Biological sample monitoring method and equipment based on Internet of Things

Abstract

The present application relates to the field of biological sample monitoring, and specifically to a biological sample monitoring method and device based on the Internet of Things. A specific implementation of the method includes: in response to determining that there is an abnormal event detection result that satisfies the abnormal condition, for each abnormal event detection result that satisfies the abnormal condition, performing the following detection steps: controlling the target detection device to collect the air composition information of the corresponding channel in real time; in response to determining that there is abnormal component information in the air composition information, determining the channel corresponding to the target detection device as an abnormal channel; controlling the associated intelligent robot to move to the abnormal channel, and confirming the abnormal event indicated by the abnormal event detection result; in response to confirming the existence of an abnormal event, controlling the intelligent robot to disinfect and clear the area indicated by the abnormal event. This implementation can monitor and detect biological samples in the laboratory from multiple angles.

Description

Technical Field

[0001] The present application relates to the field of biological sample monitoring, and specifically to a biological sample monitoring method and device based on the Internet of Things. Background Art

[0002] Biological samples are often dangerous and confidential, especially in blood, vaccines, and medicines. There are extremely strict requirements for monitoring biological samples in laboratories. At present, the monitoring method commonly used for biological samples is to monitor whether there are abnormal people entering the laboratory through cameras installed in the aisles outside the laboratory. However, the above-mentioned monitoring method for biological samples usually has the following problems: monitoring is only carried out through a camera device, the monitoring angle is single, and it is impossible to monitor whether the biological samples in the laboratory are leaked, which is easy to cause safety hazards. Summary of the invention

[0003] The content of this application is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this application is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0004] Some embodiments of the present application propose a biological sample monitoring method, a computer device, and a computer-readable storage medium based on the Internet of Things to solve the technical problems mentioned in the above background technology section.

[0005] In a first aspect, some embodiments of the present application provide a biological sample monitoring method based on the Internet of Things, which is applied to a biological sample laboratory, wherein at least one detection device and a monitoring device are provided in the biological sample laboratory, and the method comprises: for each storage device included in the storage device cluster, performing the following processing steps: in response to receiving at least one monitoring video of the biological sample laboratory collected by the monitoring device, for each monitoring video in the at least one monitoring video, performing the following processing steps: performing feature extraction on each frame image of the monitoring video to obtain an image feature sequence, wherein one monitoring video corresponds to one channel in the biological sample laboratory, and one detection device corresponds to one channel in the biological sample laboratory; performing abnormal event detection on the image feature sequence to generate an abnormal event detection result; determining whether there is an abnormal event detection result that meets an abnormal condition among the generated abnormal event detection results, Among them, the abnormal condition is: the abnormal event detection result indicates that the biological sample falls on the channel; in response to determining that there is an abnormal event detection result that meets the abnormal condition, for each abnormal event detection result that meets the abnormal condition, the following detection steps are performed: the detection device corresponding to the above abnormal event detection result is determined as the target detection device; the above target detection device is controlled to collect the air composition information of the corresponding channel in real time; in response to determining that the above air composition information contains abnormal component information, the channel corresponding to the above target detection device is determined as an abnormal channel; the associated intelligent robot is controlled to move to the above abnormal channel, and the abnormal event indicated by the above abnormal event detection result is confirmed; in response to confirming the existence of the above abnormal event, the above intelligent robot is controlled to disinfect and clear the area indicated by the above abnormal event, and generate biological sample leakage information, and send the biological sample leakage information to the biological sample monitoring and management terminal.

[0006] In a second aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the method described in any implementation of the first aspect is implemented.

[0007] In a third aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, wherein when the computer program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0008] The above-mentioned embodiments of the present application have the following beneficial effects: the present application can monitor and detect biological samples in the laboratory from multiple angles to avoid safety hazards caused by leakage / dropping and damage of biological samples. First, in response to receiving at least one monitoring video of the biological sample laboratory collected by the monitoring device, for each monitoring video in the at least one monitoring video, the following processing steps are performed: feature extraction is performed on each frame of the above-mentioned monitoring video to obtain an image feature sequence, wherein one monitoring video corresponds to a channel in the biological sample laboratory, and one detection device corresponds to a channel in the biological sample laboratory; abnormal event detection is performed on the above-mentioned image feature sequence to generate an abnormal event detection result. Thus, each channel in the laboratory can be monitored by the monitoring device to determine whether there is a biological sample drop leakage. Next, it is determined whether there is an abnormal event detection result that meets the abnormal condition among the generated abnormal event detection results, wherein the abnormal condition is: the abnormal event detection result indicates that the biological sample falls on the channel. Then, in response to determining that there is an abnormal event detection result that satisfies the abnormal condition, for each abnormal event detection result that satisfies the abnormal condition, the following detection steps are performed: determining the detection device corresponding to the abnormal event detection result as the target detection device; controlling the target detection device to collect the air composition information of the corresponding channel in real time; in response to determining that the air composition information has abnormal component information, determining the channel corresponding to the target detection device as an abnormal channel. Thus, the leakage concentration of biological samples in the air can be analyzed to avoid direct manual contact. Finally, the associated intelligent robot is controlled to move to the abnormal channel, and the abnormal event indicated by the abnormal event detection result is confirmed; in response to confirming the existence of the abnormal event, the intelligent robot is controlled to perform disinfection and removal processing on the area indicated by the abnormal event, and generate biological sample leakage information, and send the biological sample leakage information to the biological sample monitoring and management terminal. Thus, the area where the biological sample is leaked can be disinfected to avoid safety hazards caused by leakage / falling and damage of biological samples. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The above and other features, advantages and aspects of the embodiments of the present application will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar figure labels represent the same or similar elements. It should be understood that the drawings are schematic and that the components and elements are not necessarily drawn to scale.

[0010] Figure 1 is a flow chart of some embodiments of the biological sample monitoring method based on the Internet of Things according to the present application;

[0011] Figure 2 is a schematic diagram of a computer device suitable for implementing some embodiments of the present application;

[0012] Figure 3 This is a flowchart illustrating an application scenario of the biological sample monitoring method based on the Internet of Things according to the present application. DETAILED DESCRIPTION

[0013] Embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present application. It should be understood that the drawings and embodiments of the present application are only for exemplary purposes and are not intended to limit the scope of protection of the present application.

[0014] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other.

[0015] It should be noted that the concepts such as "first" and "second" mentioned in this application are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0016] It should be noted that the modifications of "one" and "plurality" mentioned in the present application are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0017] The names of the messages or information exchanged between multiple devices in the embodiments of the present application are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0018] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments.

[0019] Figure 1 The flowchart of some embodiments of the biological sample monitoring method based on the Internet of Things according to the present application is shown. The process 100 of some embodiments of the biological sample monitoring method based on the Internet of Things according to the present application is shown. The biological sample monitoring method based on the Internet of Things is applied to a biological sample laboratory, in which at least one detection device and a monitoring device are set, and includes the following steps:

[0020] Step 101, in response to receiving at least one monitoring video of a biological sample laboratory collected by a monitoring device, for each monitoring video in the at least one monitoring video, perform the following processing steps:

[0021] Step 1011, extract features from each frame of the surveillance video to obtain an image feature sequence.

[0022] In some embodiments, the execution subject (e.g., a computing device) of the method for monitoring biological samples based on the Internet of Things can extract features from each frame of the above-mentioned monitoring video to obtain an image feature sequence. Among them, one monitoring video corresponds to a channel in the biological sample laboratory, and one detection device corresponds to a channel in the biological sample laboratory. The biological sample laboratory may refer to a laboratory where various biological samples are stored, and may include multiple channels, with shelves for storing biological samples on both sides of the channels. The biological samples may be placed in glass containers. The detection device may refer to an air component detection instrument arranged in the channel of the biological sample laboratory for detecting air components, or may refer to a temperature sensor for detecting the ambient temperature. The monitoring device may refer to a camera device deployed in a channel of the biological sample laboratory, which is used to monitor whether there are biological samples falling / damaged in the channel.

[0023] For example, the execution subject may first extract video frames, thereby treating each frame of the video image as an independent image. For each image, the execution subject may use a pre-trained image extraction model to extract features of the image, thereby obtaining image features of the image. Among them, the graphic extraction model may be any machine learning model with image feature extraction function, such as a convolutional neural network (CNN). CNN is a deep learning model that is particularly suitable for processing data with a grid structure, such as images and videos. CNN generally extracts and learns the features of data through convolution operations, pooling operations, and fully connected layers. The training process of the graphic extraction model will not be repeated here.

[0024] It should be noted that the various devices in the biological sample laboratory are interconnected through the Internet of Things, so that the execution entity can directly control the various smart devices in the laboratory.

[0025] Step 1012: Perform abnormal event detection on the above image feature sequence to generate an abnormal event detection result.

[0026] In some embodiments, the above-mentioned execution entity may perform abnormal event detection on the above-mentioned image feature sequence to generate an abnormal event detection result. For example, the image feature sequence may be input into a pre-trained abnormal event detection model to obtain an abnormal event detection result. The abnormal event detection model may be a pre-trained neural network model that takes an image feature sequence as input and takes an abnormal event detection result as output. For example, the abnormal event detection result may indicate whether a biological sample has fallen / broken in the image. For example, the abnormal event detection model may be an AIGC diffusion model, Delving into the Trajectory Long-tail Distribution for Muti-object Tracking, SAFDNet, a YOLOv7 model, and the like.

[0027] The abnormal event detection model can be trained through the following steps:

[0028] The first step is to obtain a biological sample image training sample set, wherein the biological sample image feature training sample includes: a sample biological sample image and a sample label.

[0029] The second step is to determine the initial abnormal event detection model. The initial abnormal event detection model includes: an initial biological sample image feature extraction network, an initial multi-level biological sample image hybrid autoencoder network, and an initial abnormal event recognition network. For example, the initial biological sample image feature extraction network can be a convolutional neural network (CNN), a recurrent neural network (RNN), a long short-term memory network (LSTM), etc.

[0030] The second step may include the following sub-steps:

[0031] The first sub-step is to determine the initial biological sample image feature extraction network.

[0032] The second sub-step is to determine the initial multi-level biological sample image hybrid autoencoder network. The initial multi-level biological sample image hybrid autoencoder network includes: an initial encoding network (encoder) and an initial decoding network (decoder). The initial encoding network includes: an initial biological sample image feature decoupling network (including an autoencoder network and an LSTM network) and an initial biological sample image feature fusion network (VAE (Variational AutoEncoder, variational encoder). The initial biological sample image feature fusion network includes: an initial fusion network and an initial re-parameterization network. The initial fusion network can be a feature pyramid network (FPN) or a self-attention mechanism (Self-AttentionMechanism) network. The initial re-parameterization network can include: DyRep (Dynamic Re-parameterization) and ACNet (Asymmetric Convolution Net).

[0033] The third sub-step is to determine the initial abnormal event recognition network.

[0034] The third sub-step may include:

[0035] 1. Determine an abnormal event perception classification network. For example, the abnormal event perception classification network can be a multi-layer perception classifier based on KAN (Kolmogorov-Arnold Networks, a new neural network architecture).

[0036] 2. Initialize the abnormal event perception and classification network to generate an initial abnormal event perception and classification network. The abnormal event perception and classification network can be initialized by using a Kaiming initialization algorithm to generate an initial abnormal event perception and classification network.

[0037] 3. Perform noise processing on the initial abnormal event perception classification network to generate a noise abnormal event perception classification network. The initial abnormal event perception classification network can be subjected to noise processing by a Gaussian noise algorithm to generate a noise abnormal event perception classification network.

[0038] 4. Perform parameter regularization processing on the above-mentioned noise abnormal event perception classification network to generate an abnormal event perception classification regularized network. The above-mentioned noise abnormal event perception classification network can be parameter regularized by an L1 regularization (L1 norm regularization) algorithm to generate an abnormal event perception classification regularized network.

[0039] 5. Perform activation adjustment processing on the above-mentioned abnormal event perception classification regularization network to generate an initial abnormal event recognition network. The above-mentioned abnormal event perception classification regularization network can be activated and adjusted through an activation function to generate an initial abnormal event recognition network.

[0040] The fourth sub-step is to fuse the initial biological sample image feature extraction network, the initial multi-level biological sample image hybrid autoencoder network, and the initial abnormal event recognition network to generate an initial abnormal event detection model.

[0041] The third step is to select a target biological sample image training sample from the biological sample image training sample set. A biological sample image training sample can be randomly selected from the biological sample image training sample set as the target biological sample image training sample.

[0042] In the fourth step, the sample biological sample images included in the target biological sample image training samples are input into the initial biological sample image feature extraction network to obtain the initial biological sample image feature information.

[0043] The fifth step is to input the initial biological sample image feature information into the initial multi-level biological sample image hybrid autoencoder network to obtain the initial multi-level biological sample image feature information.

[0044] In the sixth step, the initial multi-level biological sample image feature information is input into the initial abnormal event recognition network to obtain the initial abnormal event recognition result.

[0045] In the seventh step, based on a preset loss function, a loss value between the initial abnormal event recognition result and the sample label included in the target biological sample image training sample is determined. For example, the loss function may be: mean square error loss (MSE Loss) function, cross-entropy loss (Cross-Entropy Loss) function, ‌mean absolute error (MAE)‌ function.

[0046] In the eighth step, in response to determining that the loss value is less than or equal to the preset loss value, the initial abnormal event detection model is determined as the trained abnormal event detection model.

[0047] Therefore, the present invention constructs a multi-level biological sample image feature hybrid autoencoder network, which can fully capture the multi-level biological sample image information in speech and enhance the efficiency and accuracy of the autoencoder in feature untangling. In addition, a multi-layer biological sample image recognition network is also constructed, which can help the model capture complex nonlinear relationships in the data and improve the accuracy of abnormal event recognition.

[0048] Step 102: determine whether there is an abnormal event detection result that meets the abnormal condition among the generated abnormal event detection results.

[0049] In some embodiments, the execution subject may determine whether there is an abnormal event detection result satisfying an abnormal condition among the generated abnormal event detection results, wherein the abnormal condition is: the abnormal event detection result indicates that the biological sample has fallen on the channel.

[0050] Step 103, in response to determining that there is an abnormal event detection result that satisfies the abnormal condition, for each abnormal event detection result that satisfies the abnormal condition, perform the following detection steps:

[0051] Step 1031: determine the detection device corresponding to the abnormal event detection result as the target detection device.

[0052] In some embodiments, the execution entity may determine the detection device corresponding to the abnormal event detection result as the target detection device.

[0053] Step 1032, controlling the target detection device to collect air composition information of the corresponding channel in real time.

[0054] In some embodiments, the execution subject may control the target detection device to collect the air composition information of the corresponding channel in real time. For example, the target detection device may be controlled to collect the air composition information of the channel where the current target detection device is located.

[0055] Step 1033, in response to determining that the air composition information contains abnormal component information, determining the channel corresponding to the target detection device as an abnormal channel.

[0056] In some embodiments, the execution subject may determine the channel corresponding to the target detection device as an abnormal channel in response to determining that the air composition information contains abnormal component information. The abnormal component information may indicate that the component of the biological sample in the air is greater than or equal to a preset concentration.

[0057] Step 1034, controlling the associated intelligent robot to move to the above-mentioned abnormal channel, and confirming the abnormal event indicated by the above-mentioned abnormal event detection result.

[0058] In some embodiments, the execution subject may control the associated intelligent robot to move to the abnormal channel and confirm the abnormal event indicated by the abnormal event detection result. For example, after the intelligent robot moves to the area indicated by the abnormal event detection result, the camera of the intelligent robot may again collect and detect images of the area indicated by the abnormal event detection result to determine whether there is an event in which the biological sample falls and is damaged.

[0059] It should be noted that intelligent robots are usually robots designed to perform various tasks and provide services in laboratory environments. These robots usually have advanced technologies such as artificial intelligence, autonomous navigation, voice recognition, and visual recognition. Here, robots, as devices with interactive capabilities, can be used to obtain on-site images at a closer distance.

[0060] In an actual application scenario, the execution subject can control the associated intelligent robot to move to the abnormal channel through the following steps:

[0061] In the first step, in response to the straight-line distance between the above-mentioned intelligent robot and the indoor obstacle in the moving direction being less than the first preset distance, the above-mentioned intelligent robot is subjected to deceleration processing and sound and light alarm processing. Among them, the above-mentioned intelligent robot has at least one pre-configured laser scanning distance measuring device that supports distance measurement with a target scanning range, and the straight-line distance is obtained based on real-time scanning and distance measurement of the laser scanning distance measuring device. The moving direction can be the driving direction of the intelligent robot on the laboratory channel. The driving obstacle can be an obstacle that affects normal driving detected by the intelligent robot when driving on the laboratory channel. For example, the driving obstacle can be a missing box. The first pre-trial distance can be a preset distance. For example, the first pre-trial distance can be 5m. The intermittent sound and light alarm processing can be an intermittent sound and light alarm. The time interval corresponding to the intermittent can be set for the intelligent robot. For example, the time interval can be 10 seconds. Among them, the above-mentioned intelligent robot has at least one pre-configured laser scanning distance measuring device that supports distance measurement with a target scanning range, and the vehicle distance is obtained based on real-time scanning and distance measurement of the laser scanning distance measuring device. Among them, the target scanning range can be pre-set in the laser scanning distance measuring device. For example, the target scanning range can be set to a scanning range with a fan shape and a radius of 10 meters in the laser scanning distance measuring device. The laser scanning distance measuring device can be a device that performs scanning distance measurement based on laser technology. The sound and light alarm can be an alarm process by sound playback and light display. Here, the intelligent robot is prevented from colliding with the driving obstacle by driving deceleration. The sound and light alarm process is used to inform relevant personnel that the intelligent robot has a driving obstacle during driving.

[0062] In the second step, in response to the straight-line distance between the intelligent robot and the indoor obstacle being less than a second preset distance during the deceleration process, the intelligent robot is stopped and continuously sounded and lighted. The second preset distance may be a preset distance. The second preset distance is less than the first preset distance. For example, the second preset distance may be 2 m. The continuous sounded and lighted alarm process may be continuous sounded and lighted alarm.

[0063] In the third step, in response to the intelligent robot detecting that the straight-line distance between the intelligent robot and the indoor obstacle is greater than the third preset distance, the intelligent robot is controlled to move in the above-mentioned direction, start the driving process and cancel the sound and light alarm process. The third preset distance may be a preset value. For example, the third preset distance may be a value of the same magnitude as the first preset distance, or a value of the same magnitude as the second preset distance, or a value greater than the first preset distance. The specific size of the third preset distance may be preset based on experience.

[0064] In an actual application scenario, the execution subject may confirm the abnormal event indicated by the abnormal event detection result through the following steps:

[0065] The first step is to use the camera installed on the above-mentioned intelligent robot to collect the video image of the above-mentioned abnormal channel, and to identify and analyze the above-mentioned video image to confirm whether there is an abnormal event indicated by the above-mentioned abnormal event detection result.

[0066] The second step is to use the thermal imaging technology provided on the above-mentioned intelligent robot to collect the infrared thermal image of the above-mentioned abnormal channel, and analyze the above-mentioned infrared thermal image to confirm whether there is an abnormal event indicated by the above-mentioned abnormal event detection result.

[0067] Step 1035, in response to confirming the existence of the above-mentioned abnormal event, control the above-mentioned intelligent robot to disinfect and clear the area indicated by the above-mentioned abnormal event, generate biological sample leakage information, and send the biological sample leakage information to the biological sample monitoring and management terminal.

[0068] In some embodiments, the execution subject may, in response to confirming the existence of the abnormal event, control the intelligent robot to perform disinfection and cleaning on the area indicated by the abnormal event, generate biological sample leakage information, and send the biological sample leakage information to the biological sample monitoring and management terminal. For example, after confirming the existence of the abnormal event, biological sample leakage information indicating the leakage of laboratory biological samples may be automatically generated.

[0069] In an actual application scenario, the execution subject can control the intelligent robot to disinfect and clear the area indicated by the abnormal event through the following steps:

[0070] The first step is to determine whether the gas disinfection chamber of the intelligent robot stores a gas disinfectant corresponding to the air composition information. The gas disinfectant may be a disinfectant corresponding to the leaked biological sample. The gas disinfection chamber may refer to a chamber in the intelligent robot that stores the disinfectant.

[0071] In the second step, in response to determining that the gas disinfectant corresponding to the gas analysis result is stored in the gas disinfection chamber, the disinfectant spraying device on the intelligent robot is controlled to spray the gas disinfectant on the area indicated by the abnormal event. The disinfectant spraying device may refer to a disinfectant sprayer provided on the intelligent robot. For example, the poison spraying device may be controlled to spray the disinfectant on the area.

[0072] The third step is to control the mechanical arm of the intelligent robot that is equipped with the detection cotton swab to collect biological samples from the area indicated by the abnormal event to obtain biological sample collection information.

[0073] In the fourth step, in response to determining that the biological sample collection information does not meet the preset disinfection conditions, the high-temperature disinfection device on the intelligent robot is controlled to perform a high-temperature disinfection operation on the area indicated by the abnormal event. For example, the high-temperature disinfection device may refer to a disinfection device that sprays high-temperature steam. The biological sample collection information may indicate the component density of the biological sample in the disinfected area. The preset disinfection condition may refer to: the component density of the biological sample in the disinfected area is less than or equal to the preset density.

[0074] The fourth step may include:

[0075] In the first sub-step, in response to detecting that at least two heating devices in the high-temperature disinfection device on the intelligent robot are activated, the temperature information detected by each temperature detection component corresponding to the at least two heating devices is obtained to obtain each temperature information. The number of heating devices included in the heating device set is greater than or equal to two, and each temperature detection component corresponds to the at least two heating devices.

[0076] Among them, each heating device in the above-mentioned heating device set can be a device for heating the water in the high-temperature disinfection device into high-temperature steam. For example, the above-mentioned heating device can be a heater. It can be understood that the above-mentioned at least two heating devices can include at least two heating devices arranged at different positions. The above-mentioned temperature detection component can be a component for detecting the temperature of steam. For example, the above-mentioned temperature detection component can be a temperature sensor. The above-mentioned individual temperature detection components correspond to the above-mentioned at least two heating devices. As an example, the temperature detection components of the above-mentioned individual temperature detection components can correspond one-to-one to the heating devices in the above-mentioned at least two heating devices. As another example, one of the temperature detection components in the above-mentioned individual temperature detection components can also correspond to two or more heating devices in the above-mentioned at least two heating devices. The above-mentioned temperature detection component can be arranged inside the corresponding heating device. The above-mentioned temperature information can be the temperature value detected by the above-mentioned temperature detection component.

[0077] The second sub-step is to control at least two heating devices on the intelligent robot to perform heating power adjustment operations according to the above-mentioned temperature information. First, in response to determining that the temperature information corresponding to the above-mentioned one heating device is less than the preset temperature threshold, the above-mentioned execution subject can adjust the heating power of the above-mentioned one heating device to a preset single heating power. Among them, the above-mentioned preset single heating power can be a heating power preset to increase the water temperature in the high-temperature disinfection device when only one heating device is turned on. The preset single heating power is greater than the combined single heating power. Then, in response to determining that the temperature information corresponding to the above-mentioned one heating device is greater than or equal to the preset temperature threshold, the above-mentioned execution subject can adjust the heating power of the above-mentioned one heating device to a preset single constant temperature heating power. The above-mentioned preset single constant temperature heating power can be a heating power preset to keep water warm when only one heating device is turned on.

[0078] The third sub-step is, in response to determining that the heating power adjustment is completed, controlling the high-temperature disinfection device on the above-mentioned intelligent robot to spray high-temperature steam to the above-mentioned abnormal area.

[0079] Thus, the heating power of each heating device can be adjusted according to the actual temperature detected, so that the water temperature in the high-temperature disinfection device is more uniform. Thus, further disinfection can be carried out by high-temperature steam.

[0080] In an actual application scenario, the above-mentioned execution subject can send the biological sample leakage information to the biological sample monitoring and management terminal through the following steps:

[0081] The first step is to determine whether there is a network connection between the above-mentioned intelligent robot and the biological sample monitoring application server. For example, the intelligent robot can send a network test message to the biological sample monitoring application server. If the network test reply message sent by the biological sample monitoring application server is received, it can be determined that there is a network connection with it. If the network test reply message sent by the biological sample monitoring application server is not received, it can be determined that there is no network connection (i.e., the network connection fails).

[0082] The second step is to send the biological sample leakage information to the corresponding biological sample monitoring application through the biological sample monitoring application server in response to determining that there is a network connection. The biological sample monitoring application is installed on the biological sample monitoring management terminal.

[0083] In the third step, in response to determining that the network connection fails, the target biological sample manager information is selected from the pre-stored biological sample manager information table. The biological sample manager information includes manager contact information. The manager contact information may include: mobile phone number, account number in chat software, etc.

[0084] The fourth step is to send the biological sample leakage information to the user terminal indicated by the manager contact information in the target biological sample manager information. The user terminal is installed with a biological sample monitoring application. The user can browse the biological sample leakage information on the application.

[0085] like Figure 3 The example illustrates an application scenario process diagram of the IoT-based biological sample monitoring method according to the present application. For example, after the detection equipment and the monitoring equipment detect an abnormal event, the intelligent robot can be controlled to confirm the abnormal event (discover abnormal inspection). After confirmation, an audible and visual alarm can be issued, and the user terminal can be notified. Afterwards, the disinfectant spraying equipment on the intelligent robot can be controlled to disinfect and remove the leaked sample.

[0086] The present application also provides a computer device 200. Figure 2 As shown, the computer device 200 includes: a bus 201, a processor 202, a memory 203 and a communication interface 204. The processor 202, the memory 203 and the communication interface 204 communicate with each other through the bus 201. The computer device 200 can be a server or a terminal device. It should be understood that the present application does not limit the number of processors and memories in the computer device 200.

[0087] The bus 201 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 The bus 201 is represented by only one line, but it does not mean that there is only one bus or one type of bus. The bus 201 may include a path for transmitting information between various components of the computer device 200 (for example, the memory 203, the processor 202, and the communication interface 204).

[0088] The processor 202 may include any one or more of a central processing unit (CPU), a graphics processing unit (GPU), a microprocessor (MP), or a digital signal processor (DSP).

[0089] The memory 203 may include a volatile memory, such as a random access memory (RAM). The memory 203 may also include a non-volatile memory, such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD).

[0090] The memory 203 stores executable program codes, and the processor 202 executes the executable program codes to respectively implement the functions of the aforementioned acquisition module, sampling module, determination module, and mixing module, thereby implementing the aforementioned method for monitoring biological samples based on the Internet of Things. That is, the memory 203 stores instructions for executing the aforementioned method for monitoring biological samples based on the Internet of Things.

[0091] The communication interface 204 uses a transceiver module such as, but not limited to, a network interface card or a transceiver to implement communication between the computer device 200 and other devices or a communication network.

[0092] An embodiment of the present application also provides a chip, which includes a processor and a data interface. The processor reads instructions stored in a memory through the data interface to execute the above-mentioned method for biological sample monitoring based on the Internet of Things.

[0093] The embodiment of the present application also provides a computer-readable storage medium. The above-mentioned computer-readable storage medium can be any available medium that can be stored by a computing device or a data storage device such as a data center containing one or more available media. The above-mentioned available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state hard disk). The computer-readable storage medium includes instructions, and the above-mentioned instructions instruct the computing device to execute the above-mentioned method for monitoring biological samples based on the Internet of Things.

[0094] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0095] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the protection scope of the technical solutions of the embodiments of the present application.

Claims

1. A biological sample monitoring method based on the Internet of Things, applied to a biological sample laboratory, wherein at least one detection device and a monitoring device are provided in the biological sample laboratory, the method comprising: In response to receiving at least one monitoring video of the biological sample laboratory collected by the monitoring device, for each monitoring video in the at least one monitoring video, the following processing steps are performed: Extracting features from each frame of the monitoring video to obtain an image feature sequence, wherein one monitoring video corresponds to one channel in the biological sample laboratory, and one detection device corresponds to one channel in the biological sample laboratory; Performing abnormal event detection on the image feature sequence to generate an abnormal event detection result; Determine whether there is an abnormal event detection result satisfying an abnormal condition among the generated abnormal event detection results, wherein the abnormal condition is: the abnormal event detection result indicates that the biological sample falls on the channel; In response to determining that there is an abnormal event detection result that satisfies the abnormal condition, for each abnormal event detection result that satisfies the abnormal condition, the following detection steps are performed: Determine the detection device corresponding to the abnormal event detection result as the target detection device; Control the target detection device to collect air composition information of the corresponding channel in real time; In response to determining that the air composition information contains abnormal composition information, determining the channel corresponding to the target detection device as an abnormal channel; Controlling the associated intelligent robot to move to the abnormal channel, and confirming the abnormal event indicated by the abnormal event detection result; In response to confirming the existence of the abnormal event, controlling the intelligent robot to perform disinfection and clearing processing on the area indicated by the abnormal event, and generating biological sample leakage information, and sending the biological sample leakage information to the biological sample monitoring and management terminal; The step of sending the biological sample leakage information to the biological sample monitoring and management terminal includes: Determine whether there is a network connection between the intelligent robot and the biological sample monitoring application server; In response to determining that there is a network connection, the biological sample leakage information is sent to the corresponding biological sample monitoring application through the biological sample monitoring application server, wherein the biological sample monitoring application is installed on the biological sample monitoring management terminal.

2. The method for monitoring biological samples based on the Internet of Things according to claim 1, characterized in that: The method further comprises: In response to determining that the network connection fails, selecting target biological sample manager information from a pre-stored biological sample manager information table, wherein the biological sample manager information includes manager contact information; According to the manager contact information in the target biological sample manager information, the biological sample leakage information is sent to a user terminal indicated by the manager contact information.

3. The method for monitoring biological samples based on the Internet of Things according to claim 1, characterized in that: The confirming the abnormal event indicated by the abnormal event detection result includes: Using a camera installed on the intelligent robot, collecting a video image of the abnormal channel, and performing recognition analysis on the video image to confirm whether there is an abnormal event indicated by the abnormal event detection result; Or, the thermal imaging technology provided on the intelligent robot is used to collect an infrared thermal image of the abnormal channel, and the infrared thermal image is analyzed to confirm whether there is an abnormal event indicated by the abnormal event detection result.

4. The method for monitoring biological samples based on the Internet of Things according to claim 1, characterized in that: The controlling the intelligent robot to perform disinfection and clearing processing on the area indicated by the abnormal event includes: Determining whether a gas disinfectant corresponding to the air composition information is stored in the gas disinfection chamber of the intelligent robot; In response to determining that a gas disinfectant corresponding to the gas analysis result is stored in the gas disinfection chamber, the disinfectant spraying device on the intelligent robot is controlled to perform a gas disinfectant spraying operation on the area indicated by the abnormal event.

5. A computer device, wherein: The computer device comprises a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium, wherein: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images