Trace water sample layered absorption and air isolation method and device, analyzer and medium

Abstract

The embodiment of the invention relates to the technical field of water quality detection, and provides a trace water sample layered absorption and air isolation method and device, an analyzer and a medium. The method comprises the following steps: determining layered information of a to-be-detected water sample according to a side image of the to-be-detected water sample to obtain first layered information, the to-be-detected water sample is a water sample which is layered after standing; a sampling strategy corresponding to a sampling device is determined according to the first layered information and the side image of the water sample to be detected, a first sampling strategy is obtained, the first sampling strategy comprises the sampling position, the sampling volume, the sampling depth and the sample air isolation strategy of the sampling device, and the sampling device comprises a sample container; an image acquisition device is arranged near the sample container; sampling the to-be-detected water sample by using the sampling device according to a first sampling strategy to obtain a target water sample; and the accuracy of trace water sample layered suction and air isolation of the water sample to be detected is improved.

Description

Technical Field

[0001] This application relates to the field of water quality testing technology, specifically to a method, apparatus, analyzer, and medium for the stratified absorptive and air-isolated extraction of trace water samples. Background Technology

[0002] "Trace water sample stratification" is a refined analytical technique for trace volume water samples (usually a few milliliters to tens of milliliters, or even less) in environmental monitoring, water quality analysis, and hydrological research. The core is to achieve the stratification and separation of different components (such as pollutants, nutrients, suspended particles, etc.) in the water sample through physical or chemical means, and then perform targeted absorption spectroscopy detection or component quantification on each layer to accurately obtain the distribution characteristics and concentration information of the target substances in the water sample.

[0003] Because of the small volume of trace water samples, after a period of settling, the trace water samples will exhibit stratification due to the characteristics of the solutes in the trace water. For example, suspended particles in the trace water sample (such as colloidal iron, silicon, etc.) will settle after a period of settling, thus causing the trace water sample to exhibit stratification.

[0004] In existing technologies, the sampling depth of a sampling device is typically determined by visually analyzing a trace water sample exhibiting stratification. The sampling device is then lowered to the designated depth, and the sampling operation is completed by activating its trigger switch. However, in trace water samples exhibiting stratification, insufficient settling time can lead to unclear boundaries between strata. This results in inaccurate visual analysis of the strata, leading to inaccurate water sample quality. Furthermore, the lack of a hydrophobic coating on the inner wall of the sample container (pipette) before sampling causes sample to adhere to the zinc film target position, further compromising accuracy in stratified sampling and air isolation. Summary of the Invention

[0005] This application provides a method, apparatus, analyzer, and medium for micro-water sample layering and air isolation. It can objectively identify the water sample layering interface using optical imaging and image analysis technology. Based on the identification results, it automatically plans and executes high-precision layered liquid sample aspiration operations. This avoids situations where insufficient settling time leads to unclear boundaries between sample layers, resulting in inaccurate analysis results when manually determining the layers to be aspirated through visual analysis, and consequently, inaccurate water sample results. By coating the inside of the sample container with a hydrophobic coating and introducing gas isolation during sampling, cross-contamination and sample denaturation are prevented. This also avoids the phenomenon of water sample adhering to the container walls when the sample is discharged from the container to the target position of the zinc film, thereby improving the accuracy of micro-water sample layering and air isolation.

[0006] A first aspect of this application provides a method for stratified aspiration and air isolation of trace water samples, the method comprising: The layering information of the water sample to be tested is determined based on the side image of the water sample to be tested, and the first layering information is obtained. The water sample to be tested is a water sample that has undergone layering after being left to stand. Based on the first layering information and the side image of the water sample to be tested, the sampling strategy corresponding to the sampling device is determined, and a first sampling strategy is obtained. The first sampling strategy includes the sampling position, sampling volume, sampling depth and sample air isolation strategy of the sampling device. The sampling device includes a sampling arm and a sample container. The sampling arm is a mechanical arm for holding the sample container. An image acquisition device is provided near the sample container. The sampling device is used to sample the water sample to be tested according to the sampling location, sampling volume, sampling depth and sample air isolation strategy in the first sampling strategy to obtain the target water sample.

[0007] In this example, the layering information of the water sample to be tested is determined based on the side image of the water sample to be tested, thus obtaining the first layering information. The water sample to be tested is a water sample that has exhibited layering after being left to stand. Based on the first layering information and the side image of the water sample to be tested, a sampling strategy corresponding to the sampling device is determined, thus obtaining the first sampling strategy. The first sampling strategy includes the sampling position, sampling volume, sampling depth, and sample air isolation strategy of the sampling device. The sampling device includes a sampling arm and a sample container. The sampling arm is a robotic arm used to hold the sample container. An image acquisition device is provided near the sample container. The sampling device is used to sample the water sample to be tested according to the sampling position, sampling volume, sampling depth, and sample air isolation strategy in the first sampling strategy to obtain the target water sample, thereby improving the accuracy of micro-water sample layering and air isolation when sampling the water sample to be tested.

[0008] In one possible implementation, a method for determining the layering information of a water sample to be tested based on a side image of the sample, and obtaining first layering information, includes: The side image of the water sample to be tested is subjected to image enhancement processing to obtain the first water sample image; Based on the first water sample image, the type of the object to be detected in the water sample to be detected is predicted to obtain the first type information; Based on the first type of information, the layering information corresponding to the object to be detected in the water sample to be tested is determined, and the first layering information is obtained.

[0009] In one possible implementation, a method for performing image enhancement processing on a side image of the water sample to be detected to obtain a first water sample image includes: The side image of the water sample to be tested is subjected to image segmentation processing to obtain a first set of images to be processed; Image super-resolution processing is performed on the first image to be processed in the first set of images to be processed to obtain the second set of images to be processed. The first light intensity value is obtained by determining the light intensity value of the environment in which the water sample to be detected is located based on the second image to be processed in the second image to be processed set. Based on the first illumination intensity value, construct the transmittance matrix corresponding to each second image in the second image set to be processed, and obtain the first transmittance matrix set; The first image to be processed is enhanced by using the first transmittance matrix in the first transmittance matrix set to obtain the third image to be processed. The third image in the third set of images to be processed is seamlessly stitched together to obtain the first water sample image.

[0010] In one possible implementation, a method for determining the stratification information corresponding to the object to be detected in the water sample to be tested based on the first type information, and obtaining the first stratification information, includes: The physicochemical properties of the object to be detected corresponding to the first type of information are determined to obtain the first characteristic information. The object to be detected can be any one of pollutants, suspended particles or target analytes in the water sample to be detected. Perform time-series feature analysis on the historical hierarchical information corresponding to the first characteristic information and the first category information to obtain the second characteristic information; The second feature information is corrected based on the historical environmental information corresponding to the water sample to be tested to obtain the third feature information; Based on the first characteristic information and the third feature information, a diffusion model corresponding to the object to be detected corresponding to the first type information is constructed to obtain the first diffusion model; The first diffusion model is used to predict the stratification information corresponding to the object to be detected in the water sample to be tested, and the first stratification information is obtained.

[0011] In one possible implementation, a sampling strategy corresponding to the sampling device is determined based on the first layering information and a side image of the water sample to be tested, to obtain a first sampling strategy, including: The sampling area corresponding to the sampling device is determined based on the side image of the water sample to be tested, and the first sub-sampling strategy is obtained. Based on the first layer information, the sampling depth corresponding to the sampling device is determined, and a second sub-sampling strategy is obtained. Based on the first type of information, the sampling capacity corresponding to the sampling device is determined, and a third sub-sampling strategy is obtained; Based on the first type of information, the sample air isolation strategy corresponding to the sampling device is determined, and the fourth sub-sampling strategy is obtained. The first sub-sampling strategy, the second sub-sampling strategy, the third sub-sampling strategy, and the fourth sub-sampling strategy are combined to obtain the first sampling strategy.

[0012] A second aspect of this application provides a device for the stratified absorption and air isolation of trace water samples, the device comprising: The first determining module is used to determine the layering information of the water sample to be tested based on the side image of the water sample to be tested, and obtain the first layering information. The water sample to be tested is a water sample that has undergone layering after being left to stand. The second determining module is used to determine the sampling strategy corresponding to the sampling device based on the first layering information and the side image of the water sample to be tested, and obtain the first sampling strategy. The first sampling strategy includes the sampling position, sampling volume, sampling depth and sample air isolation strategy of the sampling device. The sampling device includes a sampling arm and a sample container. The sampling arm is a mechanical arm for holding the sample container. An image acquisition device is provided near the sample container. The sampling module is used to sample the water sample to be tested using the sampling device according to the sampling location, sampling volume, sampling depth and sample air isolation strategy in the first sampling strategy, so as to obtain the target water sample.

[0013] In one possible implementation, the first determining module is specifically used for: The side image of the water sample to be tested is subjected to image enhancement processing to obtain the first water sample image; Based on the first water sample image, the type of the object to be detected in the water sample to be detected is predicted to obtain the first type information; Based on the first type of information, the layering information corresponding to the object to be detected in the water sample to be tested is determined, and the first layering information is obtained.

[0014] In one possible implementation, in performing image enhancement processing on the side image of the water sample to be detected to obtain a first water sample image, the first determining module is specifically used for: The side image of the water sample to be tested is subjected to image segmentation processing to obtain a first set of images to be processed; Image super-resolution processing is performed on the first image to be processed in the first set of images to be processed to obtain the second set of images to be processed. The first light intensity value is obtained by determining the light intensity value of the environment in which the water sample to be detected is located based on the second image to be processed in the second image to be processed set. Based on the first illumination intensity value, construct the transmittance matrix corresponding to each second image in the second image set to be processed, and obtain the first transmittance matrix set; The first image to be processed is enhanced by using the first transmittance matrix in the first transmittance matrix set to obtain the third image to be processed. The third image in the third set of images to be processed is seamlessly stitched together to obtain the first water sample image.

[0015] In one possible implementation, in determining the stratification information corresponding to the object to be detected in the water sample based on the first type information to obtain the first stratification information, the first determining module is specifically used for: The physicochemical properties of the object to be detected corresponding to the first type of information are determined to obtain the first characteristic information. The object to be detected can be any one of pollutants, suspended particles or target analytes in the water sample to be detected. Perform time-series feature analysis on the historical hierarchical information corresponding to the first characteristic information and the first category information to obtain the second characteristic information; The second feature information is corrected based on the historical environmental information corresponding to the water sample to be tested to obtain the third feature information; Based on the first characteristic information and the third feature information, a diffusion model corresponding to the object to be detected corresponding to the first type information is constructed to obtain the first diffusion model; The first diffusion model is used to predict the stratification information corresponding to the object to be detected in the water sample to be tested, and the first stratification information is obtained.

[0016] In one possible implementation, the second determining module is specifically used for: The sampling area corresponding to the sampling device is determined based on the side image of the water sample to be tested, and the first sub-sampling strategy is obtained. Based on the first layer information, the sampling depth corresponding to the sampling device is determined, and a second sub-sampling strategy is obtained. Based on the first type of information, the sampling capacity corresponding to the sampling device is determined, and a third sub-sampling strategy is obtained; Based on the first type of information, the sample air isolation strategy corresponding to the sampling device is determined, and the fourth sub-sampling strategy is obtained. The first sub-sampling strategy, the second sub-sampling strategy, the third sub-sampling strategy, and the fourth sub-sampling strategy are combined to obtain the first sampling strategy.

[0017] A third aspect of this application provides a terminal including a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is configured to invoke the program instructions to execute the step instructions as described in the first aspect of this application.

[0018] A fourth aspect of this application provides a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in the first aspect of this application.

[0019] A fifth aspect of this application provides a computer program product, wherein the computer program product 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 described in the first aspect of this application. The computer program product may be a software installation package. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 A partial structural schematic diagram of a laser water quality analyzer is provided for embodiments of this application; Figure 2 This application provides a schematic flowchart of a method for stratified aspiration and air isolation of a trace water sample. Figure 3 This application provides a schematic diagram of a side view of a water sample to be tested, as shown in the embodiments of this application. Figure 4 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application; Figure 5 This application provides a schematic diagram of a device for the stratified absorption and air isolation of a trace water sample. Detailed Implementation

[0022] 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 embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] The terms "first," "second," etc., in the specification, claims, and accompanying 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.

[0024] In this application, the reference to "embodiment" means that a specific feature, structure, 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 in the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. Those skilled in the art will explicitly and implicitly understand that the embodiments described in this application can be combined with other embodiments. To better understand the method for stratified aspiration and air isolation of trace water samples provided by the embodiments of this application, a brief introduction to existing methods for stratified aspiration and air isolation of trace water samples is given below. In existing technologies, the sampling depth of a sampling device is typically determined by visually analyzing a trace water sample exhibiting stratification. The sampling device is then lowered to the designated depth, and the sampling operation is completed by activating its trigger switch. However, in trace water samples exhibiting stratification, insufficient settling time can lead to unclear boundaries between strata. This results in inaccurate visual analysis of the strata, leading to inaccurate water sample quality. Furthermore, the lack of a hydrophobic coating on the inner wall of the sample container (pipette) before sampling causes sample to adhere to the zinc film target position, further compromising accuracy in stratified sampling and air isolation.

[0025] To address the aforementioned technical problems, this application provides a method for the layered aspiration and air isolation of trace water samples. The method involves image enhancement processing of a side view of the water sample to be tested to obtain a first water sample image. Based on the first water sample image, the type information of the object to be detected in the water sample is determined, resulting in first type information. Based on the first type information, the layering information of the object to be detected in the water sample is determined, resulting in first layering information. Based on the first layering information and the first type information, a sampling strategy is determined for sampling the water sample and for air isolation of the sample, resulting in a first sampling strategy. Based on the first sampling strategy, a sampling device is used to sample the water sample to obtain the target sample, thereby improving the accuracy of the layered aspiration and air isolation of trace water samples.

[0026] To better understand the micro-water sample stratification and air isolation method provided in this application, which involves drying the water sample after it has been collected using this method and discharged to a designated location, the method allows for the extraction of spectral information from the target water sample after laser bombardment. The existing water sample drying and shaping methods are briefly described below. Current technologies are primarily designed for water samples of milliliter volume and above, making it difficult to adapt to the processing needs of 1-100 μL micro-volume water samples, thus exhibiting significant technical limitations. Specifically, traditional constant temperature drying technology uses a single temperature (such as 60-70℃) to heat the water sample. Although it is simple to operate, the surface area to volume ratio of microliter water samples is significantly higher. A single high temperature can easily cause the moisture to rise suddenly and boil violently, causing solute to splash and form incomplete spots, or causing local solute to be over-concentrated and caking, resulting in irregular shapes. Traditional natural air drying technology relies on the ambient temperature and humidity to evaporate the moisture naturally. This not only takes several minutes to tens of minutes and is inefficient, but is also easily affected by ambient airflow, causing a large amount of solute to accumulate at the edge of the spot, while the central area forms a gap due to insufficient solute, which further affects subsequent detection. Meanwhile, existing technologies lack effective spot position calibration mechanisms. Slight substrate displacement and solute shrinkage during water sample drying can easily cause the dried spots to deviate from the initial water sample position, resulting in inaccurate focusing during laser detection and causing signal deviation. Furthermore, spot defect repair often relies on manual operation, such as manually adjusting the substrate position with a microscope, wiping rough edges with cotton swabs, or adding exogenous solutes to fill gaps. This not only takes 5-10 minutes per sample, making it inefficient for batch analysis, but also easily introduces exogenous impurities to contaminate the sample, or damages the spot structure due to human error. Ultimately, this limits the accuracy and scope of laser water quality analysis in micro-scale water sample scenarios (such as trace heavy metal detection and trace organic matter analysis).

[0027] To address the aforementioned issues, this application provides a method for the layered aspiration and air isolation of micro-volume water samples. This method utilizes a gradient temperature-controlled drying mechanism, position calibration processing, and morphology optimization processing to achieve the regularization of dried spots in micro-volume water samples, thereby reducing detection errors and external interference, and ultimately improving the accuracy and efficiency of laser water quality analysis.

[0028] Please see Figure 1 , Figure 1 A partial structural schematic diagram of a laser water quality analyzer is shown. Figure 1As shown, a vertical bombardment system with a movable sample stage and a fixed laser source may include a control platform and a laser water quality analyzer. The control platform is communicatively connected to at least one laser water quality analyzer. The liquids that the laser water quality analyzer can analyze include, but are not limited to, water, oil, and pharmaceutical solutions. The control platform performs data backup and subsequent processing based on the analysis results of the liquids from the laser water quality analyzer.

[0029] Figure 1 The text describes the use of a laser water quality analyzer as a device for stratified aspiration and air isolation of trace water samples. (For example...) Figure 1 The diagram shows a partial structural schematic of a laser water quality analyzer, including a laser bombardment unit 11, a water sample preparation unit 12, and a detection unit (not shown). Water samples are extracted using the micro-water sample layering and air isolation method provided in this embodiment. The extracted water samples are dried in the water sample preparation area 121 of the water sample preparation unit 12 to form spots. The laser output from the laser bombardment unit 11 bombards the spots on the water sample preparation area 121 (movable sample stage) of the water sample preparation unit 12 through its end 111. The water sample preparation area 121 is moved using a cross roller guide and a pressure point ceramic fine-tuning mechanism. The detection unit uses a spectrometer. The laser water quality analyzer mainly detects heavy metals and non-metals in the spots formed after the liquid is dried. The laser bombardment unit 11 is a fixed laser source, vertically fixed to a 20mm carbon steel substrate (flatness <2μm / m²) via a flange. The emission axis of the laser bombardment unit 11 makes an angle of 90±0.01° with the horizontal plane, and the position of the laser bombardment unit 11 remains constant. The carbon-based steel plate is mounted on four L-shaped mounting bases, with two L-shaped mounting bases on each side of the carbon-based steel plate.

[0030] Understandably, a predetermined volume (e.g., 10 μL) of liquid is placed in the water sample preparation area 121 (hereinafter referred to as the substrate), and the liquid in the water sample preparation area 121 is dried to form spots. The laser generated by the laser instrument of the laser bombardment unit 11 contacts the dried residue (spots) of the liquid. The spots form plasma at high temperature, achieving a transition from a low-energy state to a high-energy state. However, the high-energy state is unstable and immediately returns to the ground state (i.e., the original state). At this time, energy is emitted in the form of light, and the light emitted by each element is different. The spectrometer of the detection module monitors the light generated by the laser bombardment unit 11 bombarding the spots. The liquid results can be analyzed based on the data detected by the detection unit. In other words, the laser water quality analyzer can quickly detect multiple elements without consuming chemical reagents.

[0031] Optionally, the water sample preparation unit 12 includes a support platform, an unwinding mechanism, a winding structure, and a flexible membrane. The flexible membrane is unwound from the unwinding mechanism, passes over the support platform, and a predetermined volume (e.g., 10 μL) of liquid is placed in the water sample preparation area 121 on the support platform. Before the next test, the unwinding mechanism and the winding structure work together to wind the discarded flexible membrane onto the winding structure, and the unused flexible membrane is placed on the support platform so that a predetermined volume (e.g., 10 μL) of liquid can be placed in the water sample preparation area 121 on the support platform. The implementation of the unwinding mechanism and the winding structure can be selected from existing technologies and will not be described in detail here.

[0032] Optionally, the flexible membrane may be made of zinc.

[0033] Please see Figure 2 , Figure 2 This application provides a schematic flowchart of a method for stratified aspiration and air isolation of a trace water sample. Figure 2 As shown, the method includes: 201. Determine the layering information of the water sample to be tested based on the side image of the water sample to be tested, and obtain the first layering information. The water sample to be tested is a water sample that has undergone layering after being left to stand.

[0034] Specifically, the method involves acquiring a side image of the water sample to be tested using a common image acquisition device (such as an industrial camera or image sensor), performing image enhancement processing on the acquired side image to obtain a first water sample image, determining the type information of the object to be detected in the water sample based on the first water sample image to obtain first type information, and determining the stratification information corresponding to the water sample based on the first type information to obtain first stratification information. The object to be detected refers to pollutants, suspended particles, or target analytes in the water sample. Please refer to the attached image for the side image of the water sample. Figure 3 As shown; a common image acquisition device can be a camera fixedly mounted above the sampling platform to capture a head-up (surface) image of the water sample container (a transparent container for storing the water sample to be tested); and one or more cameras / sensors fixedly mounted on the sampling arm (a robotic arm for holding the sample container) to observe the state of the liquid column being drawn from the sample container from the side (for air isolation monitoring).

[0035] 202. Based on the first layering information and the side image of the water sample to be tested, determine the sampling strategy corresponding to the sampling device to obtain the first sampling strategy. The first sampling strategy includes the sampling position, sampling volume, sampling depth and sample air isolation strategy of the sampling device. The sampling device includes a sampling arm and a sample container. The sampling arm is a mechanical arm for holding the sample container. An image acquisition device is provided near the sample container.

[0036] Specifically, a first sub-sampling strategy can be obtained by extracting the region where the object to be detected is located in the water sample from the side image of the water sample to be tested, and defining the region where the object to be detected is located as the sampling area corresponding to the sampling device; a second sub-sampling strategy can be obtained by determining the depth information of the object to be detected in the water sample to be tested based on the first layering information, and defining the depth information of the object to be detected as the sampling depth corresponding to the sampling device; a third sub-sampling strategy can be obtained by determining the sampling capacity corresponding to the sampling device based on the first type information, where the sampling capacity can be understood as the volume of the target sample; a fourth sub-sampling strategy can be obtained by determining the sample air isolation strategy when the sampling device performs air isolation on the collected sample after completing the sampling of the water sample to be tested based on the first type information; and the first, second, third, and fourth sub-sampling strategies can be combined to determine the sampling strategy when sampling the water sample to be tested, thus obtaining the first sampling strategy.

[0037] 203. Using the sampling device, the water sample to be tested is sampled according to the sampling location, sampling volume, sampling depth and sample air isolation strategy in the first sampling strategy to obtain the target water sample.

[0038] Specifically, the first sampling strategy can be transmitted to the sampling device through a common data transmission method. After receiving the first sampling strategy, the sampling device will adjust the air pressure in the sample container used to hold the sample according to the first sampling strategy. The sample container adopts a negative pressure sampling device, which can more conveniently sample the water sample to be tested and effectively provide sufficient protection for the collected water sample. When the sample container is sampling the water sample to be tested, a microflow meter can be used to monitor the flow rate of the water sample to be tested in real time. Furthermore, when the negative pressure absorption of the sample container fails (the flow rate of the water sample to be tested is abnormal when the sample container is absorbing the water sample to be tested), the microflow meter can also be used to control the flow rate of the water sample to be tested, thereby completing the absorption of the water sample to be tested.

[0039] After setting the capacity of the sample container, the sampling device uses a sampling arm to clamp the sample container according to the sampling area and sampling depth in the first sampling strategy to perform sampling. During the sampling operation, the sampling device also needs to perform air isolation on the collected water sample according to the sample air isolation strategy in the first sampling strategy, and monitor the air isolation status of the collected water sample in real time. If the air isolation is good, the sampling device is retracted after completing the sampling of the water sample to be tested, and the target water sample is obtained. If the air isolation is insufficient, inert gas is slowly injected into the sample container to slowly expel all the sample in the sample container, and the air pressure in the sample container is reset. Then, the water sample to be tested is sampled again until the air isolation of the collected water sample is good, and the target water sample is obtained. The sample air isolation strategy can use inert gas or air to isolate the target water sample, for example, extracting 10 μL of air or inert gas to form a slug isolation layer.

[0040] Specifically, one or more cameras or sensors can be installed on the sampling arm (a robotic arm that can hold the sample container and rotate it in all directions) near the sample container to monitor the state of the water sample in the sample container in real time when the sampling device is sampling the water sample to be tested. The air isolation of the collected water sample can be judged by whether there are air bubbles in the water sample in the sample container. If air bubbles are present in the collected water sample, it means that the air isolation of the collected water sample is insufficient, and the water sample to be tested needs to be sampled again; if there are no air bubbles in the collected water sample, it means that the air isolation of the collected water sample is good.

[0041] Specifically, after acquiring the target water sample, the sample container needs to discharge the sample onto the target position of the zinc film. During this discharge, a binarized image of the zinc film can be acquired in real time. Since the zinc film is made of metal, different from the sample stage material, there is a clear difference between the zinc film and the sample stage in the binarized image. This allows the contour information of the zinc film to be determined using common edge detection algorithms (such as adaptive threshold segmentation, edge detection operators, region growing, etc.), and the center point of the zinc film to be determined based on this contour information. This center point is then used as the target position of the zinc film. After determining the target position, the sample container can be inverted and paused for a preset settling time to expel the inert gas or other gas used for air isolation of the target water sample. To prevent the target water sample from adhering to the container walls, this solution employs a spraying or dipping method to coat the inner wall of the sample container (pipette) with a hydrophobic polytetrafluoroethylene (PTFE) coating. This hydrophobic coating, through the creation of micro-nano rough structures and low surface energy chemical modifications on the inner wall of the sample container (pipette), creates a "Cassie-Baxter state" on the inner wall (the droplet of the target sample only contacts the micro-nano protrusions on the hydrophobic coating surface, with a contact angle ≥150° and a roll-off angle ≤10°). This achieves anti-adhesion, anti-contamination, and easy-to-clean effects, further preventing the target water sample from adhering to the container walls. After expelling the inert gas or air used for air isolation of the target water sample, the sample container is aligned with the target position on the zinc film, accurately discharging the target water sample onto the target position of the zinc film. The preset settling time can be determined by user input or by system default.

[0042] In this example, the layering information of the water sample to be tested is determined based on the side image of the water sample to be tested, thus obtaining the first layering information. The water sample to be tested is a water sample that has exhibited layering after being left to stand. Based on the first layering information and the side image of the water sample to be tested, a sampling strategy corresponding to the sampling device is determined, thus obtaining the first sampling strategy. The first sampling strategy includes the sampling position, sampling volume, sampling depth, and sample air isolation strategy of the sampling device. The sampling device includes a sampling arm and a sample container. The sampling arm is a robotic arm used to hold the sample container. An image acquisition device is provided near the sample container. The sampling device is used to sample the water sample to be tested according to the sampling position, sampling volume, sampling depth, and sample air isolation strategy in the first sampling strategy to obtain the target water sample, thereby improving the accuracy of micro-water sample layering and air isolation when sampling the water sample to be tested.

[0043] In one possible implementation, a method for determining the layering information of a water sample to be tested based on a side image of the sample, and obtaining first layering information, includes: A1. Perform image enhancement processing on the side image of the water sample to be tested to obtain the first water sample image; A2. Based on the first water sample image, predict the type of the object to be detected in the water sample to be tested to obtain the first type information, wherein the object to be detected is the object to be tested in the water sample to be tested. A3. Determine the layering information corresponding to the object to be detected in the water sample based on the first type of information to obtain the first layering information.

[0044] When using computer vision technology to process an image as a whole, low image quality can lead to the loss of subtle details or important features, resulting in inaccurate processing results. Therefore, image enhancement processing is necessary to highlight subtle details or supplement important features, thereby improving the accuracy of image processing results.

[0045] Specifically, the process can involve segmenting the side image of the water sample to be tested to obtain a set of images to be processed; performing image enhancement processing on the first image to be processed in the first set of images to be processed based on the atmospheric light intensity information corresponding to the first image to be processed in the first set of images to be processed; and then stitching the first image to be processed in the first set of images to be processed after image enhancement to obtain the first water sample image.

[0046] After obtaining the first water sample image, the RGB value feature information or state features of each layer in the first water sample image can be extracted using general computer vision calculations to obtain the first object feature information. The first object feature information is then input into a general recognition model to identify the type information corresponding to the object to be detected in the water sample to be tested, thereby obtaining the first type information. The state feature information of each layer can be any one of liquid, flocculent, or solid states.

[0047] In a specific example, the first feature information can be obtained by using computer vision to extract the RGB value feature information of each layer of the water sample to be tested, that is, the color feature information of each layer of the water sample to be tested; the first feature information is input into a general recognition model, and the recognition model recognizes that multiple layers in the water sample to be tested have transparent colored layers.

[0048] After obtaining the first type of information, a simulation experiment can be conducted on the object to be tested to extract the sinking velocity of the object in the water sample under different settling times, thus obtaining a set of sinking velocities. A linear fit is then performed on the sinking velocities in the set and the settling times corresponding to those velocities to construct a sinking velocity-settling time variation curve for the object to be tested, thus obtaining the first variation curve. A suitable initial model (such as the PINN model (Physics-Informed Neural Network)) can then be selected. Networks (Physical Information Neural Network Fusion Model) are used to train a selected initial model using the first change curve. The initial model extracts features from the first change curve, including the terminal sinking velocity (the asymptotic value of the first change curve), acceleration time constant (the time required to reach 95% terminal sinking velocity), and trajectory curvature. The extracted feature information is used to adjust the physical parameters and loss weights of the initial model. General sinking equation constraints and general diffusion equation constraints are used as constraints on the loss function of the initial model to optimize it until the initial model converges (the function value of the loss function is minimized), thereby constructing a diffusion model corresponding to the object to be detected in the water sample, resulting in a first diffusion model. The sinking rate corresponding to the object to be detected in the water sample is predicted based on the first diffusion model to obtain a second sinking velocity. The first change curve is then processed by definite integral based on the second sinking velocity to predict the layering information corresponding to the object to be detected in the water sample, resulting in first layering information. In one possible implementation, a method for image enhancement processing of a side image of the water sample to obtain a first water sample image includes: B1. Perform image segmentation processing on the side image of the water sample to be tested to obtain a first set of images to be processed; B2. Perform image super-resolution processing on the first image to be processed in the first image to be processed set to obtain the second image to be processed set. B3. Determine the light intensity value of the environment where the water sample to be tested is located based on the second image to be processed in the second image set to be processed, and obtain the first light intensity value; B3. Construct a transmittance matrix corresponding to each second image in the second image set to be processed based on the first illumination intensity value, and obtain a first transmittance matrix set; B4. Use the first transmittance matrix in the first transmittance matrix set to perform image enhancement processing on the corresponding first image to be processed, and obtain the third image to be processed set. B5. Perform seamless stitching on the third image in the third set of images to be processed to obtain the first water sample image.

[0049] Because water samples have high transmittance and refractive index, light spots may appear in the side images of the water samples to be tested. These light spots will severely reduce the accuracy of image processing when processing the side images of the water samples to be tested. Therefore, before processing the side images of the water samples to be tested, image enhancement processing is required to improve the accuracy of image processing.

[0050] One approach is to use a common image segmentation method to segment the side image of the water sample to be detected into N uniform rectangular images to obtain a first set of images to be processed.

[0051] While the traditional Transformer's self-attention mechanism excels at capturing long-range dependencies, it has limitations when processing color information. Color information in images often exhibits local correlations and certain patterns, but the self-attention mechanism may overemphasize global information during computation, neglecting subtle changes and consistency in local color regions. For example, when processing an image with rich textures and color gradations, the self-attention mechanism may fail to accurately model the interrelationships of colors within local regions, leading to color deviations during super-resolution and resulting in color distortion. Consequently, the accuracy of super-resolution processing of the image is low. Therefore, to improve the accuracy of super-resolution processing, correction processing is necessary for the super-resolution image.

[0052] After obtaining the first set of images to be processed, the first images in the first set of images to be processed can be super-resolution processed using an improved Transformer-based self-attention mechanism to improve their image quality, thus obtaining a second set of images to be processed. M reference high-resolution images corresponding to the second images in the second set of images to be processed are extracted to obtain a reference high-resolution image set. The number of reference high-resolution images in the reference high-resolution image set is M, and M is an integer equal to or equal to 2. This number can be determined by user input or by system default. For each second image in the second set of images to be processed, the pixel value corresponding to each pixel in the second image to be processed can be extracted to obtain a first set of pixel values. The accuracy corresponding to each first pixel value in the first set of pixel values ​​is calculated to obtain a first set of accuracy.

[0053] Specifically, the accuracy rate corresponding to each first pixel value in the first pixel value set can be calculated using the following formula to obtain the first accuracy rate set: In the formula This represents the first accuracy rate in the first accuracy rate set, which can be understood as the first accuracy rate corresponding to the k-th first pixel value in the first pixel value set; This represents the height information of the pixel corresponding to the first pixel value in the first pixel value set; This represents the width information corresponding to the pixel point corresponding to the first pixel value in the first pixel value set; This indicates the number of channels corresponding to the pixel corresponding to the first pixel value in the first pixel value set; This indicates the number of reference high-resolution images in the reference high-resolution image set; This indicates that the position of the k-th image in the second set of images to be processed is... The pixel value of the pixel at that location; This indicates that the position in the m-th reference high-resolution image in the reference high-resolution image set is... The pixel value of the pixel at that location; Indicates an indicator function, when At the time of its establishment, The value of is 1, and conversely, it is 0.

[0054] A first accuracy rate set is obtained by identifying the first accuracy rate set that is lower than the preset accuracy rate threshold. A target accuracy rate set is then obtained. A first pixel value corresponding to each target accuracy rate in the target accuracy rate set is obtained, resulting in a target first pixel value set. Position information of each target first pixel value in the target first pixel value set within the first pixel value set is obtained, resulting in a first position information set. The occurrence probability of each pixel in the second image to be processed corresponding to the first position information set is calculated, and the pixel with the highest occurrence probability in each first position information set is determined as the second pixel value, resulting in a second pixel value set. The second pixel value set is used to replace the target first pixel values ​​in the first pixel value set, resulting in a target pixel value set. Finally, the target pixel values ​​in the target pixel value set are used to replace the pixel values ​​of each pixel in the target image to be processed, resulting in a second image to be processed set.

[0055] Specifically, the probability of each pixel in the second image to be processed corresponding to the first position information set can be calculated using the following formula: In the formula This represents the probability of each pixel in the second image to be processed appearing in the first location information set; This represents the height information of the pixel corresponding to the first pixel value in the first pixel value set; This represents the width information corresponding to the pixel point corresponding to the first pixel value in the first pixel value set; This indicates the number of channels corresponding to the pixel corresponding to the first pixel value in the first pixel value set; This represents the first accuracy rate in the first accuracy rate set; This indicates the preset accuracy threshold. Represents the set of values ​​for the first pixel of the target; This indicates that the position of the k-th image in the second set of images to be processed is... The pixel value of the pixel at that location; This indicates that the position of the k-th image in the second set of images to be processed is... The possible pixel values ​​of the pixel at that location, and satisfying the following conditions: ; This indicates the number of second images to be processed in the second set of images to be processed; This represents the pixel values ​​of all pixels from the first to the kth image in the set of images to be processed. This indicates that the position in the second set of images to be processed, from the first image to the kth image, is... The pixel value corresponding to the pixel at that location; Indicates an indicator function, when If it is established, then The value is 1, otherwise it is 0.

[0056] After obtaining the second set of images to be processed, for each second image to be processed in the second set of images to be processed, the atmospheric light intensity information corresponding to the second image to be processed can be calculated according to the RGB value corresponding to each pixel in each second image to be processed to obtain a set of reference light intensity values; and the reference atmospheric light intensity values ​​in the set of reference light intensity values ​​are weighted and averaged according to preset weight information to obtain the first light intensity value.

[0057] After obtaining the first light intensity value, the transmittance of each pixel in the second image to be processed in the second image to be processed set can be estimated based on the first light intensity value and combined with a general transmittance estimation method (such as atmospheric scattering model and dark channel prior theory). The transmittance of each pixel in the second image to be processed is then arranged according to the arrangement of each pixel in the second image to be processed to obtain the first transmittance matrix set. After obtaining the first set of transmittance matrices, the second image in the second set of images to be processed can be enhanced by combining the atmospheric illumination diffraction model and the first transmittance matrix in the first set of transmittance matrices to remove the light spots caused by the transmission / refraction of the water sample, thereby improving the image quality of the second set of images to be processed and obtaining the third set of images to be processed.

[0058] Specifically, image enhancement processing can be performed on the second image in the second set of images to be processed by combining the atmospheric illumination diffraction model and the first transmittance matrix in the first transmittance matrix set, as shown in the following formula, to obtain the third set of images to be processed. In the formula This refers to the third image to be processed in the third set of images to be processed; This refers to the second image to be processed in the second set of images to be processed; This represents the first light intensity value; This represents the first transmittance matrix in the first transmittance matrix set; This represents the diffraction parameters of the atmospheric illumination diffraction model. These are constant values ​​and can be determined by user input or by system default. "max" indicates the operation of taking the maximum value.

[0059] After obtaining the third set of images to be processed, the third images in the third set of images to be processed can be seamlessly stitched together using a general image seamless stitching method to obtain the first water sample image.

[0060] In this example, color correction is performed on the second image to be processed by obtaining the probability of different pixel values ​​appearing at each pixel point in the second image to be processed, thereby avoiding color distortion in the second image to be processed after image super-resolution processing; image enhancement is performed on the second image to be processed in the second image to be processed set by calculating the atmospheric light intensity information corresponding to the water sample to be detected, and the enhanced third image to be processed in the third image to be processed set is seamlessly stitched to obtain the first water sample image; thereby improving the accuracy of the obtained first water sample image, and thus improving the accuracy when performing micro-water sample stratification and air isolation on the water sample to be detected.

[0061] In one possible implementation, a method for determining the stratification information corresponding to the object to be detected in the water sample to be tested based on the first type information, and obtaining the first stratification information, includes: C1. Determine the physicochemical properties of the object to be detected corresponding to the first type of information to obtain the first characteristic information. The object to be detected can be any one of pollutants, suspended particles or target analytes in the water sample to be tested. C2. Perform time-series feature analysis on the historical hierarchical information corresponding to the first characteristic information and the first category information to obtain the second characteristic information; C3. Correct the second feature information based on the historical environmental information corresponding to the water sample to be tested to obtain the third feature information; C4. Construct a diffusion model corresponding to the object to be detected corresponding to the first type of information based on the first characteristic information and the third feature information to obtain the first diffusion model; C5. Using the first diffusion model, predict the stratification information corresponding to the object to be detected in the water sample to be detected, and obtain the first stratification information.

[0062] Since the diffusion rate of the object to be detected in water varies depending on the type of information, it is necessary to combine the physicochemical properties of the object to be detected to determine its diffusion characteristics, and then determine the water layer in which the object is located based on its diffusion characteristics to obtain the first layer information.

[0063] Specifically, the first characteristic information can be obtained by querying the research report corresponding to the object to be detected based on the first type of information, determining the physicochemical characteristics of the object to be detected corresponding to the first type of information, and obtaining the first characteristic information.

[0064] After obtaining the first characteristic information, the following steps can be taken: First, extract the historical stratification information of the object to be detected corresponding to the first type of information in the water sample to be detected from a preset database to obtain a first historical stratification information set; Extract the graph features corresponding to the first historical stratification information in the first historical stratification information set according to its corresponding time information to obtain a first graph feature information set; Perform graph convolution processing on the first graph feature information in the first graph feature information set using a general convolutional neural network, such as the GATv2 convolutional neural network model (Graph Attention Network v2, an improved graph attention convolutional neural network model), to obtain a second graph feature information set; Perform temporal enhancement processing on the second graph feature information in the second graph feature information set to obtain a first temporal feature information set; Perform feature fusion on the first temporal feature information in the first temporal feature information set to obtain second feature information. The first historical stratification information set includes the stratification information of the object to be tested corresponding to the first type of information when the trace water sample was stratified and absorbed before the current time, and the stratification information of the object to be tested corresponding to the first type of information under the standard test environment; the current time can be understood as the time when the trace water sample was stratified and absorbed.

[0065] Since the degree of molecular motion varies at different temperatures, the layering information of the object to be detected differs at different temperatures. Therefore, it is necessary to correct the first feature information based on the historical environmental information of the water sample to be detected, thereby improving the accuracy of the feature information.

[0066] After obtaining the second feature information, a first historical environmental information set can be obtained by extracting the historical environmental temperature information corresponding to the water sample to be tested; a temperature-stratification change curve can be constructed based on the first historical environmental information in the first historical environmental information set and the first historical stratification information in the first historical stratification information set to obtain a first curve; the second derivative corresponding to each data point on the first curve can be extracted to obtain a second derivative set; since the second derivative on the curve can reflect the changing trend and rate of change of the data points on the curve, the influence degree between the first historical environmental information in the first historical environmental information set and the first historical stratification information in the first historical stratification information set can be analyzed based on the second derivative in the second derivative set to obtain a first influence degree set; the first influence degree in the first influence degree set can be weighted and averaged to obtain a second influence degree; the value of the second influence degree can be used as weight information to weight the second feature information to obtain a third feature information. The first historical environmental information in the first historical environmental information set includes the external environmental temperature corresponding to each time a trace water sample was drawn up before the current time.

[0067] After obtaining the third feature information, the diffusion trend of the object to be detected corresponding to the first type of information can be predicted by inputting the first feature information and the third feature information into a preset diffusion prediction model, thereby obtaining a first diffusion model. The first diffusion model can be understood as a probability model of the appearance of the object to be detected corresponding to the first type of information in each stratum of the water sample to be tested.

[0068] After obtaining the first diffusion model, the first layer information can be obtained by extracting the layer with the highest probability of the detected object corresponding to the first type of information in each layer of the water sample to be tested.

[0069] In this example, a diffusion model corresponding to the object to be detected corresponding to the first type of information is constructed based on the physicochemical properties of the object to be detected, the historical stratification information of the first type of information in the water sample to be detected, and the historical ambient temperature information of the water sample to be detected. A first diffusion model is obtained, and the stratification information corresponding to the object to be detected in the water sample to be detected is predicted by the first diffusion model to obtain the first stratification information. This improves the accuracy of the first stratification information, and further improves the accuracy when performing micro-water sample stratification and air isolation on the water sample to be detected.

[0070] In one possible implementation, a method for determining the stratification information corresponding to the object to be detected in the water sample to be tested based on the first type information, and obtaining the first stratification information, includes: D1. Determine the sampling area corresponding to the sampling device based on the side image of the water sample to be tested, and obtain the first sub-sampling strategy; D2. Determine the sampling depth corresponding to the sampling device based on the first layering information to obtain the second sub-sampling strategy; D3. Determine the sampling capacity corresponding to the sampling device based on the first type of information to obtain the third sub-sampling strategy; D4. Determine the sample air isolation strategy corresponding to the sampling device based on the first type of information to obtain the fourth sub-sampling strategy; D5. Combine the first sub-sampling strategy, the second sub-sampling strategy, the third sub-sampling strategy, and the fourth sub-sampling strategy to obtain the first sampling strategy.

[0071] Specifically, image detection can be performed on the side image of the water sample to be tested using a general image detection method to extract the location information corresponding to the area where the object to be detected is located in the side image of the water sample to be tested, thereby obtaining first location information; the first location information is mapped in the water sample to be tested, thereby mapping the first location information from the side image of the water sample to the water sample to be tested in the actual environment, thereby obtaining second location information; wherein, the second location information can be understood as the location information corresponding to the center point of the object to be detected in the water sample to be tested; the second location information is determined as the location information corresponding to the sampling area of ​​the sampling device, thereby obtaining a first sub-sampling strategy.

[0072] While obtaining the first sub-sampling strategy, the first depth information can be obtained by extracting the depth corresponding to the water layer corresponding to the first layer information; the first depth information can be determined as the sampling depth of the sampling device to obtain the second sub-sampling strategy.

[0073] While obtaining the second sub-sampling strategy, the first sample volume information can be obtained by querying the sample volume corresponding to the first type of information in a preset sampling volume lookup table based on the first type of information; the maximum capacity of the sample container of the sampling device can be extracted to obtain the second sample volume information; the initial air pressure information of the sample container of the sampling device can be extracted to obtain the first air pressure information; the air pressure information in the sample container of the sampling device can be calculated based on the first sample volume information, the second sample volume information, and the first air pressure information to obtain the second air pressure information; and the second air pressure information can be determined as the third sub-sampling strategy. The preset sampling volume lookup table includes the sample volume corresponding to each type of information during sampling; when the air pressure information of the sample container of the sampling device is the first air pressure information, the sample volume that the sample container can absorb through negative pressure is the first sample volume information.

[0074] Specifically, the second pressure information can be obtained by calculating the pressure information in the sample container of the sampling device based on the first sample volume information, the second sample volume information, and the first pressure information using the method shown in the following formula: In the formula This indicates the second air pressure information; This indicates the first air pressure information; This indicates the volume information of the second sample; This indicates the volume information of the first sample.

[0075] Specifically, when the sample container is sampling the water sample to be tested, the sample flow rate of the sample container during sampling can be monitored in real time using a microflow meter. When the negative pressure absorption of the sample container fails (the sample flow rate of the sample container during sampling is abnormal), the microflow meter can be used to switch the sampling method of the sample container. By using microflow closed-loop control, the sample flow rate of the sample container during sampling is ensured to be kept within acceptable limits. This avoids the destruction of the stratification of the sample due to excessively high sample flow rate during sampling, thereby improving the accuracy of the sample container during sampling.

[0076] While obtaining the third sub-sampling strategy, the first sample air isolation material information can be obtained by selecting a liquid or gas that does not react with the object to be detected in the water sample as the sample air isolation material according to the first type information; and the fourth sub-sampling strategy can be obtained by selecting an appropriate sample air isolation method to isolate the sample collected by the sampling device according to the type of the first sample air isolation material information.

[0077] After obtaining the first sub-sampling strategy, the second sub-sampling strategy, the third sub-sampling strategy, and the fourth sub-sampling strategy can be jointly determined as the sampling strategy corresponding to the water sample to be tested, thus obtaining the first sampling strategy.

[0078] In this example, image detection technology is used to determine the accurate location of the object to be detected in the water sample, and the sampling strategy of the sampling device is generated by combining the first layer information and the first category information, thereby improving the accuracy of the sampling device when sampling, and further improving the accuracy when performing micro-water sample layering and air isolation on the water sample to be detected.

[0079] For examples consistent with the above embodiments, please refer to... Figure 4 , Figure 4This is a schematic diagram of the structure of a terminal provided in an embodiment of this application, such as... Figure 4 As shown, it includes a processor, an input device, an output device, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions. The program includes instructions for performing the following steps. The layering information of the water sample to be tested is determined based on the side image of the water sample to be tested, and the first layering information is obtained. The water sample to be tested is a water sample that has undergone layering after being left to stand. Based on the first layering information and the side image of the water sample to be tested, the sampling strategy corresponding to the sampling device is determined, and a first sampling strategy is obtained. The first sampling strategy includes the sampling position, sampling volume, sampling depth and sample air isolation strategy of the sampling device. The sampling device includes a sample container and an image acquisition device is provided near the sample container. The sampling device is used to sample the water sample to be tested according to the sampling location, sampling volume, sampling depth and sample air isolation strategy in the first sampling strategy to obtain the target water sample.

[0080] The above mainly describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the terminal includes the corresponding hardware structure and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0081] This application embodiment can divide the terminal into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0082] For those consistent with the above, please refer to Figure 5 , Figure 5 This application provides a schematic diagram of a device for the stratified absorption and air isolation of a trace water sample. Figure 5As shown, the device includes: The first determining module 501 is used to determine the layering information of the water sample to be tested based on the side image of the water sample to be tested, and obtain the first layering information. The water sample to be tested is a water sample that has undergone layering after being left to stand. The second determining module 502 is used to determine the sampling strategy corresponding to the sampling device based on the first layering information and the side image of the water sample to be tested, and obtain the first sampling strategy. The first sampling strategy includes the sampling position, sampling volume, sampling depth and sample air isolation strategy of the sampling device. The sampling device includes a sampling arm and a sample container. The sampling arm is a mechanical arm for holding the sample container. An image acquisition device is provided near the sample container. The sampling module 503 is used to use the sampling device to sample the water sample to be tested according to the sampling location, sampling volume, sampling depth and sample air isolation strategy in the first sampling strategy, so as to obtain the target water sample.

[0083] In one possible implementation, the first determining module 501 is specifically used for: The side image of the water sample to be tested is subjected to image enhancement processing to obtain the first water sample image; Based on the first water sample image, the type of the object to be detected in the water sample to be detected is predicted to obtain the first type information; Based on the first type of information, the layering information corresponding to the object to be detected in the water sample to be tested is determined, and the first layering information is obtained.

[0084] In one possible implementation, in performing image enhancement processing on the side image of the water sample to be detected to obtain a first water sample image, the first determining module 501 is specifically used for: The side image of the water sample to be tested is subjected to image segmentation processing to obtain a first set of images to be processed; Image super-resolution processing is performed on the first image to be processed in the first set of images to be processed to obtain the second set of images to be processed. The first light intensity value is obtained by determining the light intensity value of the environment in which the water sample to be detected is located based on the second image to be processed in the second image to be processed set. Based on the first illumination intensity value, construct the transmittance matrix corresponding to each second image in the second image set to be processed, and obtain the first transmittance matrix set; The first image to be processed is enhanced by using the first transmittance matrix in the first transmittance matrix set to obtain the third image to be processed. The third image in the third set of images to be processed is seamlessly stitched together to obtain the first water sample image.

[0085] In one possible implementation, in determining the stratification information corresponding to the object to be detected in the water sample based on the first type information to obtain the first stratification information, the second determining module 501 is specifically used for: The physicochemical properties of the object to be detected corresponding to the first type of information are determined to obtain the first characteristic information. The object to be detected can be any one of pollutants, suspended particles or target analytes in the water sample to be detected. Perform time-series feature analysis on the historical hierarchical information corresponding to the first characteristic information and the first category information to obtain the second characteristic information; The second feature information is corrected based on the historical environmental information corresponding to the water sample to be tested to obtain the third feature information; Based on the first characteristic information and the third feature information, a diffusion model corresponding to the object to be detected corresponding to the first type information is constructed to obtain the first diffusion model; The first diffusion model is used to predict the stratification information corresponding to the object to be detected in the water sample to be tested, and the first stratification information is obtained.

[0086] In one possible implementation, the second determining module 502 is specifically used for: The sampling area corresponding to the sampling device is determined based on the side image of the water sample to be tested, and the first sub-sampling strategy is obtained. Based on the first layer information, the sampling depth corresponding to the sampling device is determined, and a second sub-sampling strategy is obtained. Based on the first type of information, the sampling capacity corresponding to the sampling device is determined, and a third sub-sampling strategy is obtained; Based on the first type of information, the sample air isolation strategy corresponding to the sampling device is determined, and the fourth sub-sampling strategy is obtained. The first sub-sampling strategy, the second sub-sampling strategy, the third sub-sampling strategy, and the fourth sub-sampling strategy are combined to obtain the first sampling strategy.

[0087] This application also provides a computer storage medium storing a computer program for electronic data exchange, which causes a computer to perform some or all of the steps of any of the micro-water sample stratification and air isolation methods described in the above method embodiments.

[0088] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of any of the micro-water sample stratification and air isolation methods described in the above method embodiments.

[0089] 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 preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0090] 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.

[0091] 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.

[0092] 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.

[0093] Furthermore, the functional units in the various embodiments of the 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.

[0094] 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 described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0095] 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 device, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc.

[0096] 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 stratified aspiration and air isolation of trace water samples, characterized in that, The method includes: The layering information of the water sample to be tested is determined based on the side image of the water sample to be tested, and the first layering information is obtained. The water sample to be tested is a water sample that has undergone layering after being left to stand. Based on the first layering information and the side image of the water sample to be tested, the sampling strategy corresponding to the sampling device is determined, and a first sampling strategy is obtained. The first sampling strategy includes the sampling position, sampling volume, sampling depth and sample air isolation strategy of the sampling device. The sampling device includes a sampling arm and a sample container. The sampling arm is a mechanical arm for holding the sample container. An image acquisition device is provided near the sample container. The sampling device is used to sample the water sample to be tested according to the sampling location, sampling volume, sampling depth and sample air isolation strategy in the first sampling strategy to obtain the target water sample.

2. The method for stratified aspiration and air isolation of trace water samples according to claim 1, characterized in that, The step of determining the layering information of the water sample to be tested based on the side image of the water sample to be tested, and obtaining the first layering information, includes: The side image of the water sample to be tested is subjected to image enhancement processing to obtain the first water sample image; Based on the first water sample image, the type of the object to be detected in the water sample to be detected is predicted to obtain the first type information; Based on the first type of information, the layering information corresponding to the object to be detected in the water sample to be tested is determined, and the first layering information is obtained.

3. The method for stratified aspiration and air isolation of trace water samples according to claim 2, characterized in that, The step of performing image enhancement processing on the side image of the water sample to be tested to obtain a first water sample image includes: The side image of the water sample to be tested is subjected to image segmentation processing to obtain a first set of images to be processed; Image super-resolution processing is performed on the first image to be processed in the first set of images to be processed to obtain the second set of images to be processed. The first light intensity value is obtained by determining the light intensity value of the environment in which the water sample to be detected is located based on the second image to be processed in the second image to be processed set. Based on the first illumination intensity value, construct the transmittance matrix corresponding to each second image in the second image set to be processed, and obtain the first transmittance matrix set; The first image to be processed is enhanced by using the first transmittance matrix in the first transmittance matrix set to obtain the third image to be processed. The third image in the third set of images to be processed is seamlessly stitched together to obtain the first water sample image.

4. The method for stratified aspiration and air isolation of trace water samples according to claim 3, characterized in that, The step of determining the stratification information corresponding to the object to be detected in the water sample based on the first type of information, to obtain the first stratification information, includes: The physicochemical properties of the object to be detected corresponding to the first type of information are determined to obtain the first characteristic information. The object to be detected can be any one of pollutants, suspended particles or target analytes in the water sample to be detected. Perform time-series feature analysis on the historical hierarchical information corresponding to the first characteristic information and the first category information to obtain the second characteristic information; The second feature information is corrected based on the historical environmental information corresponding to the water sample to be tested to obtain the third feature information; Based on the first characteristic information and the third feature information, a diffusion model corresponding to the object to be detected corresponding to the first type information is constructed to obtain the first diffusion model; The first diffusion model is used to predict the stratification information corresponding to the object to be detected in the water sample to be tested, and the first stratification information is obtained.

5. The method for stratified aspiration and air isolation of trace water samples according to claim 4, characterized in that, The step of determining the sampling strategy corresponding to the sampling device based on the first layering information and the side image of the water sample to be tested, to obtain the first sampling strategy, includes: The sampling area corresponding to the sampling device is determined based on the side image of the water sample to be tested, and the first sub-sampling strategy is obtained. Based on the first layer information, the sampling depth corresponding to the sampling device is determined, and a second sub-sampling strategy is obtained. Based on the first type of information, the sampling capacity corresponding to the sampling device is determined, and a third sub-sampling strategy is obtained; Based on the first type of information, the sample air isolation strategy corresponding to the sampling device is determined, and the fourth sub-sampling strategy is obtained. The first sub-sampling strategy, the second sub-sampling strategy, the third sub-sampling strategy, and the fourth sub-sampling strategy are combined to obtain the first sampling strategy.

6. A device for stratified aspiration and air isolation of trace water samples, characterized in that, The device includes: The first determining module is used to determine the layering information of the water sample to be tested based on the side image of the water sample to be tested, and obtain the first layering information. The water sample to be tested is a water sample that has undergone layering after being left to stand. The second determining module is used to determine the sampling strategy corresponding to the sampling device based on the first layering information and the side image of the water sample to be tested, and obtain the first sampling strategy. The first sampling strategy includes the sampling position, sampling volume, sampling depth and sample air isolation strategy of the sampling device. The sampling device includes a sampling arm and a sample container. The sampling arm is a mechanical arm for holding the sample container. An image acquisition device is provided near the sample container. The sampling module is used to sample the water sample to be tested using the sampling device according to the sampling location, sampling volume, sampling depth and sample air isolation strategy in the first sampling strategy, so as to obtain the target water sample.

7. The micro-water sample stratification and air isolation device according to claim 6, characterized in that, In determining the layering information of the water sample to be tested based on the side image of the water sample to be tested, and obtaining the first layering information, the first determining module is specifically used for: The side image of the water sample to be tested is subjected to image enhancement processing to obtain the first water sample image; Based on the first water sample image, the type of the object to be detected in the water sample to be detected is predicted to obtain the first type information; Based on the first type of information, the layering information corresponding to the object to be detected in the water sample to be tested is determined, and the first layering information is obtained.

8. The micro-water sample stratification and air isolation device according to claim 7, characterized in that, In performing image enhancement processing on the side image of the water sample to be detected to obtain a first water sample image, the first determining module is specifically used for: The side image of the water sample to be tested is subjected to image segmentation processing to obtain a first set of images to be processed; Image super-resolution processing is performed on the first image to be processed in the first set of images to be processed to obtain the second set of images to be processed. The first light intensity value is obtained by determining the light intensity value of the environment in which the water sample to be detected is located based on the second image to be processed in the second image to be processed set. Based on the first illumination intensity value, construct the transmittance matrix corresponding to each second image in the second image set to be processed, and obtain the first transmittance matrix set; The first image to be processed is enhanced by using the first transmittance matrix in the first transmittance matrix set to obtain the third image to be processed. The third image in the third set of images to be processed is seamlessly stitched together to obtain the first water sample image.

9. A laser water quality analyzer, characterized in that, The laser water quality analyzer is used to perform the micro-water sample stratification and air isolation method as described in any one of claims 1-5. The laser water quality analyzer includes: a laser bombardment unit, a water sample preparation unit, and a detection unit. The laser output from the laser bombardment unit bombards spots on the water sample preparation area of ​​the water sample preparation unit through the end of the laser bombardment unit. The detection unit monitors the spectral information generated by the spots bombarded by the laser bombardment unit.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the micro-water sample stratification and air isolation method as described in any one of claims 1-5.

Images