Biological experiment management method and device, electronic equipment and storage medium

Abstract

The invention discloses a biological experiment management method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring experimental variable data corresponding to a biological experiment through a sensor; acquiring image data corresponding to the biological experiment through camera equipment; based on the experimental variable data and the image data, determining whether the current synthesis generation experiment is abnormal or not; under the condition that the current biological experiment is not abnormal, predicting a future change trend corresponding to the biological experiment based on the experimental variable data and the image data; determining an adjustment scheme corresponding to the biological experiment based on the future change trend; and adjusting the synthesis generation experiment based on the adjustment scheme.

Description

Technical Field

[0001] This application relates to the field of biological experimental technology, specifically to a method, apparatus, electronic device, and storage medium for managing biological experiments. Background Technology

[0002] Biological experiments typically involve a large number of experimental variables, and changes in these variables affect the experimental results. Currently, the control of synthetic generation experiments mainly relies on manual monitoring to determine whether there are any abnormalities. This method has a low level of intelligence and is inefficient. Furthermore, adjustments are only made when abnormalities are detected, which still fails to prevent the occurrence of abnormalities and thus cannot guarantee the success rate of the experiment.

[0003] Therefore, improving the intelligence level of synthesis and generation experiments and increasing the success rate of experiments are urgent problems to be solved. Summary of the Invention

[0004] This application provides a management method, apparatus, electronic device, and storage medium for biological experiments, which can improve the intelligence level of synthetic generation experiments and increase the success rate of experiments.

[0005] In a first aspect, this application provides a method for managing biological experiments, the method being applied to a management device for biological experiments, the method comprising:

[0006] Data on experimental variables corresponding to biological experiments are collected using sensors;

[0007] Acquire image data corresponding to biological experiments using camera equipment;

[0008] Based on experimental variable data and image data, determine whether there are any anomalies in the current synthesis generation experiment;

[0009] Assuming no anomalies exist in the current biological experiment, predict future trends in the biological experiment based on experimental variable data and image data;

[0010] Based on future trends, determine adjustment plans corresponding to biological experiments;

[0011] The synthesis and generation experiments were adjusted based on the adjustment scheme.

[0012] Secondly, this application provides another method for managing biological experiments, which is applied to a management system for biological experiments, and the method includes:

[0013] The sensor collects experimental variable data corresponding to the biological experiment and sends the experimental variable data to the management device of the biological experiment;

[0014] The camera equipment acquires image data corresponding to the biological experiment and sends the image data to the management device of the biological experiment;

[0015] The management device for biological experiments determines whether there are any anomalies in the current synthesis and production experiment based on experimental variable data and image data;

[0016] Under the condition that there are no abnormalities in the current biological experiment, the management device of the biological experiment predicts the future trend of the biological experiment based on experimental variable data and image data;

[0017] The management system for biological experiments determines adjustment plans corresponding to future trends.

[0018] The management device for biological experiments adjusts the synthesis and generation experiments based on the adjustment plan.

[0019] Thirdly, this application provides a management system for biological experiments, the method comprising:

[0020] Sensors are used to collect experimental variable data corresponding to biological experiments and send the experimental variable data to the management device of the biological experiment.

[0021] Camera equipment is used to acquire image data corresponding to biological experiments and send the image data to the management device of the biological experiments;

[0022] A management device for biological experiments, used to determine whether there are any abnormalities in the current synthesis and generation experiment based on experimental variable data and image data;

[0023] In the absence of any abnormalities in the current biological experiment, the biological experiment management device is also used to predict the future trend of the biological experiment based on experimental variable data and image data.

[0024] The management device for biological experiments is also used to determine adjustment plans corresponding to biological experiments based on future trends.

[0025] The biological experiment management device is also used to adjust the synthesis and generation experiments based on the adjustment plan.

[0026] Fourthly, this application provides a management device for biological experiments, the device comprising: an acquisition unit and a processing unit;

[0027] The acquisition unit is used to collect experimental variable data corresponding to biological experiments through sensors; and to acquire image data corresponding to biological experiments through camera equipment;

[0028] The processing unit is used to determine whether there are any anomalies in the current synthesis and generation experiment based on experimental variable data and image data; if there are no anomalies in the current biological experiment, it predicts the future change trend of the biological experiment based on experimental variable data and image data; based on the future change trend, it determines the adjustment plan corresponding to the biological experiment; and adjusts the synthesis and generation experiment based on the adjustment plan.

[0029] Fifthly, this application provides an electronic device, including: a processor and a memory, the processor being connected to the memory, the memory being used to store a computer program, and the processor being used to execute the computer program stored in the memory, so that the electronic device performs the methods as described in the first and second aspects.

[0030] Sixthly, this application provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the methods of the first and second aspects.

[0031] In a seventh aspect, this application provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, performs the methods as described in the first and second aspects.

[0032] Implementing this application will have the following beneficial effects:

[0033] First, experimental variable data corresponding to the biological experiment is collected through sensors; and image data corresponding to the biological experiment is acquired through camera equipment. Then, based on the experimental variable data and image data, it is determined whether there are any anomalies in the current synthesis and generation experiment. By combining multimodal data, the presence of experimental anomalies is determined, eliminating reliance on manual monitoring and resulting in a higher level of intelligence and efficiency. If no anomalies are found in the current biological experiment, the future change trend of the biological experiment is predicted based on the experimental variable data and image data. Then, based on the future change trend, an adjustment plan is determined for the biological experiment. Finally, the synthesis and generation experiment is adjusted based on the adjustment plan. In other words, although it is predicted that there are no anomalies at present, this application predicts the future change trend of the experiment and determines the corresponding adjustment plan based on the future change area. The experiment is then adjusted based on the adjustment plan. This eliminates the need to wait until an anomaly is detected before intervening in the adjustment. Instead, the experiment is adjusted in advance based on the predicted future change area, which can minimize the probability of anomalies occurring and thus improve the success rate and efficiency of the experiment. Attached Figure Description

[0034] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0035] Figure 1 A flowchart illustrating a method for managing biological experiments provided in this application embodiment;

[0036] Figure 2 This application provides a schematic diagram of a process for determining whether there is an anomaly in the current synthesis and generation experiment based on experimental variable data and image data.

[0037] Figure 3 A flowchart illustrating another method for managing biological experiments provided in this application embodiment;

[0038] Figure 4 A schematic diagram of a biological experiment management system provided in an embodiment of this application;

[0039] Figure 5 A functional unit block diagram of a biological experiment management device provided in an embodiment of this application;

[0040] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0041] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0042] The terms "first," "second," "third," and "fourth," etc., used in the specification, claims, and drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0043] In this document, the term "embodiment" means that a particular feature, result, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0044] First, the relevant terms and technologies involved in the embodiments of this application will be explained:

[0045] Biological experiments: Biological experiments cover a very wide range, encompassing many different disciplines and technical fields. Based on the purpose, research objects, and methods of the experiments, biological experiments can be divided into the following categories: synthesis and generation experiments, molecular biology experiments, cell biology experiments, physiological experiments, ecological experiments, biochemical experiments, genetic experiments, microbiological experiments, pharmacological experiments, immunological experiments, bioinformatics experiments, etc., which are not limited in this application.

[0046] Sensors: Different types of biological experiments correspond to different experimental variables, and consequently, different types of sensors are used to collect these variables. These sensors can be configured according to the specific needs of the experiment. For example, synthetic biology can be used to explain the main types of sensors, including temperature sensors (for monitoring the temperature in the reaction system to ensure that the organism expresses itself at a suitable growth temperature), pH sensors (for monitoring the pH value of the culture medium or reaction solution, especially during fermentation, where pH changes directly affect metabolic pathways and gene expression), fluorescence sensors (for real-time detection of fluorescent markers in the genome to determine whether the gene has been successfully expressed), gas sensors (for detecting gases such as CO2 and O2 produced during biological metabolism to assess cellular respiration rate and metabolic activity), and optical sensors (for detecting optical density values), etc. This application does not limit the types of sensors used. It should be noted that other types of biological experiments are not explained here, but are all within the scope of protection of this application.

[0047] Experimental variables: Different types of biological experiments have different experimental variables. For example, in synthetic biology experiments, the experimental variables may include some or all of the following: environmental variables (such as temperature, pH value, oxygen concentration, gas concentration such as carbon dioxide, light intensity, etc.), culture medium variables (such as nutrient components, carbon source concentration, nitrogen source concentration, trace elements, additives, etc.), and culture method variables (such as culture time, inoculation density, stirring rate, etc.). This application does not limit these variables. It should be noted that other types of biological experiments will not be explained here, but all of them fall within the scope of protection of this application.

[0048] As can be seen from the above background technology, biological experiments usually involve a large number of experimental variables. Changes in these variables affect the experimental results. Currently, the control of synthetic generation experiments mainly relies on manual monitoring to determine whether there are any abnormalities. This method has a low level of intelligence and low efficiency. Furthermore, adjustments are only made when an abnormality is detected, which still fails to prevent the occurrence of abnormalities and thus cannot guarantee the success rate of the experiment.

[0049] Therefore, to overcome the limitations of existing technologies, this application provides a method for managing biological experiments. This method involves collecting experimental variable data corresponding to the biological experiment using sensors and acquiring image data corresponding to the biological experiment using imaging equipment. Based on the experimental variable data and image data, it determines whether there are any anomalies in the current synthesis experiment. By combining multimodal data, it determines whether an anomaly exists, eliminating reliance on manual monitoring and thus achieving a higher level of intelligence and efficiency. If no anomalies are found in the current biological experiment, it predicts the future trend of the biological experiment based on the experimental variable data and image data. Based on this future trend, it determines an adjustment plan for the biological experiment. The synthesis experiment is then adjusted based on this adjustment plan. In other words, although it is predicted that no anomalies exist currently, this application predicts the future trend of the experiment and determines the corresponding adjustment plan based on the future change area. The experiment is then adjusted based on this plan. This eliminates the need to wait until an anomaly is detected before intervening; instead, it intervenes in advance based on the predicted future change area, minimizing the probability of anomalies and thus improving the success rate and efficiency of the experiment.

[0050] The present application will be explained and described below with reference to specific embodiments, as follows:

[0051] See Figure 1 , Figure 1 This is a flowchart illustrating a method for managing biological experiments provided in an embodiment of this application. The method is applied to a management device for biological experiments, and embodiments of the method include, but are not limited to, steps S101-S106:

[0052] S101. Collect experimental variable data corresponding to biological experiments through sensors.

[0053] In the embodiments of this application, different types of biological experiments are used, and the corresponding types of sensors are also different, and the experimental variable data collected by the sensors are also different, which will not be elaborated here.

[0054] S102. Acquire image data corresponding to the biological experiment using camera equipment.

[0055] In the embodiments of this application, experimental variable data corresponding to biological experiments can be collected periodically, which can realize the periodic management of biological experiments. It can also be understood as a way to monitor and manage biological experiments in real time. The experimental variable data collected in step S101 can be regarded as the data collected in the current cycle. This application does not limit the specific duration of each cycle.

[0056] Furthermore, each cycle can be divided into multiple time points, so the experimental variable data collected within each cycle can include the experimental variable data collected at each time point within that cycle. Similarly, the image data corresponding to the biological experiment collected within each cycle can include the image data captured at each time point within that cycle. The image data captured at each time point can include images corresponding to the environmental variables of the biological experiment at that time point, images corresponding to the biological state in the culture medium, etc., and this application does not impose any limitations on this.

[0057] S103. Based on experimental variable data and image data, determine whether there are any anomalies in the current synthesis generation experiment.

[0058] For example, see Figure 2 , Figure 2 This application provides a flowchart illustrating a process for determining whether an anomaly exists in the current synthesis and generation experiment based on experimental variable data and image data. Specifically, this process may include, but is not limited to, the following steps S201-S207:

[0059] S201. Group the experimental variable data according to the preset experimental procedure to obtain multiple first experimental variable data.

[0060] In this system, multiple first experimental variable data points correspond one-to-one with multiple experimental procedures in the preset experimental process. There is a temporal sequence relationship between the multiple experimental procedures, and correspondingly, there is also a temporal sequence relationship between the multiple first experimental variable data points. In addition, since the multiple first experimental variable data points are obtained by grouping according to the experimental procedures, and the duration of each experimental procedure is not necessarily the same, the collection time period corresponding to each first experimental variable data point is also different. That is, each first experimental variable data point can be regarded as the variable data corresponding to each moment in the corresponding collection time period.

[0061] S202. Based on each first experimental variable data, predict the first anomaly probability corresponding to each experimental variable in each first experimental variable data.

[0062] Since the experimental variable data collected in each cycle can include the experimental variable data collected at each time point within each cycle, and the experimental variable data includes data corresponding to multiple experimental variables, then each grouped first experimental variable data also includes the data corresponding to each experimental variable in the experimental procedure corresponding to each first experimental variable data. Therefore, based on each first experimental variable data, the probability of the first anomaly corresponding to each experimental variable in each first experimental variable data can be predicted, for example:

[0063] First, the average of the data corresponding to each experimental variable in each first experimental variable data set is calculated to obtain the average value corresponding to each experimental variable in each first experimental variable data set. For example, if each first experimental variable data set includes the variable data corresponding to each moment in the collection period corresponding to each first experimental variable data set, then the average of the data corresponding to each experimental variable at each moment in each first experimental variable data set can be calculated to obtain the average value corresponding to each experimental variable in each first experimental variable data set. Then, based on the data corresponding to each experimental variable in each first experimental variable data set, the maximum and minimum values ​​corresponding to each experimental variable in each first experimental variable data set are determined.

[0064] Then, based on the mean, maximum, and minimum values ​​corresponding to each experimental variable in each first experimental variable data set, predict the first anomaly probability corresponding to each experimental variable in each first experimental variable data set, specifically:

[0065] First, based on the average value corresponding to each experimental variable in each first experimental variable data set, the third anomaly probability corresponding to each experimental variable in each first experimental variable data set is predicted. For example, based on the average value corresponding to each experimental variable in each first experimental variable data set and the preset standard average value corresponding to each experimental variable, the first difference corresponding to each experimental variable in each first experimental variable is determined. Optionally, the preset standard average value corresponding to each experimental variable can be the preset standard average value corresponding to each experimental variable in each experimental procedure, that is, different experimental procedures may not be the same as the preset standard average value corresponding to each experimental variable. Alternatively, the entire experimental procedure may be the same as the preset standard average value corresponding to each experimental variable. This application does not limit this. If the average is less than (or equal to) the preset standard average, the first difference is the preset standard average minus the average; if the average is greater than (or equal to) the preset standard average, the first difference is the average minus the preset standard average. Then, based on the first difference corresponding to each experimental variable in each first experimental variable and the preset standard average corresponding to each experimental variable, the first ratio corresponding to each experimental variable in each first experimental variable is determined. Then, based on the first ratio corresponding to each experimental variable in each first experimental variable, the third anomaly probability corresponding to each experimental variable in each first experimental variable data is determined. For example, the third anomaly probability corresponding to the z-th experimental variable in the i-th first experimental variable data is used as an example for explanation. The following formula (1) can be referred to:

[0066]

[0067] Wherein, the i-th first experimental variable data is any one of the multiple first experimental variable data, and the z-th experimental variable in the i-th first experimental variable data is any one of the multiple experimental variables in the i-th first experimental variable data.

[0068] Test variables, Let z be the probability of the third anomaly in the i-th first experimental variable data. e is the first ratio corresponding to the z-th experimental variable in the i-th experimental variable data. () If the function is exponential, then similarly, the third anomaly probability corresponding to each experimental variable in each of the first experimental variable data can be determined, which will not be elaborated here. It should be noted that other methods can also be used to determine the third anomaly probability, as long as the first difference corresponding to each experimental variable in each of the first experimental variable data is positively correlated with the corresponding third anomaly probability. All of these methods fall within the scope of protection of this application, and will not be elaborated here.

[0069] Then, based on the maximum and minimum values ​​corresponding to each experimental variable in each first experimental variable data, the fourth anomaly probability corresponding to each experimental variable in each first experimental variable data is predicted. For example, by obtaining the safety threshold interval corresponding to each experimental variable in the experimental procedure corresponding to each first experimental variable data, each experimental variable corresponds to multiple safety threshold intervals, and these multiple safety threshold regions correspond one-to-one with the aforementioned multiple experimental procedures. Then, it is determined whether the maximum and minimum values ​​corresponding to each experimental variable in each first experimental variable data are both within the safety threshold interval corresponding to each experimental variable in the experimental procedure corresponding to each first experimental variable data. If both are within the safety threshold interval, the fourth abnormal probability corresponding to each experimental variable in each first experimental variable data is determined as the first preset probability. If neither is within the safety threshold interval, or if any one is not within the safety threshold interval, a second difference is determined based on the maximum value and the preset standard average value corresponding to each experimental variable in each first experimental variable data, and a third difference is determined based on the minimum value and the preset standard average value corresponding to each experimental variable in each first experimental variable data. The explanation of the principle of the second and third differences can be referred to the explanation of the first difference above, and will not be repeated here. Then, based on the second and third differences corresponding to each experimental variable in each first experimental variable data, the fourth anomaly probability corresponding to each experimental variable in each first experimental variable data is determined. For example, the fourth anomaly probability corresponding to the z-th experimental variable in the i-th first experimental variable data is used as an example for illustration. The following formula (2) can be referred to:

[0070]

[0071] in, Let z be the probability of the fourth anomaly in the z-th experimental variable among the i-th first experimental variable data. This represents the third difference corresponding to the z-th experimental variable in the i-th data of the first experimental variable. Let Q1 be the fourth difference corresponding to the z-th experimental variable in the i-th first experimental variable data, Q2 be the first preset weighting coefficient, and Q1 be the second preset weighting coefficient. Similarly, the fourth anomaly probability corresponding to each experimental variable in each first experimental variable data can be determined, which will not be elaborated here. It should be noted that other methods can also be used to determine the fourth anomaly probability, as long as the third and fourth differences corresponding to each experimental variable in each first experimental variable data are positively correlated with the corresponding fourth anomaly probability. All of these methods fall within the scope of protection of this application, and will not be elaborated here.

[0072] Then, based on the third and fourth anomaly probabilities corresponding to each experimental variable in each first experimental variable data, the first anomaly probability corresponding to each experimental variable in each first experimental variable data can be determined. For example, the first anomaly probability corresponding to each experimental variable in each first experimental variable data can be obtained by summing and averaging the third and fourth anomaly probabilities corresponding to each experimental variable in each first experimental variable data.

[0073] Alternatively, a fifth anomaly probability corresponding to each experimental variable can be determined based on a third anomaly probability corresponding to each experimental variable in each first experimental variable data and a first preset threshold. The fifth anomaly probability is the probability that the plurality of third anomaly probabilities (corresponding one-to-one with the plurality of first experimental variable data) corresponding to each experimental variable is greater than or equal to the first preset threshold. A sixth anomaly probability corresponding to each experimental variable can be determined based on a fourth anomaly probability corresponding to each experimental variable in each first experimental variable data and a second preset threshold. The sixth anomaly probability is the probability that the plurality of fourth anomaly probabilities (corresponding one-to-one with the plurality of first experimental variable data) corresponding to each experimental variable is greater than or equal to the second preset threshold. The values ​​of the first preset threshold and the second preset threshold can be the same or different, and this application does not limit this. Then, based on the third anomaly probability corresponding to each experimental variable in each first experimental variable data and a first preset threshold... Given the fifth and sixth anomaly probabilities corresponding to each experimental variable, determine the first anomaly probability corresponding to each experimental variable in the data of each first experimental variable. For example, sum and average the fifth and sixth anomaly probabilities corresponding to each experimental variable to obtain the first anomaly probability corresponding to each experimental variable in the data of each first experimental variable. Alternatively, the first quantity corresponding to each experimental variable can be obtained based on the sum of the number of fifth and sixth anomaly probabilities corresponding to each experimental variable, and the second quantity corresponding to each experimental variable can be obtained based on the sum of the number of third and fourth anomaly probabilities corresponding to each experimental variable. Then, based on the first and second quantities corresponding to each experimental variable, determine the first anomaly rate corresponding to each experimental variable, such as the ratio of the two, which is not limited in this application.

[0074] It should be explained that, in the embodiments of this application, when determining the first anomaly probability corresponding to each experimental variable in each first experimental variable data, the experimental variable data is divided according to the experimental procedure, and then the corresponding first anomaly probability is analyzed based on the divided first experimental variable data. This is because the experimental procedures corresponding to biological experiments are different, and the corresponding experimental states are different. Consequently, the anomaly detection for different experimental procedures will also be different. Therefore, this approach can ensure the accuracy of the determined first anomaly probability, thereby improving the accuracy of anomaly detection.

[0075] S203. Perform feature extraction on each first experimental variable data to obtain the first feature vector corresponding to each first experimental variable data.

[0076] S204. Extract features from the image data corresponding to each first experimental variable data to obtain a second feature vector corresponding to each first experimental variable data.

[0077] S205. Based on the first feature vector and the second feature vector corresponding to each first experimental variable data, predict the second anomaly probability corresponding to each experimental variable in each first experimental variable data.

[0078] For example, the first feature vector and the second feature vector corresponding to each first experimental variable data can be fused (e.g., by concatenation, weighted averaging, etc., which are not limited in this application) to obtain the second fused feature vector corresponding to each first experimental variable data. Then, based on the first pre-trained model and the second fused feature vector, the second anomaly probability corresponding to each experimental variable in each first experimental variable data can be predicted. The first pre-trained model can be a pre-trained Transformer model, a BERT model, etc., which are not limited in this application.

[0079] Alternatively, the first and second feature vectors corresponding to each first experimental variable data can be mapped to the same dimensional space to obtain the fifth and sixth feature vectors corresponding to each first experimental variable data, respectively. Then, the fifth and sixth feature vectors corresponding to each first experimental variable data are concatenated to obtain the first concatenated feature vector corresponding to each first experimental variable data. Attention processing is then applied to the first concatenated feature vector to obtain the seventh feature vector corresponding to each first experimental variable data, and graph convolution processing is then applied to the first concatenated feature vector to obtain the eighth feature vector corresponding to each first experimental variable data. Finally, the seventh and eighth feature vectors corresponding to each first experimental variable data are fused to obtain the feature vector corresponding to each first experimental variable data. The third fusion feature vector corresponding to each first experimental variable data is obtained; then, the second and third fusion feature vectors corresponding to each first experimental variable data are subjected to residual connection and normalization to obtain the ninth feature vector corresponding to each first experimental variable data; then, the ninth feature vector corresponding to each first experimental variable data is input into the feedforward neural network to obtain the tenth feature vector corresponding to each first experimental variable data; then, the ninth and tenth feature vectors corresponding to each first experimental variable data are subjected to residual connection and normalization to obtain the eleventh feature vector corresponding to each first experimental variable data; then, the eleventh feature vector corresponding to each first experimental variable data is input into the linear layer and the activation layer to output the second anomaly probability corresponding to each experimental variable in each first experimental variable data.

[0080] S206. Based on the first and second abnormal probabilities corresponding to each experimental variable in each first experimental variable data, predict the current abnormal probability corresponding to the synthetic generation experiment.

[0081] For example, the first and second anomaly probabilities corresponding to each experimental variable in each first experimental variable data can be summed and averaged or weighted averaged, etc. This application does not limit the method, to obtain the anomaly probability corresponding to the current synthesis generation experiment.

[0082] S207. Based on the anomaly probability, determine whether there is an anomaly in the current synthesis generation experiment.

[0083] For example, if the probability of an anomaly is greater than or equal to the third threshold, then it is determined that there is an anomaly in the current synthesis and generation experiment; conversely, if the probability of an anomaly is less than the third threshold, then it is determined that there is an anomaly in the current synthesis and generation experiment.

[0084] As can be seen, in the embodiments of this application, the anomaly probability corresponding to the current synthesis generation experiment is predicted by using the first anomaly probability and the second anomaly probability corresponding to each experimental variable in each first experimental variable data. That is, anomalies are detected by combining two dimensions of artificial intelligence and data analysis, which can improve the accuracy and efficiency of anomaly detection.

[0085] S104. Under the condition that there are no abnormalities in the current biological experiment, predict the future change trend of the corresponding biological experiment based on experimental variable data and image data.

[0086] If it is determined that there are no anomalies in the current biological experiment, then based on the experimental variable data and image data, the future trend of the corresponding biological experiment can be predicted. Specifically:

[0087] First, historical experimental variable data and corresponding historical image data are obtained. Then, based on the historical experimental variable data and historical image data, multiple data combinations are determined. Each data combination includes the data corresponding to each experimental variable in the historical experimental variable data and the image corresponding to the data corresponding to each experimental variable in the historical image data. In other words, the data in the data combination consists of the data from the experimental variable data and the images from the image data. For example:

[0088] Historical experimental variable data and historical image data can be data within a historical period, that is, including historical experimental variable data and historical image data corresponding to each moment in multiple moments within the historical period. Then, the variable data and image data for each experimental variable at each moment in the historical experimental variable data are determined. Next, for each experimental variable, the variable data and image for each experimental variable at each moment are permuted and combined to obtain multiple fourth data combinations corresponding to each experimental variable. The permutation and combination method can be exhaustive, and each fourth data combination must include at least one moment's variable data and one moment's image for each experimental variable. Then, the multiple fourth data combinations corresponding to each experimental variable are filtered to obtain multiple fifth data combinations corresponding to each experimental variable. Each fifth data combination must include at least two moments' variable data and two moments' images for each experimental variable, and adjacent variable data in each fifth data combination must belong to data from adjacent experimental processes or data from adjacent moments, and adjacent image data in each fifth data combination must belong to images from adjacent experimental processes or... The images belong to adjacent time points; then, based on multiple fifth data combinations corresponding to each experimental variable, the above-mentioned multiple data combinations are obtained. For example, the multiple data combinations include multiple fifth data combinations corresponding to each experimental variable. Alternatively, the probability corresponding to each fifth data combination corresponding to each experimental variable can be determined based on each fifth data combination corresponding to each experimental variable and the data corresponding to each experimental variable in the historical experimental variable data and the image corresponding to each experimental variable in the historical image data. The probability corresponding to each fifth data combination corresponding to each experimental variable represents the probability that the data corresponding to each time point in the fifth data combination appears simultaneously in the historical experimental variable data and the historical image data. Then, based on the probability corresponding to each fifth data combination corresponding to each experimental variable, the multiple fifth data combinations corresponding to each experimental variable are filtered to obtain a sixth data combination corresponding to each experimental variable. The probability corresponding to the sixth data combination corresponding to each experimental variable is greater than or equal to a preset probability threshold. Then, based on the sixth data combination corresponding to each experimental variable, the above-mentioned multiple data combinations are obtained. For example, at this time, the multiple data combinations include the sixth data combination corresponding to each experimental variable.

[0089] Then, based on experimental variable data, image data, and multiple data combinations, the future trend of biological experiment is predicted. Specifically, based on experimental variable data and image data, multiple first data combinations are determined. In each first data combination, the variable data and image data are data corresponding to the same experimental variable. Each first data combination includes the variable data and image data of an experimental variable at each moment in the current period.

[0090] Then, based on multiple first data combinations and multiple data combinations, a first probability corresponding to each data combination is determined. For example, the similarity between each first data combination and each data combination is determined, resulting in multiple similarities corresponding to each data combination, where each similarity corresponds one-to-one with multiple first data combinations. Then, based on the multiple similarities corresponding to each data combination, a first similarity corresponding to each data combination is determined, where the first similarity is the largest similarity among the multiple similarities. Finally, based on the first similarity corresponding to each data combination, a first probability corresponding to each data combination is determined, for example, the first similarity corresponding to each data combination is determined as the first probability corresponding to each data combination.

[0091] Then, feature extraction is performed on the experimental variable data to obtain a third feature vector, and feature extraction is performed on the image data to obtain a fourth feature vector; then, the third feature vector and the fourth feature vector are fused to obtain a first fused feature vector; then, based on the first fused feature vector, a second probability corresponding to each data combination is predicted, such as based on a second pre-trained model and the second fused feature vector, where the second pre-trained model can be a pre-trained Transformer model, a BERT model, etc., which are not limited in this application.

[0092] Alternatively, the third feature vector can be processed by graph convolution to obtain the twelfth feature vector, and the fourth feature vector can be processed by graph convolution to obtain the thirteenth feature vector; then the twelfth and thirteenth feature vectors can be fused to obtain the fourth fused feature vector; then the third and fourth feature vectors can be processed by cross-attention to obtain the fourteenth feature vector; then the fourth and fourteenth fused feature vectors can be fused, for example by concatenation or weighted averaging, to obtain the fifth fused feature vector; then the second and fifth fused feature vectors can be processed by residual connection and normalization to obtain the fifteenth feature vector; then the fifteenth feature vector can be input into the feedforward neural network to obtain the sixteenth feature vector; then the fifteenth and sixteenth feature vectors can be processed by residual connection and normalization to obtain the seventeenth feature vector; then the seventeenth feature vector can be input into the linear layer and the activation layer, and the output is the second probability corresponding to each data combination.

[0093] Then, based on the first and second probabilities corresponding to each data combination, the future trend of the biological experiment is predicted. For example, firstly, based on the first probability corresponding to each data combination, a second data combination is determined from multiple data combinations, wherein the second data combination is the combination with the highest first probability or the combination with the first probability greater than or equal to a first threshold; and based on the second probability corresponding to each data combination, a third data combination is determined from multiple data combinations, wherein the third data combination is the combination with the highest second probability or the combination with the second probability greater than or equal to a second threshold; then, the second and third data combinations are fused to obtain the target data combination. For example, if the second and third data combinations correspond to the same experimental variable, then the union of the second and third data combinations is taken according to the chronological order to obtain the target data combination; if the second and third data combinations do not correspond to the same experimental variable, then both the second and third data combinations are determined as the target data combination. In this case, the target data combination includes two data combinations.

[0094] Finally, based on the target data set, the future trend of the biological experiment is determined. Since the target data set includes data for the experimental variable at each time step, the changes in the experimental variable after the current time step are determined based on the data of the experimental variable in the target data set, such as whether it increases or decreases, and by how much. For example, the target data set might be [D...]. t1 D t2 D t3 I t1 I t2 I t3 ,], where D t1 D t2 D t3 Let I represent the experimental variable data of experimental variable A at times t1, t2, and t3, respectively. t1 I t2 I t3 Let t1, t2, and t3 represent the image data of experimental variable A at times t1, t2, and t3, respectively. The times t1, t2, and t3 are arranged in chronological order. The current time corresponds to time t2 in the target data combination. Based on the experimental variable data between times t3 and t2, we can determine whether the future trend of experimental variable A is an increase or a decrease. In other words, the future trend is the trend of the experimental variable corresponding to the target data combination.

[0095] S105. Based on future trends, determine the adjustment plan corresponding to biological experiments.

[0096] After predicting the future trend of the experimental variables corresponding to the target data combination, an adjustment scheme that matches the future change region can be determined from multiple preset adjustment schemes corresponding to the experimental variables corresponding to the target data combination based on the future trend.

[0097] S106. Adjust the synthesis and generation experiment based on the adjustment scheme.

[0098] Once a matching adjustment scheme is determined, the synthetic biology experiment can be adjusted based on the matching scheme. For example, if the adjustment scheme includes raising or lowering the temperature to a first value, the biological experiment management device sends a temperature adjustment command to the sensor (i.e., the temperature sensor), and then the temperature sensor responds to the temperature adjustment command and adjusts the temperature. Of course, the adjustment scheme can also include adjusting the light intensity, stirring rate, etc., in which case the biological experiment management device can send corresponding adjustment commands to the relevant sensors. The principle is similar to that of the temperature sensor, and will not be elaborated here.

[0099] Of course, in an optional embodiment, if it is determined that there is an anomaly in the current biological experiment, the experimental variable with the anomaly can be determined based on the anomaly in the current biological experiment; then, based on the anomaly of the experimental variable with the anomaly, an adjustment scheme that matches the anomaly can be selected from multiple preset adjustment schemes corresponding to the experimental variable with the anomaly; and then the synthesis and generation experiment can be adjusted based on the matching adjustment scheme.

[0100] For further details, please refer to [link / reference]. Figure 3 , Figure 3 This is a flowchart illustrating another biological experiment management method provided in an embodiment of this application. The method is applied to a biological experiment management system, which includes sensors, camera equipment, and a biological experiment management device. The method includes, but is not limited to, steps S301-S306:

[0101] S301. The sensor collects experimental variable data corresponding to the biological experiment and sends the experimental variable data to the management device of the biological experiment.

[0102] S302. The camera device acquires image data corresponding to the biological experiment and sends the image data to the management device of the biological experiment.

[0103] S303. The biological experiment management device determines whether there are any abnormalities in the current synthesis and generation experiment based on experimental variable data and image data.

[0104] S304. Under the condition that there are no abnormalities in the current biological experiment, the management device of the biological experiment predicts the future change trend of the biological experiment based on experimental variable data and image data.

[0105] S305. The management device for biological experiments determines an adjustment plan corresponding to the biological experiments based on future changing trends.

[0106] S306. The management device for biological experiments adjusts the synthesis and generation experiments based on the adjustment scheme.

[0107] It should be noted that the principles of steps S301-S306 can be referred to the above. Figure 1 The corresponding explanation of the embodiments, and the corresponding execution thereof. Figure 1 Other steps in the embodiments will not be described in detail here.

[0108] As can be seen, in the embodiments of this application, experimental variable data corresponding to the biological experiment are collected by sensors; and image data corresponding to the biological experiment is acquired by camera equipment; then, based on the experimental variable data and image data, it is determined whether there is an anomaly in the current synthesis and generation experiment. By combining multimodal data, it is determined whether there is an experimental anomaly, which is no longer based on human monitoring, thus achieving a higher level of intelligence and efficiency; then, if there is no anomaly in the current biological experiment, the future change trend corresponding to the biological experiment is predicted based on the experimental variable data and image data; then, based on the future change trend, an adjustment plan corresponding to the biological experiment is determined; and then, the synthesis and generation experiment is adjusted based on the adjustment plan. That is to say, although it is predicted that there is no anomaly at present, this application predicts the future change trend corresponding to the experiment and determines the corresponding adjustment plan based on the future change area, and then adjusts the experiment based on the adjustment plan. In this way, it is no longer necessary to wait until an anomaly is detected before intervening in the adjustment, but to intervene in the adjustment of the experiment in advance based on the predicted future change area. This can minimize the probability of anomalies occurring, thereby improving the success rate and efficiency of the experiment.

[0109] The system architecture involved in this application will be explained below with reference to the accompanying drawings:

[0110] See Figure 4 , Figure 4 This is a schematic diagram of a biological experiment management system provided in an embodiment of this application.

[0111] Figure 4The system shown includes sensors, camera equipment, and a management device for biological experiments. The number of sensors can be one or more. For example, if there is only one sensor and the biological experiment requires multiple types of sensors, then multiple types of sensors can be integrated onto one sensor. If there are multiple sensors, then these multiple sensors can be the various types of sensors required for the biological experiment; this application does not limit the number. The number of camera equipment can be one or more; this application also does not limit the number. The management device for biological experiments can be a server. The server can be an independent physical server, a server cluster composed of multiple physical servers, or a distributed system. It can also be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, and big data and artificial intelligence platforms; this application does not specifically limit the number. Alternatively, the management device for biological experiments can also be a terminal device, such as a smartphone, tablet, laptop, desktop computer, smart TV, desktop computer, smartwatch, smart vehicle, etc., but is not limited to these. It should be noted that... Figure 4 The embodiment mainly uses a single sensor, a single camera, and a terminal device as the management device for the biological experiment as an example for illustration. Specifically:

[0112] First, sensors collect experimental variable data corresponding to the biological experiment and send this data to the biological experiment management device; similarly, camera equipment acquires image data corresponding to the biological experiment and sends this data to the management device. Then, based on the experimental variable data and image data, the management device determines whether there are any anomalies in the current synthesis experiment. If no anomalies are found, the management device predicts future trends based on the experimental variable data and image data. Based on these future trends, the management device determines an adjustment plan for the biological experiment. Finally, the management device adjusts the synthesis experiment according to the adjustment plan.

[0113] It should be noted that the principles of the steps performed by each device in this embodiment can be referred to the corresponding explanations in the above embodiments, which will not be repeated here. Also, the steps performed by each device in the above embodiments can be executed accordingly, which will not be repeated here.

[0114] See Figure 5 , Figure 5 This is a functional unit block diagram of a biological experiment management device provided in an embodiment of this application. The biological experiment management device 500 includes: an acquisition unit 501 and a processing unit 502;

[0115] The acquisition unit 501 is used to acquire experimental variable data corresponding to the biological experiment through sensors; and to acquire image data corresponding to the biological experiment through a camera device;

[0116] The processing unit 502 is used to determine whether there is an anomaly in the current synthesis and generation experiment based on experimental variable data and image data; if there is no anomaly in the current biological experiment, it predicts the future change trend of the biological experiment based on experimental variable data and image data; based on the future change trend, it determines the adjustment plan corresponding to the biological experiment; and adjusts the synthesis and generation experiment based on the adjustment plan.

[0117] In one embodiment of this application, the experimental variable data includes data corresponding to multiple experimental variables. In determining whether an anomaly exists in the current synthesis generation experiment based on the experimental variable data and image data, the processing unit 502 is specifically used for:

[0118] Following the pre-set experimental procedure, the experimental variable data were grouped to obtain multiple first experimental variable data.

[0119] Based on the data of each first experimental variable, predict the first anomaly probability corresponding to each experimental variable in the data of each first experimental variable;

[0120] For each first experimental variable data, feature extraction is performed to obtain the first feature vector corresponding to each first experimental variable data;

[0121] Feature extraction is performed on the image data corresponding to each first experimental variable data to obtain a second feature vector corresponding to each first experimental variable data.

[0122] Based on the first feature vector and the second feature vector corresponding to each first experimental variable data, predict the second anomaly probability corresponding to each experimental variable in each first experimental variable data;

[0123] Based on the first and second anomalies corresponding to each experimental variable in each first experimental variable data, predict the current anomaly probability corresponding to the synthetic generation experiment;

[0124] Based on the anomaly probability, determine whether there is an anomaly in the current synthesis generation experiment.

[0125] In one embodiment of this application, in predicting the first anomaly probability corresponding to each experimental variable in each of the first experimental variable data based on each first experimental variable data, the processing unit 502 is specifically used for:

[0126] The average of the data corresponding to each experimental variable in each first experimental variable data is calculated to obtain the average value corresponding to each experimental variable in each first experimental variable data.

[0127] Based on the data corresponding to each experimental variable in each first experimental variable data, determine the maximum and minimum values ​​corresponding to each experimental variable in each first experimental variable data;

[0128] Based on the mean, maximum, and minimum values ​​of each experimental variable in each first experimental variable data, predict the first anomaly probability corresponding to each experimental variable in each first experimental variable data.

[0129] In one embodiment of this application, in predicting the first anomaly probability corresponding to each experimental variable in each first experimental variable data based on the average, maximum, and minimum values ​​corresponding to each experimental variable in each first experimental variable data, the processing unit 502 is specifically used for:

[0130] Based on the average value of each experimental variable in each first experimental variable data, predict the third anomaly probability corresponding to each experimental variable in each first experimental variable data;

[0131] Based on the maximum and minimum values ​​corresponding to each experimental variable in each first experimental variable data, predict the fourth anomaly probability corresponding to each experimental variable in each first experimental variable data;

[0132] Based on the third and fourth anomaly probabilities corresponding to each experimental variable in each first experimental variable data, the first anomaly probability corresponding to each experimental variable in each first experimental variable data is determined.

[0133] In one embodiment of this application, in predicting future trends of biological experiments based on experimental variable data and image data, the processing unit 502 is specifically used for:

[0134] Acquire historical experimental variable data and corresponding historical image data;

[0135] Based on historical experimental variable data and historical image data, multiple data combinations are determined. Each data combination includes the data corresponding to each experimental variable in the historical experimental variable data and the image corresponding to the data corresponding to each experimental variable in the historical image data.

[0136] Based on experimental variable data, image data, and multiple data combinations, predict future trends of biological experiments.

[0137] In one embodiment of this application, in predicting future trends of biological experiments based on experimental variable data, image data, and multiple data combinations, the processing unit 502 is specifically used for:

[0138] Based on experimental variable data and image data, multiple first data combinations were determined;

[0139] Based on multiple first data combinations and multiple data combinations, determine the first probability corresponding to each data combination;

[0140] Feature extraction was performed on the experimental variable data to obtain the third feature vector, and feature extraction was performed on the image data to obtain the fourth feature vector;

[0141] The third and fourth feature vectors are fused to obtain the first fused feature vector;

[0142] Based on the first fused feature vector, predict the second probability corresponding to each data combination;

[0143] Based on the first and second probabilities corresponding to each data combination, predict the future trend of biological experiments.

[0144] In one embodiment of this application, in predicting the future trend of a biological experiment based on a first probability and a second probability corresponding to each data combination, the processing unit 502 is specifically used for:

[0145] Based on the first probability corresponding to each data combination, a second data combination is determined from multiple data combinations, wherein the second data combination is the combination with the highest first probability among the multiple data combinations or the combination with the first probability greater than or equal to a first threshold;

[0146] Based on the second probability corresponding to each data combination, a third data combination is determined from multiple data combinations, wherein the third data combination is the combination with the highest second probability among the multiple data combinations or the combination with a second probability greater than or equal to a second threshold.

[0147] The second and third data combinations are fused to obtain the target data combination.

[0148] Based on the target data combination, determine the future trend of biological experiment.

[0149] In specific implementations, the acquisition unit 501 and processing unit 502 described in the embodiments of the present invention may also execute other implementation methods described in the method embodiments provided in the embodiments of the present invention, which will not be repeated here.

[0150] See Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Figure 6As shown, the electronic device 600 includes a transceiver 601, a processor 602, and a memory 603. These are connected via a bus 604. The memory 603 stores computer programs and data, and can transfer data stored in the memory 603 to the processor 602.

[0151] Processor 602 is used to read the computer program in memory 603 and perform the following operations:

[0152] The control transceiver 601 collects experimental variable data corresponding to the biological experiment through sensors; and acquires image data corresponding to the biological experiment through camera equipment;

[0153] Based on experimental variable data and image data, determine whether there are any anomalies in the current synthesis generation experiment;

[0154] Assuming no anomalies exist in the current biological experiment, predict future trends in the biological experiment based on experimental variable data and image data;

[0155] Based on future trends, determine adjustment plans corresponding to biological experiments;

[0156] The synthesis and generation experiments were adjusted based on the adjustment scheme.

[0157] In one embodiment of this application, the experimental variable data includes data corresponding to multiple experimental variables. Regarding determining whether an anomaly exists in the current synthesis generation experiment based on the experimental variable data and image data, the processor 602 is specifically configured to perform the following steps:

[0158] Following the pre-set experimental procedure, the experimental variable data were grouped to obtain multiple first experimental variable data.

[0159] Based on the data of each first experimental variable, predict the first anomaly probability corresponding to each experimental variable in the data of each first experimental variable;

[0160] For each first experimental variable data, feature extraction is performed to obtain the first feature vector corresponding to each first experimental variable data;

[0161] Feature extraction is performed on the image data corresponding to each first experimental variable data to obtain a second feature vector corresponding to each first experimental variable data.

[0162] Based on the first feature vector and the second feature vector corresponding to each first experimental variable data, predict the second anomaly probability corresponding to each experimental variable in each first experimental variable data;

[0163] Based on the first and second anomalies corresponding to each experimental variable in each first experimental variable data, predict the current anomaly probability corresponding to the synthetic generation experiment;

[0164] Based on the anomaly probability, determine whether there is an anomaly in the current synthesis generation experiment.

[0165] In one embodiment of this application, in predicting the first anomaly probability corresponding to each experimental variable in each of the first experimental variable data based on each first experimental variable data, the processor 602 is specifically configured to perform the following steps:

[0166] The average of the data corresponding to each experimental variable in each first experimental variable data is calculated to obtain the average value corresponding to each experimental variable in each first experimental variable data.

[0167] Based on the data corresponding to each experimental variable in each first experimental variable data, determine the maximum and minimum values ​​corresponding to each experimental variable in each first experimental variable data;

[0168] Based on the mean, maximum, and minimum values ​​of each experimental variable in each first experimental variable data, predict the first anomaly probability corresponding to each experimental variable in each first experimental variable data.

[0169] In one embodiment of this application, the processor 602 is specifically configured to perform the following steps in predicting the first anomaly probability corresponding to each experimental variable in each first experimental variable data based on the average, maximum, and minimum values ​​corresponding to each experimental variable in each first experimental variable data:

[0170] Based on the average value of each experimental variable in each first experimental variable data, predict the third anomaly probability corresponding to each experimental variable in each first experimental variable data;

[0171] Based on the maximum and minimum values ​​corresponding to each experimental variable in each first experimental variable data, predict the fourth anomaly probability corresponding to each experimental variable in each first experimental variable data;

[0172] Based on the third and fourth anomaly probabilities corresponding to each experimental variable in each first experimental variable data, the first anomaly probability corresponding to each experimental variable in each first experimental variable data is determined.

[0173] In one embodiment of this application, in predicting future trends of biological experiments based on experimental variable data and image data, the processor 602 is specifically configured to perform the following steps:

[0174] Acquire historical experimental variable data and corresponding historical image data;

[0175] Based on historical experimental variable data and historical image data, multiple data combinations are determined. Each data combination includes the data corresponding to each experimental variable in the historical experimental variable data and the image corresponding to the data corresponding to each experimental variable in the historical image data.

[0176] Based on experimental variable data, image data, and multiple data combinations, predict future trends of biological experiments.

[0177] In one embodiment of this application, in predicting future trends of biological experiments based on experimental variable data, image data, and multiple data combinations, the processor 602 is specifically configured to perform the following steps:

[0178] Based on experimental variable data and image data, multiple first data combinations were determined;

[0179] Based on multiple first data combinations and multiple data combinations, determine the first probability corresponding to each data combination;

[0180] Feature extraction was performed on the experimental variable data to obtain the third feature vector, and feature extraction was performed on the image data to obtain the fourth feature vector;

[0181] The third and fourth feature vectors are fused to obtain the first fused feature vector;

[0182] Based on the first fused feature vector, predict the second probability corresponding to each data combination;

[0183] Based on the first and second probabilities corresponding to each data combination, predict the future trend of biological experiments.

[0184] In one embodiment of this application, in predicting the future trend of a biological experiment based on a first probability and a second probability corresponding to each data combination, the processor 602 is specifically configured to perform the following steps:

[0185] Based on the first probability corresponding to each data combination, a second data combination is determined from multiple data combinations, wherein the second data combination is the combination with the highest first probability among the multiple data combinations or the combination with the first probability greater than or equal to a first threshold;

[0186] Based on the second probability corresponding to each data combination, a third data combination is determined from multiple data combinations, wherein the third data combination is the combination with the highest second probability among the multiple data combinations or the combination with a second probability greater than or equal to a second threshold.

[0187] The second and third data combinations are fused to obtain the target data combination.

[0188] Based on the target data combination, determine the future trend of biological experiment.

[0189] In specific implementations, the transceiver 601 and processor 602 described in the embodiments of the present invention can also execute other implementations described in the method embodiments provided in the embodiments of the present invention, which will not be repeated here.

[0190] Specifically, the transceiver 601 described above can be... Figure 5 The acquisition unit 501 of the biological experiment management device 500 in the embodiment, the processor 602 can be... Figure 5 The processing unit 502 of the biological experiment management device 500 of the embodiment.

[0191] It should be understood that the management device and electronic equipment for biological experiments in this application can be either terminal devices or servers. Terminal devices can be smart terminals such as smartphones, tablets, laptops, desktop computers, smart TVs, desktop computers, smartwatches, and smart in-vehicle systems, but are not limited to these. Servers can be independent physical servers, server clusters or distributed systems composed of multiple physical servers, or cloud servers providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, and big data and artificial intelligence platforms. This application does not impose specific limitations. The aforementioned electronic equipment is merely an example, not an exhaustive list, and includes, but is not limited to, the aforementioned electronic equipment.

[0192] It should be understood that embodiments of this application also provide a computer-readable storage medium storing a computer program that is executed by a processor to implement some or all of the steps of any of the biological experiment management methods described in the above method embodiments.

[0193] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the biological experiment management methods described in the above method embodiments.

[0194] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to this application.

[0195] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0196] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0197] The units described as separate components may or may not be physically separate. 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 can be selected to achieve the purpose of this embodiment according to actual needs.

[0198] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.

[0199] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0200] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0201] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for managing biological experiments, characterized in that, The method includes: The experimental variable data corresponding to the biological experiment are collected using sensors; Image data corresponding to the biological experiment is acquired using a camera device; Based on the experimental variable data and the image data, determine whether there is any anomaly in the current synthesis generation experiment; Under the premise that there are no abnormalities in the current biological experiment, predict the future trend of the biological experiment based on the experimental variable data and the image data; Based on the aforementioned future trends, an adjustment plan corresponding to the biological experiment will be determined; The synthesis and generation experiment was adjusted based on the aforementioned adjustment scheme.

2. The method according to claim 1, characterized in that, The experimental variable data includes data corresponding to multiple experimental variables. Determining whether there is an anomaly in the current synthesis generation experiment based on the experimental variable data and the image data includes: According to the preset experimental procedure, the experimental variable data are grouped to obtain multiple first experimental variable data; Based on the data of each first experimental variable, predict the first anomaly probability corresponding to each experimental variable in the data of each first experimental variable; For each first experimental variable data, feature extraction is performed to obtain the first feature vector corresponding to each first experimental variable data; Feature extraction is performed on the image data corresponding to each first experimental variable data to obtain a second feature vector corresponding to each first experimental variable data. Based on the first feature vector and the second feature vector corresponding to each first experimental variable data, predict the second anomaly probability corresponding to each experimental variable in each first experimental variable data; Based on the first and second anomaly probabilities corresponding to each experimental variable in each first experimental variable data, predict the current anomaly probability corresponding to the synthetic generation experiment; Based on the anomaly probability, it is determined whether the current synthesis generation experiment is abnormal.

3. The method according to claim 2, characterized in that, The step of predicting the first anomaly probability corresponding to each experimental variable in each set of first experimental variable data based on each set of first experimental variable data includes: The average of the data corresponding to each experimental variable in each first experimental variable data is calculated to obtain the average value corresponding to each experimental variable in each first experimental variable data. Based on the data corresponding to each experimental variable in each first experimental variable data, determine the maximum and minimum values ​​corresponding to each experimental variable in each first experimental variable data; Based on the mean, maximum, and minimum values ​​of each experimental variable in each first experimental variable data, predict the first anomaly probability corresponding to each experimental variable in each first experimental variable data.

4. The method according to claim 2, characterized in that, The step of predicting the first anomaly probability corresponding to each experimental variable in each first experimental variable data based on the average, maximum, and minimum values ​​of each experimental variable in each first experimental variable data includes: Based on the average value of each experimental variable in each first experimental variable data, predict the third anomaly probability corresponding to each experimental variable in each first experimental variable data; Based on the maximum and minimum values ​​corresponding to each experimental variable in each first experimental variable data, predict the fourth anomaly probability corresponding to each experimental variable in each first experimental variable data; Based on the third and fourth anomaly probabilities corresponding to each experimental variable in each first experimental variable data, the first anomaly probability corresponding to each experimental variable in each first experimental variable data is determined.

5. The method according to any one of claims 1-4, characterized in that, The prediction of future trends corresponding to the biological experiment based on the experimental variable data and the image data includes: Acquire historical experimental variable data and historical image data corresponding to the historical experimental variable data; Based on the historical experimental variable data and the historical image data, multiple data combinations are determined, wherein each data combination includes the data corresponding to each experimental variable in the historical experimental variable data and the image corresponding to the data corresponding to each experimental variable in the historical image data; Based on the experimental variable data, the image data, and the combination of multiple data, the future trend of the biological experiment is predicted.

6. The method according to claim 5, characterized in that, The prediction of future trends corresponding to the biological experiment based on the experimental variable data, the image data, and the combination of multiple data includes: Based on the experimental variable data and the image data, multiple first data combinations are determined; Based on the plurality of first data combinations and the plurality of data combinations, a first probability corresponding to each data combination is determined; Feature extraction is performed on the experimental variable data to obtain a third feature vector, and feature extraction is performed on the image data to obtain a fourth feature vector; The third feature vector and the fourth feature vector are fused to obtain a first fused feature vector; Based on the first fused feature vector, predict the second probability corresponding to each data combination; Based on the first and second probabilities corresponding to each data combination, the future trend of the biological experiment is predicted.

7. The method according to claim 6, characterized in that, The prediction of future trends corresponding to the biological experiment based on the first and second probabilities corresponding to each data combination includes: Based on the first probability corresponding to each data combination, a second data combination is determined from the plurality of data combinations, wherein the second data combination is the combination with the highest first probability or the combination with a first probability greater than or equal to a first threshold among the plurality of data combinations; Based on the second probability corresponding to each data combination, a third data combination is determined from the plurality of data combinations, wherein the third data combination is the combination with the highest second probability among the plurality of data combinations or the combination with a second probability greater than or equal to a second threshold; The second data combination and the third data combination are fused to obtain the target data combination; Based on the target data combination, the future trend of change corresponding to the biological experiment is determined.

8. A management device for biological experiments, characterized in that, The device includes: an acquisition unit and a processing unit; The acquisition unit is used to collect experimental variable data corresponding to the biological experiment through a sensor; and to acquire image data corresponding to the biological experiment through a camera device; The processing unit is configured to determine whether there is an anomaly in the current synthesis and generation experiment based on the experimental variable data and the image data; if there is no anomaly in the current biological experiment, predict the future change trend of the biological experiment based on the experimental variable data and the image data; determine an adjustment plan corresponding to the biological experiment based on the future change trend; and adjust the synthesis and generation experiment based on the adjustment plan.

9. An electronic device, characterized in that, include: A processor and a memory, the processor being connected to the memory, the memory being used to store a computer program, and the processor being used to execute the computer program stored in the memory to cause the electronic device to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is executed by a processor to implement the method as described in any one of claims 1-7.

Images