Sterile experiment whole process monitoring method and device

Abstract

The invention provides a whole-process monitoring method and device for a sterile experiment, and belongs to the technical field of sterile monitoring, and the method comprises the steps: carrying out the feature extraction of operation actions of target equipment and target personnel, and obtaining a real-time operation specification which comprises the operation sequence of the target equipment and the operation sequence of the target personnel; based on the deviation between the real-time operation specification and the standard operation specification, the sterile test operation process is evaluated, and the operation sequence of the target equipment and the operation sequence of the target personnel are both provided with the corresponding standard operation specification. According to the sterile experiment whole-process monitoring method and device provided by the invention, the reliability and the success rate of the experiment can be ensured.

Description

Technical Field

[0001] The present application belongs to the field of sterile monitoring technology, and more specifically, relates to a method and device for monitoring the entire process of a sterile experiment. Background Art

[0002] In the field of sterile testing, traditional monitoring methods rely heavily on manual observation, which is highly subjective and prone to omissions, making it difficult to comprehensively and accurately determine whether operational procedures are standardized. The lack of a systematic, real-time feature extraction and evaluation mechanism for the operating sequence of operating equipment and the sequence of experimental personnel prevents timely detection of operational deviations, making experiments susceptible to improper equipment operation and human error, increasing the risk of experimental failure and wasting time and resources. Summary of the Invention

[0003] The purpose of this application is to provide a method and device for monitoring the entire process of sterility experiments to ensure the reliability and success rate of the experiments.

[0004] In a first aspect of an embodiment of the present application, a method for monitoring the entire process of a sterile experiment is provided, comprising: extracting features of operating actions of a target device and a target person to obtain a real-time operating specification, wherein the real-time operating specification includes an operating sequence of the target device and an operating sequence of the target person; The sterility test operation process is evaluated based on the deviation between the real-time operation specification and the standard operation specification. The operation sequence of the target equipment and the operation sequence of the target personnel are both provided with corresponding standard operation specifications.

[0005] A second aspect of the embodiments of the present application provides a full-process monitoring device for sterile experiments, comprising: A feature extraction module is used to extract features of the operation actions of the target device and the target person to obtain a real-time operation specification, wherein the real-time operation specification includes the operation sequence of the target device and the operation sequence of the target person; The operation process evaluation module is used to evaluate the sterility test operation process based on the deviation between the real-time operation specification and the standard operation specification. The operation sequence of the target equipment and the operation sequence of the target personnel are both provided with corresponding standard operation specifications.

[0006] The third aspect of the embodiments of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned sterile experiment full-process monitoring method are implemented.

[0007] In a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned sterility experiment full-process monitoring method are implemented.

[0008] The beneficial effects of the sterile experiment full-process monitoring method and device provided by the embodiment of the present application are as follows: the embodiment of the present application evaluates the sterile test operation process by extracting features of the target equipment operation sequence and the target personnel operation sequence respectively, and comparing the deviations with the standard operation specifications. On the one hand, it can timely detect deviations in the equipment operation sequence, avoid affecting the experimental process and results due to improper equipment operation, and ensure that the equipment operates according to specifications; on the other hand, it can detect irregularities in the personnel operation sequence, reduce the risk of contamination introduced by human errors, and ensure the sterile environment of the experiment. Overall, it improves the comprehensiveness, accuracy and timeliness of sterile experiment monitoring, and effectively guarantees the reliability and success rate of the experiment. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0010] Figure 1 A schematic diagram of a process for monitoring the entire sterility experiment process according to an embodiment of the present application; Figure 2 This is a structural block diagram of a sterility experiment full-process monitoring device provided in one embodiment of the present application; Figure 3 A schematic block diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0011] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0012] In order to make the purpose, technical solutions and advantages of this application clearer, specific embodiments will be described below with reference to the accompanying drawings.

[0013] Please refer to Figure 1 , Figure 1 A schematic diagram of a method for monitoring the entire sterility experiment process according to an embodiment of the present application is provided, wherein the method includes: S101: extracting features of the operation actions of the target device and the target person to obtain a real-time operation specification, which includes the operation sequence of the target device and the operation sequence of the target person.

[0014] In this embodiment, the target equipment refers to various instruments and devices used in the sterile experiment process, such as automatic quantitative culture medium addition devices, electric lifting platforms, robotic arms, etc. The target personnel are personnel involved in the sterile experiment operation.

[0015] In this embodiment, when extracting features from the target device's operating actions, various types of sensors, such as microswitches, proximity sensors, and pressure sensors, can be installed at key operating locations on the target device. These sensors can capture changes in the state of the target device's components. For example, a microswitches can detect when a button is pressed or released, a proximity sensor can determine whether a component is near a specific location, and a pressure sensor can sense pressure changes to determine the open or closed state of a valve. When the target device is operated, the sensors in the corresponding locations are triggered, generating electrical or digital signals.

[0016] In this embodiment, a precise timestamp is recorded for each sensor-generated operation signal. For example, in a sterile experiment, when the peristaltic pump start button is pressed, the microswitch sensor emits a signal, recording the time at that moment. All operation signals are sorted and organized based on the order of the timestamps, determining the order of each operation on the target device and thus forming the target device's operation sequence.

[0017] For example, through timestamp sorting, we can know the operating sequence of the device: first open the feed valve of the culture medium storage tank, then start the peristaltic pump for transportation, and finally close the discharge valve.

[0018] In this embodiment, when extracting features from the target person's operating actions, multiple cameras can be arranged in the sterile experimental operation area to capture the target person's operating behavior from different angles in all directions, and obtain image and video data containing information such as the target person's limb movements, gesture changes, and body posture.

[0019] In this embodiment, a deep learning convolutional neural network can be used to extract features from image data to identify various body parts and key joints. A recurrent neural network can then analyze the time series information of these joints to identify different operating actions, such as picking up an instrument, putting down a sample, or turning a knob. In this embodiment, the identified operating actions can be arranged in chronological order to form an operating sequence for the target person.

[0020] For example, the experimenter first reaches out to pick up the pipette, then inserts the pipette into the sample container to absorb the liquid, and then moves it over the culture dish to release the liquid. The actions arranged in time sequence form an operation sequence, which becomes another part of the real-time operation specification.

[0021] S102: Evaluate the sterility test operation process based on the deviation between the real-time operation specifications and the standard operation specifications. The operation sequence of the target equipment and the operation sequence of the target personnel are equipped with corresponding standard operation specifications.

[0022] In this embodiment, the standard operating specifications of the target device are operating guidelines to ensure the success of the experiment and maintain a sterile environment, which can be obtained based on the standard requirements of the sterile experiment, the design purpose of the device, and long-term practice summary.

[0023] This embodiment can represent the operation sequence as a directed graph based on a graph matching algorithm, where nodes represent operation steps and edges represent the order of the operation steps. By calculating the difference between the real-time operation sequence graph and the standard operation sequence graph, an operation sequence deviation value is obtained. For example, if the vacuum pump is started first and the filter membrane is installed later in the real-time operation, this differs from the standard sequence, and the deviation value calculated using the graph matching algorithm will be larger.

[0024] In this embodiment, an operation sequence deviation threshold can be set and the calculated deviation value can be compared with the deviation threshold. If the deviation value is less than or equal to the deviation threshold, it indicates that the operation sequence of the target device basically complies with the standard operating specifications and the experimental operation has a low risk in terms of the device operation sequence. If the deviation value is greater than the deviation threshold, it is determined that the operation sequence of the target device does not comply with the specifications.

[0025] In this embodiment, the target personnel's standard operating procedures are the actions that the target personnel should perform at each stage of the experiment and their correct sequence. The standard operating sequence for the target personnel is formulated by combining the sterile laboratory operating procedures, the scientific rationality of the personnel's operations, and the principle of avoiding the introduction of contamination.

[0026] This embodiment can compare the target person's real-time operation sequence with the standard operation sequence based on a similarity assessment method. For example, a dynamic time warping algorithm can be used. The dynamic time warping algorithm can find the optimal matching path between the target person's real-time operation sequence and the standard operation sequence while taking time expansion into account, and calculate the similarity score between the target person's real-time operation sequence and the standard operation sequence based on the optimal matching path.

[0027] In this embodiment, a similarity threshold can be set and the calculated similarity score can be compared with the similarity threshold. If the similarity score is higher than the similarity threshold, it indicates that the target person's operation sequence is close to the standard operation sequence and the operation is relatively standard. If the similarity score is lower than the similarity threshold, it indicates that the target person's operation sequence is not standard and the operation needs to be adjusted and standardized.

[0028] The target equipment operation sequence deviation evaluation results and the target personnel operation sequence deviation evaluation results are comprehensively evaluated. In this embodiment, different weights can be assigned to the target equipment operation sequence deviation and the target personnel operation sequence deviation according to the characteristics and requirements of the experiment to reflect the importance of their impact on the sterility test operation process.

[0029] For example, for experiments that are highly dependent on equipment, the weight of the target equipment operation sequence deviation may be set higher; while for experiments that are more critical to manual operation, the weight of the target personnel operation sequence deviation may be set higher. Through weighted calculation, a comprehensive deviation index is obtained. Based on the comprehensive deviation index, the sterility test operation process is comprehensively evaluated to determine whether the operation process meets the requirements of the sterility test and the degree of non-compliance. Comprehensive feedback information is provided to the experimenter so that timely measures can be taken to improve the operation and ensure the smooth progress of the sterility test.

[0030] From the above, it can be concluded that this embodiment evaluates the sterility test operation process by extracting features from the target equipment operation sequence and the target personnel operation sequence respectively, and comparing the deviations with the standard operating specifications. On the one hand, it can promptly detect deviations in the equipment operation sequence, avoid affecting the experimental process and results due to improper equipment operation, and ensure that the equipment operates according to specifications; on the other hand, it can detect irregularities in the personnel operation sequence, reduce the risk of contamination introduced by human errors, and ensure the sterile environment of the experiment. Overall, it improves the comprehensiveness, accuracy and timeliness of sterility experiment monitoring, and effectively guarantees the reliability and success rate of the experiment.

[0031] In one embodiment of the present application, feature extraction is performed on the operation actions of the target device and the target person to obtain real-time operation specifications, including: The key point data of the target device is used as a network node. The key point data is used to sense the operation of the target device. The key point data includes operation type data and target device identification data; Build blockchain based on network nodes; Obtain the target device's operation record blocks based on blockchain; The operation record blocks are sorted based on the timestamp sequence to obtain the operation sequence of the target device.

[0032] In this embodiment, the operation type data is used to identify the specific operation performed by the device, such as turning it on, off, adjusting parameters, and other different types. The identification data is used to distinguish different devices, as there are different target devices in sterile experiments. When the target device performs an operation, the key point data can produce corresponding data changes. For example, the switching action of the target device can change the value of the operation type data from "off" to "on". At the same time, the target device identification data ensures accurate identification of which device has performed the operation, thereby sensing the operating state changes of the target device in real time.

[0033] In this embodiment, key point data is used as network nodes, and then the network nodes are connected to build a blockchain. Each block of the blockchain can store a certain amount of device operation-related information, and each block contains the hash value of the previous block, forming a chain structure to ensure the consistency of data.

[0034] Each time a target device performs an operation, changes in the corresponding key data trigger the generation of a new operation record block. This operation record block contains the operation type, target device identification, and the timestamp of the operation. The timestamp records the time each operation occurred. By analyzing the timestamps in the acquired operation record blocks, the order in which each operation occurred can be determined. All operation record blocks are sorted by timestamp order to determine the order in which the target device was operated.

[0035] For example, sequencing can be used to determine whether the target device performs a parameter adjustment operation first and then performs a startup operation, which serves as an operation sequence part in the real-time operation specification of the target device.

[0036] As can be seen from the above, this embodiment uses the target device's key point data as network nodes to build a blockchain, leveraging the blockchain's immutable and distributed storage characteristics to ensure the authenticity and reliability of operation records and enhance data security. By sorting the operation record blocks based on timestamps to obtain the operation sequence, the device operation process can be accurately restored.

[0037] In one embodiment of the present application, feature extraction is performed on the operation actions of the target device and the target person to obtain real-time operation specifications, further comprising: Perform feature fusion on the target person's gesture feature data to obtain the initial operation action. The target person's gesture feature data includes joint point coordinate sequence data and gesture acceleration data; The operation category of the target person's operation action is taken as the action space, and the initial operation action is taken as the state space; Build reinforcement learning models based on action space and state space; The target person's operation sequence is obtained based on the reinforcement learning model.

[0038] In this embodiment, gesture feature data is collected during the target person's operation. Joint coordinate sequence data is acquired through a camera using a human posture estimation algorithm, reflecting the spatial position and shape changes of the gesture. Gesture acceleration data is obtained using an accelerometer worn on a glove, reflecting the speed changes of the gesture. By fusion-processing the target person's gesture feature data, a comprehensive description of the target person's gestures is obtained, thereby deriving the initial operation action.

[0039] In this embodiment, the joint point coordinate sequence data and gesture acceleration data can be directly concatenated in terms of dimension. For example, if the joint point coordinate sequence data is an n×m matrix (n represents the number of time steps, and m represents the dimension of the joint point, such as 2D coordinates for 2D and 3D coordinates for 3D), and the gesture acceleration data is an n×k matrix (k represents the dimension of the accelerometer, generally 3 dimensions, corresponding to the x, y, and z axis accelerations, respectively), direct concatenation results in a new n×(m+k) matrix. This new matrix integrates the position and velocity change information of the gesture and serves as a feature representation of the initial operation action, which is then input into the subsequent model for processing.

[0040] In this embodiment, the target person's operation category, such as grabbing, placing, stirring, etc., is defined as the action space. The initial operation obtained through feature fusion is set as the state space, which can reflect the actual state of the target person's gesture at the current moment.

[0041] Based on the current state space (i.e., the initial action), an action category is selected from the action space as the output—that is, the action corresponding to the current gesture is predicted. The reinforcement learning model then receives a reward or penalty based on how well the actual action matches the prediction. If the prediction is accurate, a positive reward is given to encourage the model to continue making that choice in similar situations; if the prediction is incorrect, a negative penalty is given to prompt the model to adjust its strategy. Through repeated training, the reinforcement learning model gradually learns how to accurately select the corresponding action category from the action space based on different initial actions. After extensive training, the reinforcement learning model is able to accurately determine the action category based on the initial action input.

[0042] In practical applications, as the target person continues to operate, the reinforcement learning model can sequentially judge each initial action and output the corresponding action category. The action categories arranged in chronological order constitute the target person's action sequence. This action sequence is used to represent the target person's complete action flow during the sterile laboratory operation.

[0043] As can be seen from the above, this embodiment comprehensively captures the target person's gesture characteristics by fusing the joint coordinate sequence with gesture acceleration data to obtain the initial operation. Constructing a reinforcement learning model with the operation category as the action space and the initial operation as the state space allows the model to accurately judge the operation after training. The resulting target person's operation sequence is more accurate, which helps to accurately monitor personnel operations in sterile experiments, promptly detect irregularities, ensure that experiments are carried out according to standard procedures, and improve experimental success rate and reliability.

[0044] In one embodiment of the present application, the deviation between the real-time operation specification and the standard operation specification includes: a deviation between the operation sequence of the target personnel and the operation sequence of the standard personnel, and a deviation between the operation sequence of the target device and the operation sequence of the standard device; Deviations between the target personnel's operating sequence and the standard personnel's operating sequence include: The deviation between the target person's operation sequence and the standard person's operation sequence is calculated based on the similarity between the joint point coordinate sequence data and the standard joint point coordinate sequence data.

[0045] In this embodiment, the target person's hand gestures during the operation can be accurately represented by joint point coordinate sequence data. Joint point coordinate sequence data is used to represent the spatial position of each hand joint at different times, forming the dynamic changes of the hand gesture. Similarly, the standard joint point coordinate sequence data represents the ideal position changes of the hand joints during standard operation.

[0046] This embodiment can use a dynamic time warping algorithm to find the best matching path between the target person's joint point coordinate sequence and the standard joint point coordinate sequence. Because the actual operation and the standard operation have different time rhythms, but the movements are essentially similar, the dynamic time warping algorithm can effectively handle this situation. The similarity calculated based on the best matching path measures the degree of closeness between the two. The higher the similarity, the closer the target person's operation sequence is to the standard sequence, and the smaller the deviation; conversely, the lower the similarity, the greater the deviation.

[0047] As can be seen from the above, this embodiment uses the deviations between the target operator's operation sequence and the standard sequence, as well as the target equipment's operation sequence and the standard sequence, as evaluation criteria to comprehensively and accurately monitor sterile laboratory operations. By calculating deviations based on the similarity of joint coordinate sequence data for the target operator's operation sequence, this method objectively quantifies operational differences at the level of subtle movements, accurately assessing the degree of operator standardization and facilitating the timely detection and correction of non-standard operations.

[0048] In one embodiment of the present application, the deviation between the target person's operation sequence and the standard person's operation sequence is calculated based on the similarity between the joint point coordinate sequence data and the standard joint point coordinate sequence data, including: Calculate the deviation between the target person's operation sequence and the standard person's operation sequence based on the first formula; The first formula is:

[0049] in, Indicates the similarity between the joint point coordinate sequence data and the standard joint point coordinate sequence data, represents the coordinates of the i-th real-time joint point, represents the coordinates of the i-th standard joint point, represents the weight of the i-th joint in action judgment, It represents the maximum distance that a joint point can move, and n represents the number of joint points.

[0050] During the operation, the real-time positions of the target person's hand joints form a real-time joint point coordinate sequence, while the ideal positions of the corresponding joints during the standard person's operation form a standard joint point coordinate sequence. This application evaluates the deviation between the target person's operation sequence and the standard person's operation sequence by calculating the similarity between the joint point coordinate sequence data. By comparing the similarity of these two sets of sequences, we can reflect the degree of fit between the target person's operation and the standard operation, and then derive the deviation of the operation sequence.

[0051] In this embodiment, the similarity between the joint point coordinate sequence data and the standard joint point coordinate sequence data is The closer it is to 0, the higher the similarity between the two, the closer the target person's operation sequence is to the standard sequence, and the smaller the deviation; conversely, the further it deviates from 0, the larger the deviation.

[0052] The i-th real-time joint point coordinates and the coordinates of the i-th standard joint point Determine the position of the i-th joint point under real-time operation and standard operation respectively. By calculating the distance between them , the position difference of a single joint point in real-time and standard operation can be obtained.

[0053] Different joints have different importance in judging whether the operation is standard. For example, in the hand grasping action, the weight of the finger joints may be relatively high. It is used to represent the importance difference. By multiplying the position difference of different joint points by the corresponding weight, the influence of key joint points on the overall similarity can be highlighted, making the deviation calculation more in line with the actual operation specification judgment requirements.

[0054] Maximum distance a joint can move It provides a normalized reference standard for the position differences of joint points. Divide by , the position differences of different joint points can be unified into the interval [0,1] for easy comparison.

[0055] The formula is based on the position difference of each joint point , according to its weight Weighted, then sum up all weighted difference values , and then divided by the sum of the weights , get the similarity value of the degree of difference of the positions of all relevant nodes . Similarity value The deviation between the target personnel's operation sequence and the standard personnel's operation sequence can be determined, providing an accurate basis for judging the sterile experiment operation specifications.

[0056] As can be seen from the above, this embodiment uses the first formula to calculate the similarity of the joint point coordinate sequence data to determine the deviation of the operation sequence between the target person and the standard person. This can accurately consider the impact of the position difference of each joint point on the operation deviation.

[0057] In one embodiment of the present application, the real-time operation specification further includes a time interval between adjacent operations; The deviation between the real-time operation specification and the standard operation specification also includes: the deviation between the time interval of adjacent operations and the standard time interval; Calculating the deviation between the time interval of adjacent operations and the standard time interval based on the second formula; The second formula is:

[0058] in, Indicates the deviation between the time interval of adjacent operations and the standard time interval, represents the time interval between the jth adjacent operations, Indicates the average value of the time interval between adjacent operations.

[0059] In aseptic laboratory operation monitoring, real-time operating specifications not only cover the target equipment and personnel operation sequences, but also consider the time intervals between adjacent operations. Accordingly, deviations between real-time operating specifications and standard operating specifications also include deviations in the time intervals between adjacent operations. This makes the evaluation of operating specifications more comprehensive and takes into account the impact of the time dimension on laboratory operations.

[0060] In this embodiment, the deviation between the time interval of adjacent operations and the standard time interval is The larger it is, the greater the deviation between the actual adjacent operation time interval and the standard time interval; The smaller the value, the closer the two are, and the more the operation complies with standard specifications in terms of time control.

[0061] The time interval between the jth adjacent operations It is the actual time interval data obtained by real-time monitoring and recording of adjacent operations of target equipment or target personnel. During the sterile experiment operation, the time difference between the completion of one operation and the start of the next operation is , reflecting the duration of actual operations over time.

[0062] The average value of the time interval between adjacent operations represents the time interval that should be maintained between adjacent operations in an ideal state, and serves as a benchmark for measuring whether the actual operation time interval meets the standard. In this embodiment, the average value of the time interval between adjacent operations is Expressed as:

[0063] in, represents the minimum time interval between the i-th adjacent operation events, It represents the maximum time interval between the ith adjacent operation events. Together, they determine the range of the standard time interval between adjacent operation events. .

[0064] By calculating the actual adjacent operation time interval Average time interval with standard Absolute value of the difference , determining the extent of deviation between the actual time interval and the standard value. This deviation is then normalized by dividing it by the standard average time interval to obtain a relative deviation value. This way, regardless of the specific value of the standard time interval, the degree of deviation between the actual operation time interval and the standard can be uniformly measured. Based on this deviation value, it is possible to accurately assess whether the timing control of adjacent operations in sterile laboratory operations meets standard specifications.

[0065] As can be seen from the above, this embodiment adds the time intervals between adjacent operations to the consideration of deviations from real-time operation specifications. This, combined with the difference between actual and standard time intervals, intuitively reflects the degree of compliance with time control. This helps laboratory personnel promptly identify improper time control and avoid time deviations that affect experimental sterility and accuracy.

[0066] In one embodiment of the present application, the sterility test operation process is evaluated based on the deviation between the real-time operation specification and the standard operation specification, including: Assign corresponding weight coefficients based on the deviation between the real-time operating specifications and the standard operating specifications; Perform weighted calculation on the weight coefficient to obtain the risk value of each deviation; Generate an assessment report based on the risk value.

[0067] In the sterility test operation process assessment, there are various deviations between real-time operation specifications and standard operation specifications, including deviations in the target equipment operation sequence, deviations in the target personnel operation sequence, and deviations in the time intervals between adjacent operations. Different types of deviations have different degrees of impact on the sterility test results. Based on this, each deviation can be assigned a corresponding weight coefficient based on factors such as its importance in the actual sterility experiment and the potential risk to the experimental results. For example, errors in the key operation sequence of the target equipment may have a serious impact on the experimental results, so they are assigned a higher weight coefficient; while some relatively minor deviations in the time intervals between adjacent operations may be assigned a lower weight coefficient.

[0068] In this embodiment, after assigning weight coefficients to various deviations, the weight coefficients corresponding to each deviation are weighted. Taking the deviation of the target person's operation sequence as an example, assuming that the similarity deviation of the joint point coordinate sequence data is calculated by the previous formula as , the weight coefficient assigned to this deviation type is , the risk value contribution of this deviation is Similarly, for the time interval deviation between adjacent operations, the calculated deviation is , the corresponding weight coefficient is , and its risk value contribution is The risk contributions of all deviations are summed to obtain the comprehensive risk value for each deviation. The weighted calculation comprehensively considers the severity and probability of occurrence of different deviations, and can more accurately reflect the actual risk impact of each deviation on the sterility test operation process.

[0069] A detailed assessment report is generated based on the calculated risk value for each deviation. This report details each deviation, including the deviation type, severity, and corresponding risk value. This report allows laboratory personnel to intuitively understand which steps in the sterility testing process carry risk, and the severity of the risk.

[0070] For example, if the risk value of deviation in the operating sequence of a target device is high, the report can prompt the laboratory personnel to focus on the operation of the device and take corrective measures in a timely manner, thereby ensuring that the sterility test operation process complies with the specifications and ensuring the accuracy and reliability of the experimental results.

[0071] As can be seen from the above, this embodiment can accurately assign values based on the degree of impact of deviations on the experiment by assigning weight coefficients to different deviations. The risk value calculated by weighted calculation comprehensively evaluates each deviation and presents its actual risk. The assessment report generated based on the risk value intuitively displays the risk points and degree in the operation process, helping experimenters quickly identify problems, prioritize high-risk deviations, ensure operational compliance, and improve the success rate and reliability of sterility testing.

[0072] Corresponding to the full-process monitoring method of the sterility experiment in the above embodiment, Figure 2 This is a structural block diagram of a sterile experiment full-process monitoring device provided in one embodiment of the present application. For ease of explanation, only the parts related to the embodiment of the present application are shown. Figure 2 The sterility experiment full-process monitoring device 20 includes: a feature extraction module 21 and an operation process evaluation module 22.

[0073] The feature extraction module 21 is used to extract features of the operation actions of the target device and the target person to obtain real-time operation specifications, which include the operation sequence of the target device and the operation sequence of the target person; The operation process evaluation module 22 is used to evaluate the sterility test operation process based on the deviation between the real-time operation specifications and the standard operation specifications. The operation sequence of the target equipment and the operation sequence of the target personnel are both equipped with corresponding standard operation specifications.

[0074] In one embodiment of the present application, the feature extraction module 21 is specifically configured to: The key point data of the target device is used as a network node. The key point data is used to sense the operation of the target device. The key point data includes operation type data and target device identification data; Build blockchain based on network nodes; Obtain the target device's operation record blocks based on blockchain; The operation record blocks are sorted based on the timestamp sequence to obtain the operation sequence of the target device.

[0075] In one embodiment of the present application, the feature extraction module 21 is further configured to: Perform feature fusion on the target person's gesture feature data to obtain the initial operation action. The target person's gesture feature data includes joint point coordinate sequence data and gesture acceleration data; The operation category of the target person's operation action is taken as the action space, and the initial operation action is taken as the state space; Build reinforcement learning models based on action space and state space; The target person's operation sequence is obtained based on the reinforcement learning model.

[0076] In one embodiment of the present application, the deviation between the real-time operation specification and the standard operation specification includes: a deviation between the operation sequence of the target personnel and the operation sequence of the standard personnel, and a deviation between the operation sequence of the target device and the operation sequence of the standard device; The operation process evaluation module 22 is specifically used to: The deviation between the target person's operation sequence and the standard person's operation sequence is calculated based on the similarity between the joint point coordinate sequence data and the standard joint point coordinate sequence data.

[0077] In one embodiment of the present application, the operation process evaluation module 22 is further configured to: Calculate the deviation between the target person's operation sequence and the standard person's operation sequence based on the first formula; The first formula is:

[0078] in, Indicates the similarity between the joint point coordinate sequence data and the standard joint point coordinate sequence data, represents the coordinates of the i-th real-time joint point, represents the coordinates of the i-th standard joint point, represents the weight of the i-th joint in action judgment, It represents the maximum distance that a joint point can move, and n represents the number of joint points.

[0079] In one embodiment of the present application, the real-time operation specification further includes a time interval between adjacent operations; The operation process evaluation module 22 is further specifically used for: Calculating the deviation between the time interval of adjacent operations and the standard time interval based on the second formula; The second formula is:

[0080] in, Indicates the deviation between the time interval of adjacent operations and the standard time interval, represents the time interval between the jth adjacent operations, Indicates the average value of the time interval between adjacent operations.

[0081] In one embodiment of the present application, the operation process evaluation module 22 is further configured to: Assign corresponding weight coefficients based on the deviation between the real-time operating specifications and the standard operating specifications; Perform weighted calculation on the weight coefficient to obtain the risk value of each deviation; Generate an assessment report based on the risk value.

[0082] See also Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided in one embodiment of the present application. Figure 3The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned device embodiments, such as Figure 2 The functions of the feature extraction module 21 and the operation process evaluation module 22 are shown.

[0083] It should be understood that in the embodiment of the present application, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0084] The input device 302 may include a touchpad, a fingerprint collection sensor (for collecting user fingerprint information and fingerprint direction information), a microphone, etc. The output device 303 may include a display (LCD, etc.), a speaker, etc.

[0085] The memory 304 may include a read-only memory and a random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store device type information.

[0086] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present application can execute the implementation methods described in the first and second embodiments of the full-process monitoring method of the sterile experiment provided in the embodiments of the present application, and can also execute the implementation methods of the electronic device described in the embodiments of the present application, which will not be repeated here.

[0087] In another embodiment of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, all or part of the process of the method in the above embodiment is implemented. The computer program can also be used to instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above method embodiments are implemented. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0088] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. Furthermore, the computer-readable storage medium can include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or is about to be output.

[0089] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0090] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0091] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or can be an electrical, mechanical or other form of connection.

[0092] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0093] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0094] The above are only specific embodiments of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and such modifications or substitutions should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for monitoring the entire process of a sterility experiment, characterized in that: include: Extracting features of the operation actions of the target device and the target person to obtain a real-time operation specification, wherein the real-time operation specification includes the operation sequence of the target device and the operation sequence of the target person; The sterility test operation process is evaluated based on the deviation between the real-time operation specification and the standard operation specification. The operation sequence of the target equipment and the operation sequence of the target personnel are both provided with corresponding standard operation specifications.

2. The sterility test full process monitoring method according to claim 1, characterized in that: The feature extraction of the operation actions of the target device and the target person to obtain the real-time operation specifications includes: Using key point data of the target device as a network node, the key point data is used to sense the operation of the target device, and the key point data includes operation type data and target device identification data; Build blockchain based on network nodes; Obtaining an operation record block of a target device based on the blockchain; The operation record blocks are sorted based on the timestamp sequence to obtain the operation sequence of the target device.

3. The sterility test full process monitoring method according to claim 2, characterized in that: The feature extraction of the operation actions of the target device and the target person to obtain the real-time operation specification also includes: Performing feature fusion on the target person's gesture feature data to obtain an initial operation action, wherein the target person's gesture feature data includes joint point coordinate sequence data and gesture acceleration data; The operation category of the target person's operation action is used as the action space, and the initial operation action is used as the state space; constructing a reinforcement learning model based on the action space and the state space; An operation sequence of the target person is obtained based on the reinforcement learning model.

4. The sterility test full process monitoring method according to claim 1, characterized in that: The deviation between the real-time operation specification and the standard operation specification includes: the deviation between the operation sequence of the target personnel and the operation sequence of the standard personnel, and the deviation between the operation sequence of the target equipment and the operation sequence of the standard equipment; The deviations between the target personnel's operation sequence and the standard personnel's operation sequence include: The deviation between the target person's operation sequence and the standard person's operation sequence is calculated based on the similarity between the joint point coordinate sequence data and the standard joint point coordinate sequence data.

5. The sterility test full process monitoring method according to claim 4, characterized in that: The calculating the deviation between the target person's operation sequence and the standard person's operation sequence based on the similarity between the joint point coordinate sequence data and the standard joint point coordinate sequence data includes: Calculate the deviation between the target person's operation sequence and the standard person's operation sequence based on the first formula; The first formula is: in, Indicates the similarity between the joint point coordinate sequence data and the standard joint point coordinate sequence data, represents the coordinates of the i-th real-time joint point, represents the coordinates of the i-th standard joint point, represents the weight of the i-th joint in action judgment, It represents the maximum distance that a joint point can move, and n represents the number of joint points.

6. The sterility test full process monitoring method according to claim 1, characterized in that: The real-time operation specification also includes the time interval between adjacent operations; The deviation between the real-time operation specification and the standard operation specification also includes: the deviation between the time interval of adjacent operations and the standard time interval; Calculating the deviation between the time interval of adjacent operations and the standard time interval based on the second formula; The second formula is: in, Indicates the deviation between the time interval of adjacent operations and the standard time interval, represents the time interval between the jth adjacent operations, Indicates the average value of the time interval between adjacent operations.

7. The sterility test full process monitoring method according to claim 1, characterized in that: The evaluation of the sterility test operation process based on the deviation between the real-time operation specification and the standard operation specification includes: assigning corresponding weight coefficients based on the deviation between the real-time operating specification and the standard operating specification; Performing weighted calculation on the weight coefficients to obtain a risk value for each deviation; An assessment report is generated based on the risk value.

8. A sterile experiment full process monitoring device, characterized in that: include: A feature extraction module is used to extract features of the operation actions of the target device and the target person to obtain a real-time operation specification, wherein the real-time operation specification includes the operation sequence of the target device and the operation sequence of the target person; The operation process evaluation module is used to evaluate the sterility test operation process based on the deviation between the real-time operation specification and the standard operation specification. The operation sequence of the target equipment and the operation sequence of the target personnel are both provided with corresponding standard operation specifications.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images