different. 【0158】 The following example describes how to generate a first quality evaluation model 151 that assigns a first attribute, but the same process can be applied to generating quality evaluation models 151 that assign other attributes. 【0159】 The first quality evaluation model 151 is a neural network that takes combination data corresponding to the first attribute as input and outputs a quality score for the sample in the first attribute. Server 1 generates the first quality evaluation model 151 using training data. The training data is combination data in which combination data corresponding to the first attribute is associated with the quality score of the sample in the first attribute. The process of generating the first quality evaluation model 151 using the training data is the same as in Embodiment 1, so the explanation is omitted. 【0160】 Server 1 generates a second quality evaluation model 151 that assigns a second attribute, a third quality evaluation model 151 that assigns a third attribute, a fourth quality evaluation model 151 that assigns a fourth attribute, and a fifth quality evaluation model 151 that assigns a fifth attribute, similar to the generation process of the first quality evaluation model 151 described above. 【0161】 Server 1 uses each generated quality evaluation model 151 to predict the quality score of the sample for each attribute. Below, we will explain an example of predicting the quality score of the sample for the first attribute using the generated first quality evaluation model 151, but this process can be similarly applied to predicting the quality score of the sample for other attributes. 【0162】 Server 1 acquires, based on the biological material container ID of the biological material container 3 containing the target sample, time-series sensor data (e.g., liquid temperature, light, and pH) corresponding to the first attribute obtained from multiple sensors installed inside the biological material container 3 during the target period of transport, as the first input data. 【0163】 Server 1 acquires climate information (e.g., temperature, humidity, and weather) at predetermined time intervals from the transport quality DB 152 as second input data during the target period. Server 1 inputs the combined data of the acquired first input data and second input data into the first quality evaluation model 151 and outputs the quality score of the sample for the first attribute. 【0164】 Furthermore, rule-based quality evaluation can be achieved based on the combined data of the first input data and the second input data. Specifically, Server 1 determines the transport quality score by comparing the first input data and the second input data with predetermined reference values. 【0165】 For example, Server 1 determines whether the temperature (liquid temperature) is within a reference range (e.g., 2°C to 8°C), the light intensity is within a reference range, and the pH value is within a reference range in the first input data, and then determines a quality score by referring to a pre-set rule. Server 1 also adjusts the quality score by comparing the second input data (temperature, humidity, and weather) with reference values. For example, if the temperature exceeds a reference value, Server 1 adjusts the quality score to decrease by a predetermined amount (e.g., "5"). 【0166】 Next, Server 1 outputs (transmits) the quality scores output from each quality evaluation model 151, along with the attributes assigned to each quality evaluation model 151, to the carrier terminal 2. The following describes an example of outputting the quality scores along with each attribute on a graph. 【0167】 Figure 13 is an explanatory diagram showing an example of outputting quality scores on a chart. In Figure 13, the quality scores output from each quality evaluation model 151 can be displayed on a chart 81 with attributes as the axis. 【0168】 Figure 13 includes the first attribute display axis 11a, the second attribute display axis 11b, the third attribute display axis 11c, the fourth attribute display axis 11d, the fifth attribute display axis 11e, and the overall score display area 11f. The first attribute display axis 11a is a display axis based on the first attribute (e.g., "protection from external influences"). The second attribute display axis 11b is a display axis based on the second attribute (e.g., "freshness"). The third attribute display axis 11c is a display axis based on the third attribute (e.g., "match with requested information"). 【0169】 The fourth attribute display axis 11d is a display axis based on the fourth attribute (e.g., "handling of luggage"). The fifth attribute display axis 11e is a display axis based on the fifth attribute (e.g., "careful driving"). The overall score display area 11f is a display area that displays the overall quality score. 【0170】 Chart 81 is a graph that shows the relationship between each attribute and the quality score from each quality evaluation model 151, by plotting the quality scores output from each quality evaluation model 151 that assigns each attribute on each axis. Server 1 generates Chart 81 based on the quality scores output from each quality evaluation model 151. 【0171】 Server 1 calculates an overall score based on the quality scores from each quality evaluation model 151. For example, Server 1 accepts the setting of weights for each attribute according to their importance. For example, the weights for the first to fifth attributes may be "0.2", "0.3", "0.2", "0.15", and "0.15". Server 1 calculates the overall score by multiplying the quality scores from each quality evaluation model 151 by the weights corresponding to each attribute. Alternatively, Server 1 may calculate the overall score by averaging the quality scores from each quality evaluation model 151. 【0172】 Server 1 transmits the generated chart 81 and the calculated total score to the carrier terminal 2. Carrier terminal 2 receives the chart 81 and total score transmitted from Server 1. Carrier terminal 2 displays the received chart 81 and total score on its screen. 【0173】 As shown in the diagram, the quality scores output from each quality evaluation model 151 (e.g., "67", "50", "70", "81", and "66") are displayed on Chart 81, corresponding to each attribute, based on the following axes: "protection from external influences", "freshness", "match with request information", "handling of cargo", and "careful driving". In addition, the overall score (e.g., "65") is displayed in the overall score display field 11f on Chart 81. 【0174】 Furthermore, Server 1 may use a language model to generate comments and improvement measures for the quality scores of the samples based on the quality scores output from each quality evaluation model 151. The language model is a language generation model constructed by pre-training on a large amount of text data (dataset). 【0175】 As language models, large-scale language models (LLMs) such as Transformer, ALBERT (A Lite BERT), GPT (Generative Pre-trained Transformer)-2, GPT-3, GPT-4, LLaVA (Large Language and Vision Assistant), MiniGPT-4, or BERT (Bidirectional Encoder Representations from Transformers) can be used. 【0176】 Specifically, Server 1 inputs the quality score output from each quality evaluation model 151, the combination data corresponding to that quality score, and prompts including instructions for outputting comments and improvement measures for that quality score into the language model, and outputs the comments and improvement measures. 【0177】 For example, the output comments and improvement measures could be: "External factors are observed to be influencing the transport. Temperature fluctuations are particularly significant. Please adjust the temperature inside truck 91 to maintain a stable environment." 【0178】 Figure 14 is an explanatory diagram showing an example of outputting quality scores from sensor data for each unit of time on a graph. Figure 14 includes Graph 82. Graph 82 is a graph showing the fluctuation of quality scores from each quality evaluation model 151 for each predetermined period (e.g., 10 minutes). The horizontal axis of Graph 82 represents the time period for each predetermined unit of time, and the vertical axis represents the quality score from each quality evaluation model 151. 【0179】 Server 1, based on the biological material container ID of the biological material container 3 containing the target sample, acquires time-series sensor data (e.g., liquid temperature, light, and pH) corresponding to the first attribute ("protection from external influences") obtained from multiple sensors installed inside the biological material container 3 from the sensor data DB 153 at predetermined unit time intervals (e.g., 10-minute intervals) during the target period during transport (e.g., 9:00 to 9:40) as the first input data. 【0180】 Server 1 acquires climate information for predetermined time units from the transport quality DB 152 as second input data during the target period. Server 1 inputs the combined data of the acquired first input data and second input data into the first quality evaluation model 151 and outputs the quality score of the sample for the first attribute for each predetermined time unit. 【0181】 Similar to the process described above, Server 1 acquires the sample quality score for the second attribute ("freshness"), the sample quality score for the third attribute ("match with request information"), the sample quality score for the fourth attribute ("handling of packages"), and the sample quality score for the fifth attribute ("carefulness of driving") at each predetermined unit of time. 【0182】 Server 1 generates a graph 82 based on the quality score of the sample for each attribute acquired at predetermined intervals. Server 1 transmits the generated graph 82 to the carrier terminal 2. The carrier terminal 2 receives the graph 82 transmitted from Server 1 and displays the received graph 82 on its screen. 【0183】 As shown in the diagram, during the period of transport (for example, 9:00 to 9:40), the quality score of the sample for each attribute, such as "protection from external influences," "freshness," "match with request information," "handling of the package," and "carefulness of driving," is displayed in chronological order on Graph 82 at 10-minute intervals. 【0184】 Although Chart 81 and Graph 82 described above are in the form of a chart and a line graph, the graph is not limited to these and other graph formats (for example, pie charts and bar graphs) may also be used. 【0185】 In this embodiment, an example is described in which the quality score is output on a graph along with each attribute, but this is not the only example. For example, Server 1 may directly output the quality score along with each attribute in text format to the carrier terminal 2. 【0186】 Furthermore, if the quality score of any of the multiple attributes is below a predetermined threshold (e.g., 60), Server 1 sends warning information to the carrier terminal 2. The warning information includes, for example, the container ID for biological materials, the quality score of the relevant attribute (e.g., the first attribute), and a message indicating an abnormality. The message may be, for example, "The liquid temperature is outside the set range. Current temperature: 15°C (Recommended range: 20°C~25°C)" or "The pH value is inappropriate. Current pH value: 9.5 (Recommended range: 6.5~7.5)." 【0187】 In addition to the processing described above, for example, Server 1 may send warning information to the carrier terminal 2 if the quality score of a predetermined number of attributes (e.g., "2") is below a predetermined threshold. For example, Server 1 sends warning information to the carrier terminal 2 if the quality score of the first attribute ("protection from external influences") is below a predetermined threshold, AND the quality score of the second attribute ("freshness") is below a predetermined threshold. 【0188】 Furthermore, if the overall score calculated based on the quality scores obtained from each quality evaluation model 151 is below a predetermined threshold (for example, 65), the server 1 may send warning information to the carrier terminal 2. 【0189】 It is possible to use multiple thresholds, and the process for sending warnings based on multiple thresholds is the same as in Embodiment 1, so the explanation will be omitted. 【0190】 Figure 15 is a flowchart showing the processing procedure when outputting Chart 81. Based on the biological material container ID of the biological material container 3 containing the target sample, the control unit 11 of the server 1 acquires time-series sensor data corresponding to the first attribute obtained from multiple sensors installed inside the biological material container 3 during the target period of transport from the sensor data DB 153 of the large-capacity storage unit 15 as the first input data (step S111). 【0191】 The control unit 11 acquires second input data corresponding to each attribute assigned to the quality evaluation model 151 during the target period (step S112). For example, if the second input data is climate information, the control unit 11 acquires climate information (e.g., temperature, humidity, and weather) for predetermined time intervals during the target period from the transport quality DB 152 of the large-capacity storage unit 15 as the second input data. 【0192】 The control unit 11 generates combination data of the first and second input data corresponding to each attribute based on the acquired first and second input data (step S113). The control unit 11 inputs the generated combination data corresponding to each attribute into the quality evaluation model 151 that assigns each attribute (step S114), and outputs the quality score of the sample for each attribute (step S115). 【0193】 The control unit 11 generates a chart 81 based on the quality score for each attribute output from each quality evaluation model 151 (step S116). 11 transmits the generated chart 81 to the carrier terminal 2 via the communication unit 13 (step S117). The control unit 21 of the carrier terminal 2 receives the chart 81 transmitted from the server 1 via the communication unit 23 (step S211). The control unit 21 displays the received chart 81 using the display unit 25 (step S212). The control unit 21 terminates processing. 【0194】 Figure 16 is a flowchart showing the processing procedure for outputting graph 82. Based on the biological material container ID of the biological material container 3 containing the target sample, the control unit 11 of the server 1 acquires time-series sensor data corresponding to each attribute obtained from multiple sensors installed inside the biological material container 3 from the sensor data DB 153 of the large-capacity storage unit 15 as first input data at predetermined unit time intervals (for example, 10-minute intervals) during the target period of transport (step S121). 【0195】 The control unit 11 acquires second input data corresponding to each attribute assigned to the quality evaluation model 151 during the target period (step S122). For example, if the second input data is climate information, the control unit 11 acquires climate information for predetermined unit time intervals as second input data from the transport quality DB 152 of the large-capacity storage unit 15 during the target period. 【0196】 The control unit 11 generates combination data of the first and second input data corresponding to each attribute based on the acquired first and second input data (step S123). The control unit 11 inputs the generated combination data corresponding to each attribute into the quality evaluation model 151 that assigns each attribute (step S124), and outputs the quality score of the sample for each attribute at predetermined unit time intervals (step S125). 【0197】 The control unit 11 generates a graph 82 based on the quality score for each attribute output from each quality evaluation model 151 at predetermined time intervals (step S126). The control unit 11 transmits the generated graph 82 to the carrier terminal 2 via the communication unit 13 (step S127). The control unit 21 of the carrier terminal 2 receives the graph 82 transmitted from the server 1 via the communication unit 23 (step S221). The control unit 21 displays the received graph 82 using the display unit 25 (step S222). The control unit 21 terminates processing. 【0198】 According to this embodiment, it is possible to output quality values ​​from each quality evaluation model 151 along with the attributes assigned to each quality evaluation model 151. 【0199】 According to this embodiment, by outputting the quality values ​​from each quality evaluation model 151 onto a chart 81 with attributes as axes, it becomes possible to grasp the quality values ​​for each attribute at a glance. 【0200】 According to this embodiment, by outputting the time-series values ​​related to quality obtained from each quality evaluation model 151 at predetermined unit time intervals onto the graph 82 for each attribute, it becomes possible to track the trends and changes in the values ​​related to quality. 【0201】 In addition, in each of the embodiments described above, a sensing device is provided for sensing the effects on biological materials such as specimens when they are transported. The sensing device has a container 3 for biological materials containing the biological materials, and a sensor for sensing the effects of transport is provided inside the container 3 for biological materials. 【0202】 The specific configuration of the sensing device may consist of one sensor or multiple sensors, as described in Figures 4, 5A, and 5B. The sensor may be a sensor provided in the container for biological material, as described in the embodiments described above, and is preferably at least one selected from the group consisting of, for example, a temperature sensor, an inertial sensor, a pressure sensor, a light sensor, and a sensor for detecting liquid surface movement. The sensor for detecting liquid surface movement is preferably a floating sensor that floats on the liquid surface of the sample or dummy sample using buoyancy, or is supported by the container for biological material 3. 【0203】 The embodiments disclosed herein should be considered in all respects to be illustrative and not restrictive. The scope of the invention is indicated by the claims, not in the sense described above, and all modifications within the sense and scope equivalent to the claims are intended. 【0204】 The matters described in each embodiment can be combined with each other. Furthermore, the independent and dependent claims described in the claims can be combined with each other in any combination, regardless of the form of reference. In addition, the claims use a form in which claims referencing two or more other claims (multi-claim form), but are not limited to this. A form in which multi-claims referencing at least one multi-claim (multi-multi-claim) may also be used. [Explanation of symbols] 【0205】 1. Information processing device (server) 11 Control Unit 12 Storage section 13 Communications Department 14 Reading section 15 Mass storage 151 Quality Evaluation Model 152 Conveying Quality DB 153 Sensor Data Database 1a Portable storage medium 1b Semiconductor memory 1P Control Program 2. Information processing terminal (transporter terminal) 21 Control Unit 22 Memory section 23 Communications Department 24 Input section 25 Display section 2P control program 3. Containers for biomaterials 31 Control Unit 32 Storage section 33 Communications Department 34 Inertial Sensors 35 probes 36 Pressure Sensor 361 First cylindrical section 362 Second cylindrical section 363 Pressure Sensor Cable 37 Light Sensor 373 Optical sensor cable 38 Temperature Sensor 383 Temperature sensor cable 39 pH meter 40 Hydrometer 41 Tube section 42 Lid 43 Internal cap section 441 First holder 442 Second holder 3P control program 4. Containers for biomaterials 81 Chart 82 Graphs 91 Tracks 92. Storage container for biological materials B Bus N Network

Claims

[Claim 1] Time-series sensor data obtained during transport is acquired from multiple sensors installed inside at least one of several containers for biological materials containing biological materials. The acquired time-series sensor data is stored in the memory unit. Information processing methods. [Claim 2] The time-series sensor data stored in the memory unit is acquired, By inputting the acquired sensor data into a model that outputs values ​​related to transport quality when sensor data is input, the model will output values ​​related to quality. The information processing method according to claim 1. [Claim 3] The aforementioned quality-related value is the quality score. The information processing method according to claim 2. [Claim 4] The sensor data includes at least two of the following: temperature data from a temperature sensor located within the biological material, inertial data from an inertial sensor, pressure data from a pressure sensor located within the biological material, and optical data from an optical sensor located within the biological material. The information processing method according to claim 1 or 2. [Claim 5] By further inputting motion data from a sensor that detects the movement of the liquid surface of biological material into the aforementioned model, the model can output the aforementioned quality values. The information processing method according to claim 2 or 3. [Claim 6] By inputting sensor data at predetermined time intervals into the aforementioned model, the model outputs the quality-related values ​​at those predetermined time intervals. The information processing method according to claim 2 or 3. [Claim 7] When the quality value is below a predetermined threshold, the sensor data and date / time corresponding to the quality value are output. The information processing method according to claim 2 or 3. [Claim 8] When the aforementioned quality value is below a predetermined threshold, a warning is output to the terminal device of the transporter carrying the container for the biological material. The information processing method according to claim 2 or 3. [Claim 9] A learning model that outputs a quality value when inputting first input data containing multiple time-series sensor data obtained from multiple types of sensors, and second input data containing climate information or transport information indicating transport conditions, is provided with at least three different combinations of first and second input data where the sensor types are mutually different. Output the quality values ​​from each learning model, along with the attributes assigned to each model. The information processing method according to claim 2 or 3. [Claim 10] The quality values ​​from each learning model are output on a chart plotted on an attribute axis. The time-series values ​​related to quality obtained from each learning model at predetermined time intervals are output on a graph for each attribute. The information processing method according to claim 9. [Claim 11] The type of the aforementioned biomolecule is obtained, By further inputting the type of acquired biomaterial into the aforementioned model, the model can output the quality-related values. The information processing method according to claim 2 or 3. [Claim 12] Obtain climate information related to the climate, By further inputting the acquired climate information into the aforementioned model, the model outputs the values ​​related to the aforementioned quality. The information processing method according to claim 2 or 3. [Claim 13] Acquire transport information showing the transport status of the container for the biological material, By further inputting the acquired transport information into the aforementioned model, the model outputs the quality-related values. The information processing method according to claim 2 or 3. [Claim 14] Time-series sensor data obtained during transport is acquired from multiple sensors installed inside at least one of several containers for biological materials containing biological materials. The acquired time-series sensor data is stored in the memory unit. A program that instructs a computer to perform a process. [Claim 15] An information processing device comprising a control unit, The control unit, Time-series sensor data obtained during transport is acquired from multiple sensors installed inside at least one of several containers for biological materials containing biological materials. The acquired time-series sensor data is stored in the memory unit. Information processing device. [Claim 16] A sensing device for sensing the effects on a biological substance when transporting the biological substance, It has a container for biological materials that contains the aforementioned biological material, A sensor for sensing the effects of the aforementioned transport is provided inside the container for the biological material. Sensing device. [Claim 17] The sensor is at least one selected from the group consisting of a temperature sensor, an inertial sensor, a pressure sensor, a light sensor, and a sensor that detects the movement of a liquid surface. The sensing device according to claim 16. [Claim 18] The sensor that detects the movement of the liquid surface is a floating sensor that floats on the liquid surface of the biological material using buoyancy, or is supported by the container for the biological material. The sensing device according to claim 17.

Images