Test tube sorting device, sample analysis system, and test tube sorting method

Abstract

The invention discloses a test tube classification device, a sample analysis system and a test tube classification method. A test tube disc of the test tube classification device is used for placing a plurality of test tubes to be classified; the acquisition mechanism is arranged above and / or on the side of the test tube disc and is used for performing image acquisition on the to-be-classified test tubes so as to obtain to-be-identified images of the to-be-classified test tubes; the loading mechanism is arranged on one side of the test tube disc; the processor is connected with the acquisition mechanism and the loading mechanism and is used for carrying out image feature extraction on the to-be-recognized image. Through the mode, the test tube classification device can obtain the test tube position and the first test tube type of the to-be-classified test tube through the to-be-recognized image of the to-be-classified test tube, and sorts the to-be-classified test tube to the corresponding test tube rack based on the test tube position and the first test tube type, so that automatic classification and sorting of the to-be-classified test tube are completed; the manual intervention and processing time is reduced, and the sample analysis efficiency is improved.

Description

Technical Field

[0001] This application relates to the technical field of medical devices, and particularly to a test tube sorting device, a sample analysis system, and a test tube sorting method. Background Art

[0002] In a clinical testing scenario, existing sample analysis systems are usually connected to multiple testing instruments with different detection principles. After receiving test tubes of multiple different sample types or testing types, staff need to manually sort the test tubes and place the sorted test tubes into a test tube rack, so as to place the test tube rack in the sampling area of the sample analysis system for fully automatic analysis and testing.

[0003] Existing sample analysis systems require manual sorting of test tubes, resulting in high labor costs; moreover, for different test items and sample types, there are many types of test tubes, and staff also need to sort different types of test tubes into different types of test tube racks, with high sorting difficulty, low efficiency, and high sample analysis costs. Summary of the Invention

[0004] To solve the above technical problems, this application provides a test tube sorting device, a sample analysis system, and a test tube sorting method.

[0005] To solve the above problems, this application provides a first technical solution: providing a test tube sorting device, including a test tube tray, a collection mechanism, a loading mechanism, and a processor. The test tube tray is used to place a number of test tubes to be sorted; the collection mechanism is arranged above and / or on the side of the test tube tray, and is used to perform image collection on the test tubes to be sorted, so as to obtain the to-be-identified images of the test tubes to be sorted; the loading mechanism is arranged on one side of the test tube tray; the processor is respectively connected to the collection mechanism and the loading mechanism, and is used to extract image features from the to-be-identified images, so as to identify the test tube positions and the first test tube types of the test tubes to be sorted from the to-be-identified images; the processor is further used to control the loading mechanism to sort the test tubes to be sorted onto the corresponding test tube racks based on the test tube positions and the first test tube types.

[0006] Optionally, the collection mechanism includes at least one first collector arranged above the test tube tray. The first collector is used to perform image collection on the test tubes to be sorted and obtain first image data. The processor is used to extract color features from the first image data to obtain the color information of the first image data. The processor is further used to obtain the corresponding first test tube type based on the color information.

[0007] Optionally, the above-mentioned processor is further configured to extract edge features from the above-mentioned first image data to extract the graphic information of the above-mentioned first image data, and the above-mentioned processor is further configured to obtain the above-mentioned first test tube type based on the above-mentioned color information and the above-mentioned graphic information.

[0008] Optionally, the above-mentioned test tube tray is provided with a plurality of visual positioning marks, and the above-mentioned processor is configured to obtain the coordinate data of the above-mentioned visual positioning marks in the first image data, so as to correct the first image data according to the above-mentioned coordinate data.

[0009] Optionally, the above-mentioned acquisition mechanism further includes at least one second collector disposed on the side of the above-mentioned test tube tray. The above-mentioned second collector is configured to collect images of the above-mentioned test tubes to be classified and obtain second image data. The above-mentioned processor is further configured to obtain the height of the above-mentioned test tubes to be classified based on the above-mentioned second image data, and control the above-mentioned loading mechanism to lower by a preset number of steps based on the above-mentioned height, so that the above-mentioned loading mechanism grabs the above-mentioned test tubes to be classified and sorts them.

[0010] Optionally, the above-mentioned acquisition mechanism further includes a first second collector and a second second collector. The acquisition range of the above-mentioned first second collector is a first area, and the acquisition range of the above-mentioned second second collector is a second area. The above-mentioned first area and the above-mentioned second area intersect; wherein, the above-mentioned processor is configured to control the above-mentioned first second collector and the above-mentioned second second collector to respectively collect images of the above-mentioned test tubes to be classified in response to the above-mentioned test tubes to be classified being located in the intersection area of the above-mentioned first area and the above-mentioned second area; the above-mentioned processor is further configured to control the above-mentioned loading mechanism to lower by a preset number of steps based on the second image data collected by the above-mentioned first second collector and the above-mentioned second second collector.

[0011] Optionally, the above-mentioned first second collector collects images of the above-mentioned test tubes to be classified to obtain third image data, and the above-mentioned second second collector collects images of the above-mentioned test tubes to be classified to obtain fourth image data. The above-mentioned processor is further configured to control the above-mentioned loading mechanism to lower by a first preset number of steps in response to identifying that the height of the above-mentioned test tubes to be classified is a preset height from the above-mentioned third image data and / or the above-mentioned fourth image data.

[0012] Optionally, the above test tube sorting device further includes a barcode scanning mechanism, which is arranged on one side of the test tube tray and connected to the processor. The barcode scanning mechanism is used to scan the barcode information of the test tube to be sorted to obtain the second test tube type of the test tube to be sorted. Wherein, the processor is configured to control the loading mechanism to move the test tube to be sorted to the abnormal handling area in response to the difference between the first test tube type and the second test tube type of the test tube to be sorted, and / or, the processor is configured to control the loading mechanism to sort the test tube to be sorted based on the second test tube type in response to the failure to recognize the first test tube type from the to-be-recognized image.

[0013] To solve the above problems, the present application provides a second technical solution: providing a sample analysis system, including the above test tube sorting device, a scheduling module, and a detection module. The test tube sorting device is used to obtain a plurality of test tubes to be sorted and sort the test tubes to be sorted onto corresponding test tube racks; the scheduling module is used to schedule the sorted test tube racks to the detection module, and the detection module is used to detect the test tubes on the test tube racks.

[0014] To solve the above problems, the present application provides a third technical solution: providing a test tube sorting method, including: receiving a plurality of test tubes to be sorted, and performing image acquisition on the plurality of test tubes to be sorted to obtain a to-be-recognized image of the test tubes to be sorted; performing image feature extraction on the to-be-recognized image to identify the test tube position and the first test tube type of the test tubes to be sorted from the to-be-recognized image; sorting the test tubes to be sorted onto corresponding test tube racks based on the test tube position and the first test tube type.

[0015] The present application provides a test tube sorting device, a sample analysis system, and a test tube sorting method. The test tube sorting device includes a test tube tray, an acquisition mechanism, a loading mechanism, and a processor. The test tube tray is used to place a plurality of test tubes to be sorted; the acquisition mechanism is arranged above and / or on the side of the test tube tray and is used to perform image acquisition on the test tubes to be sorted to obtain a to-be-recognized image of the test tubes to be sorted; the loading mechanism is arranged on one side of the test tube tray; the processor is respectively connected to the acquisition mechanism and the loading mechanism and is used to perform image feature extraction on the to-be-recognized image to identify the test tube position and the first test tube type of the test tubes to be sorted from the to-be-recognized image; the processor is further used to control the loading mechanism to sort the test tubes to be sorted onto corresponding test tube racks based on the test tube position and the first test tube type. In this way, the test tube sorting device can obtain the test tube position and the first test tube type of the test tubes to be sorted through the to-be-recognized image of the test tubes to be sorted, and sort the test tubes to be sorted onto corresponding test tube racks based on the test tube position and the first test tube type, so as to complete the automatic classification and sorting of the test tubes to be sorted, reduce the time of manual intervention and processing, and improve the sample analysis efficiency. Description of the Drawings

[0016] To more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings. Among them:

[0017] Figure 1 is a schematic structural diagram of an embodiment of the test tube sorting device provided by the present application;

[0018] Figure 2 is a schematic flowchart of an embodiment of the test tube sorting method provided by the present application;

[0019] Figure 3 is a schematic flowchart of another embodiment of the test tube sorting method provided by the present application;

[0020] Figure 4 is a schematic structural diagram of an embodiment of the computer-readable storage medium provided by the present application. Detailed implementation manners

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0022] It should be noted that if there are directional indications (such as up, down, left, right, front, back...) involved in the embodiments of the present application, the directional indications are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the drawings). If the specific posture changes, the directional indications will also change accordingly.

[0023] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by the present application.

[0024] Please refer to Figure 1 ,Figure 1 This is a schematic structural diagram of an embodiment of the test tube sorting device provided by this application. As Figure 1 shown, the test tube sorting device of the embodiment of this application includes a test tube tray 11, a collection mechanism (not shown in the figure), a loading mechanism 12, and a processor (not shown in the figure).

[0025] Specifically, the test tube tray 11 is used to place a plurality of test tubes 13 to be sorted; the collection mechanism is arranged above and / or on the side of the test tube tray 11 and is used to perform image collection on the test tubes 13 to be sorted, so as to obtain the to-be-identified images of the test tubes 13 to be sorted; the loading mechanism 12 is arranged on one side of the test tube tray 11; the processor is respectively connected to the collection mechanism and the loading mechanism 12, and the processor is used to extract image features from the to-be-identified images, so as to identify the test tube positions and the first test tube types of the test tubes 13 to be sorted from the to-be-identified images; the processor is further used to control the loading mechanism 12 to sort the test tubes 13 to be sorted onto the corresponding test tube racks 14 based on the test tube positions and the first test tube types.

[0026] Specifically, the test tube tray 11 can be provided with a plurality of placement holes for inserting a plurality of test tubes 13 to be sorted into the placement holes, so that the test tubes 13 to be sorted are placed upright on the test tube tray 11. The collection mechanism is arranged above and / or on the side of the test tube tray 11 and aligns the collection angle with the test tube tray 11 to perform image collection on the test tubes 13 to be sorted on the test tube tray 11 from at least one collection angle and obtain at least one to-be-identified image. Among them, the number of collectors of the collection mechanism is related to the size of the test tube tray 11. When the size of the test tube tray 11 is larger and the number of test tubes 13 to be sorted is more, and a single collector of the collection mechanism cannot perform image collection on all the test tubes 13 to be sorted on the test tube tray 11, the collection mechanism can divide a plurality of collection areas and set corresponding collectors in each collection area to perform image collection on all the test tubes 13 to be sorted on the test tube tray 11.

[0027] The processor is connected to the collection mechanism, and the collection mechanism is used to transmit the to-be-identified images of the test tubes 13 to be sorted obtained to the processor. The processor is used to extract image features from the test tubes 13 to be sorted. The image feature extraction is to extract local features or global features of the image. For example, the image feature extraction can be to extract at least one of color features, texture features, shape features, spatial position relationship features, etc. of the to-be-identified images, so as to obtain the test tube positions and the first test tube types of the test tubes 13 to be sorted according to the extracted feature information. The loading mechanism 12 is arranged on one side of the test tube tray 11, and the loading mechanism 12 is used to obtain the test tubes 13 to be sorted from the test tube tray 11 and place the test tubes 13 to be sorted on the corresponding test tube racks 14 based on the test tube positions and the first test tube types of the test tubes 13 to be sorted.

[0028] Among them, on one side of the test tube tray 11 of the test tube sorting device, a plurality of test tube racks 14 of different types can also be placed. Each test tube rack 14 is used to place test tubes of the same type, so that the sample analysis system can directly detect the test tubes according to the type of the test tube rack 14 and the type of the test tube. The loading mechanism 12 can pick up the corresponding test tube 13 to be sorted from the test tube tray 11 by setting a loading gripper.

[0029] In an alternative embodiment, the processor may be referred to as a CPU (Central Processing Unit); the processor may also be an electronic chip with signal processing capabilities; the processor may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. General-purpose processors include but are not limited to microprocessors or conventional processors, etc.

[0030] In the embodiment of the present application, the processor of the test tube sorting device can obtain the test tube position and the first test tube type of the test tube 13 to be sorted through the image to be recognized of the test tube 13 to be sorted, and control the loading mechanism 12 to sort the test tube 13 to be sorted onto the corresponding test tube rack 14 based on the test tube position and the first test tube type, so as to complete the automatic classification and sorting of the test tube 13 to be sorted, reduce the time of manual intervention and processing, and improve the sample analysis efficiency.

[0031] In one embodiment, the acquisition mechanism includes at least one first collector disposed above the test tube tray 11. The first collector is used to collect images of the test tube 13 to be sorted and obtain first image data. The processor is used to extract color features from the first image data to obtain the color information of the first image data, and the processor is also used to obtain the corresponding first test tube type based on the color information.

[0032] Specifically, at least one first collector can be disposed above the test tube tray 11. The first collector is used to collect images of all the test tubes 13 to be sorted on the test tube tray 11 and obtain at least one first image data. The processor is used to receive the first image data transmitted by the first collector, extract color features from the first image data to obtain the color information of several test tubes 13 to be sorted in the first image data, and the processor is also used to obtain the first test tube type corresponding to the color information based on the color information of each test tube 13 to be sorted.

[0033] Among them, test tubes of existing different sample types and detection types are usually distinguished by the color of the test tube caps, the size of the test tubes, etc. For example, ordinary serum tubes usually use red test tube caps, rapid serum tubes usually use orange-red test tube caps, clot activator tubes usually use golden yellow test tube caps, anticoagulant tubes usually use green test tube caps, plasma separator tubes usually use light green test tube caps, routine blood test venous blood tubes usually use purple test tube caps, routine blood test peripheral blood tubes usually use pink test tube caps, coagulation test tubes usually use light blue test tube caps, erythrocyte sedimentation rate test tubes usually use black test tube caps, blood glucose test tubes usually use gray test tube caps, etc.

[0034] The test tube classification device of this embodiment extracts the color features of the test tube 13 to be classified from the first image data through the processor, so as to obtain the first test tube type corresponding to the color information according to the color information of the test tube 13 to be classified, so that the loading mechanism 12 sorts the test tube 13 to be classified to the corresponding test tube rack 14 based on the test tube position and the first test tube type, so as to complete the automatic classification and sorting of the test tube 13 to be classified, reduce the time of manual intervention and processing, and improve the sample analysis efficiency.

[0035] Optionally, the test tube classification device further includes a memory, the memory is connected to the processor, the memory stores predefined sample tube types, and the processor is used to identify the first test tube type of the test tube 13 to be classified from the first image data based on the correspondence between the color information and the sample tube types.

[0036] Specifically, the test tube classification device of this embodiment is also provided with a memory, the memory stores predefined sample tube types, the sample tube types are related to the sample types loaded in several test tubes 13 to be classified or the detection types of several test tubes 13 to be classified, and each sample tube type may include the corresponding test tube color tone and / or test tube pattern. For example, the sample tube types corresponding to the above-mentioned test tube caps of different colors are stored in the memory. After the processor extracts the features of the first image data and obtains the color information, it retrieves the stored sample tube types from the memory and determines the first test tube type of the test tube 13 to be classified according to the correspondence between the color information and the sample tube types.

[0037] Among them, the memory can be a memory module, a TF card, etc., and can be used to store all information in the test tube sorting device. All the input original data, computer programs, intermediate operation results, and final operation results are stored in the memory. The memory stores and retrieves information according to the positions specified by the processor. The memory can be divided into a main memory (internal memory) and an auxiliary memory (external memory) according to its use. The external memory is usually a magnetic medium or an optical disc, etc., which can store information for a long time; the internal memory refers to the storage component on the motherboard, which is used to store the data and programs being currently executed, but only temporarily stores the programs and data. When the power is turned off or cut off, the data will be lost. The storage method of the memory is not specifically limited here.

[0038] In the embodiment of the present application, the test tube sorting device extracts the color features of the test tube 13 to be sorted in the first image data through the processor to obtain color information. The processor calls the types of sample tubes stored in the memory, and based on the correspondence between the color information and the types of sample tubes, identifies the first test tube type of the test tube 13 to be sorted from the first image data, so as to automatically sort the test tubes, reduce the time of manual intervention and processing, and improve the sample analysis efficiency.

[0039] Further, in a possible implementation manner, the test tube sorting device is also connected to an external display device, so that the user can preset the types of sample tubes to be identified through the display device, which is convenient for the processor to identify the first test tube type of the test tube 13 to be sorted from the first image data.

[0040] Optionally, the processor is further configured to extract the edge features of the first image data to extract the graphic information of the first image data, and the processor is further configured to obtain the first test tube type based on the color information and the graphic information.

[0041] Specifically, the processor is configured to extract the edge features of the first image data to extract the graphic information of the first image data. When the difference value between the color information identified in the first image data and the tube color tone of the types of sample tubes stored in the memory is greater than a preset threshold, the processor is further configured to call the tube graphics of the types of sample tubes in the memory, and make an auxiliary judgment based on the correspondence between the graphic information of the test tube 13 to be sorted and the tube graphics of the types of sample tubes, so as to obtain the first test tube type.

[0042] When the processor determines the test tube type based on the color information and the graphic information, different weights can be set to determine the proportion of the color information and the graphic information. For example, when the accuracy of the color information is higher, the weight of the color information can be set to 0.6 and the weight of the graphic information can be set to 0.4. Or, when the accuracy of the graphic information is higher, the weight of the color information can be set to 0.4 and the weight of the graphic information can be set to 0.6. In other embodiments, different weights can also be selected to determine the type of the first test tube according to the difference value between the color information and the test tube hue in different intervals, which is not specifically limited herein.

[0043] In the embodiment of the present application, the test tube classification device extracts the edge features of the first image data through the processor to extract the graphic information of the first image data. The processor compares the color information and the graphic information of the test tube 13 to be classified with the sample tube type, and identifies the type of the first test tube of the test tube 13 to be classified from the first image data, so as to automatically classify the test tubes, reduce the time of manual intervention and processing, and improve the sample analysis efficiency.

[0044] Optionally, the test tube tray 11 is provided with a plurality of visual positioning marks, and the processor is configured to obtain the coordinate data of the visual positioning marks in the first image data, so as to perform image correction on the first image data according to the coordinate data.

[0045] Specifically, a plurality of visual positioning marks are arranged on the test tube tray 11, and the visual positioning marks can be standard parts for visual positioning that are exposed on the test tube tray 11 and located between different placement holes. Among them, the positions of the visual positioning marks are fixed. For example, the visual positioning marks can be arranged at the four corner points and the center point of the test tube tray 11. When obtaining the first image data, the processor is further configured to perform image recognition on the visual positioning marks in the first image data to obtain the coordinate data of the visual positioning marks, and perform image correction on the first image data according to the coordinate data relationship between different visual positioning marks. Exemplarily, the processor can calculate the distances between different corner points and the visual positioning marks at the center point according to the coordinate data of the visual positioning marks at different corner points and the center point, so as to perform image correction on the first image data according to the distances.

[0046] In the embodiment of the present application, the processor performs image correction on the first image data according to the coordinate data of the visual positioning marks, so that the processor can perform image feature extraction on the corrected first image data, reduce the recognition error caused by graphic distortion of the first image data, and improve the recognition accuracy of the test tube type.

[0047] Optionally, the collection mechanism further includes at least one second collector disposed on the side of the test tube tray 11. The second collector is used to collect images of the test tubes 13 to be classified and obtain second image data. The processor is further configured to obtain the height of the test tubes 13 to be classified based on the second image data, and control the loading mechanism 12 to lower by a preset number of steps based on the height, so that the loading mechanism 12 grabs the test tubes 13 to be classified and sorts them.

[0048] Specifically, the collection mechanism further includes at least one second collector disposed on the side of the test tube tray 11. The second collector is used to collect images of the test tubes 13 to be classified and obtain second image data. Among them, the first image data is collected by the first collector disposed above the test tube tray 11, and the second image data is collected by the second collector disposed on the side of the test tube tray 11. Without considering the image distortion caused by the collection angle of the collector, the first image data can be approximately understood as the top view of the test tubes 13 to be classified placed on the test tube tray 11, and the second image data can be approximately understood as the side view of the test tubes 13 to be classified placed on the test tube tray 11. The processor of this embodiment is configured to extract image features from the second image data to obtain the height of the test tubes 13 to be classified; the processor is further configured to control the loading mechanism 12 to lower by a preset number of steps based on the height of the test tubes 13 to be classified, so that the loading mechanism 12 can stably grab the test tubes 13 to be classified and sort the test tubes 13 to be classified.

[0049] It can be understood that test tubes of different types have differences in shape, height, etc. For example, when the collected blood sample is a venous blood sample, the height of the test tube used is relatively high; when the collected blood sample is a peripheral blood sample, the height of the test tube used is relatively low, so that when the loading mechanism 12 grabs test tubes of different heights, different numbers of lowering steps need to be executed for test tube grabbing. The test tube classification device of this embodiment can collect images of the test tubes 13 to be classified through the second collector, so that the processor can identify the height of the test tubes 13 to be classified based on the second image data, and the loading mechanism 12 can lower to the corresponding height for test tube grabbing according to the height of the test tubes 13 to be classified, reducing the possibility of accidents such as test tube dropping and breaking caused by position errors and unstable grabbing when the loading mechanism 12 grabs test tubes, and improving the stability of the test tube classification device.

[0050] Further, the collection mechanism further includes a first second collector and a second second collector. The collection range of the first second collector is the first area, and the collection range of the second second collector is the second area, and the first area and the second area intersect.

[0051] Specifically, when multiple second collectors are provided in the collection mechanism, the collection ranges of the multiple second collectors for image collection of the test tube tray 11 are divided into multiple regions, and there will be partial intersections between different regions. For example, the collection range of the first second collector is the first region, and the collection range of the second second collector is the second region, and the first region and the second region intersect. The processor is configured to control the first second collector and the second second collector to respectively perform image collection on the test tube 13 to be classified in response to the test tube 13 to be classified being located in the intersection region of the first region and the second region; the processor is further configured to control the loading mechanism 12 to lower by a preset number of steps based on the second image data collected by the first second collector and the second second collector.

[0052] Wherein, after obtaining the second image data collected by the first second collector and the second second collector, the processor respectively extracts image features from the second image data of different second collectors to respectively obtain a first height and a second height, and the processor controls the loading mechanism 12 to lower by a preset number of steps based on the first height and the second height. For example, when the first height indicates that the test tube 13 to be classified is a tall test tube and the second height indicates that the test tube 13 to be classified is a short test tube, the loading mechanism 12 is controlled to lower by a first preset number of steps; alternatively, the processor controls the loading mechanism 12 to lower by a corresponding preset number of steps based on the weights of the first height and the second height, which is not specifically limited herein.

[0053] It can be understood that the test tube 13 to be classified located in the intersection region of different collectors is usually located at the edge of the image. Due to adverse factors such as image distortion and collection angle, the recognition accuracy of the processor for the test tube at the image edge will decrease. In the embodiment of the present application, the processor synchronously recognizes the second image data of multiple collectors located in the intersection region to control the loading mechanism 12 to lower by a preset number of steps according to the recognized height, so as to recognize the height of the test tube 13 to be classified from different collection angles and improve the recognition accuracy of the test tube height.

[0054] Further, the first second collector performs image collection on the test tube 13 to be classified to obtain third image data, and the second second collector performs image collection on the test tube 13 to be classified to obtain fourth image data. The processor is further configured to control the loading mechanism 12 to lower by a first preset number of steps in response to recognizing that the height of the test tube 13 to be classified is a preset height from the third image data and / or the fourth image data.

[0055] Specifically, the first second collector performs image acquisition on the test tube 13 to be classified to obtain third image data, and the second second collector performs image acquisition on the test tube 13 to be classified to obtain fourth image data. The processor extracts image features from the third image data and the fourth image data respectively to obtain the first height of the test tube 13 to be classified in the third image data and the second height of the test tube 13 to be classified in the fourth image data. In response to the first height and / or the second height being a preset height, at this time, the image data collected by at least one of the first second collector and the second second collector indicates that the test tube 13 to be classified is a tall test tube, and the processor is used to control the loading mechanism 12 to lower by a first preset number of steps; in response to the first height and the second height being other heights than the preset height, at this time, the image data collected by the first second collector and the second second collector both indicate that the test tube 13 to be classified is a short test tube, and the processor is used to control the loading mechanism 12 to lower by a second preset number of steps, and the second preset number of steps is greater than the first preset number of steps.

[0056] In the embodiment of the present application, the processor determines that the test tube 13 to be classified is a tall test tube by recognizing that the height of the test tube 13 to be classified is a preset height through the third image data and / or the fourth image data, so as to control the loading mechanism 12 to lower by a first preset number of steps, improving the accuracy of test tube height recognition.

[0057] Optionally, the test tube classification device further includes a barcode scanning mechanism. The barcode scanning mechanism is arranged on one side of the test tube tray 11 and is connected to the processor. Specifically, the barcode scanning mechanism can be separately arranged on one side of the test tube tray 11, or can be integrally arranged on the loading mechanism, and no limitation is made here. The barcode scanning mechanism is used to scan the barcode information of the test tube 13 to be classified to obtain the second test tube type of the test tube 13 to be classified. Specifically, a corresponding barcode information can be pasted on the test tube 13 to be classified, and the barcode information can be at least used to indicate the second test tube type of the test tube 13 to be classified, so that the barcode scanning mechanism transmits the obtained second test tube type to the processor.

[0058] Wherein, the processor is used to control the loading mechanism 12 to move the test tube 13 to be classified to the abnormal handling area in response to the first test tube type and the second test tube type of the test tube 13 to be classified being different, and / or, the processor is used to sort the test tube 13 to be classified by controlling the loading mechanism 12 based on the second test tube type in response to the first test tube type not being recognized from the image to be recognized.

[0059] Specifically, in one embodiment, the abnormal handling area can be set on one side of the test tube tray 11. When the first test tube type and the second test tube type of the test tubes to be classified 13 are different, or when the first test tube type and the second test tube type cannot be obtained, the processor controls the loading mechanism 12 to move the test tubes to be classified 13 to the abnormal handling area, so that the user can perform manual processing on the test tubes to be classified 13 in the abnormal handling area. In another embodiment, the processor is further configured to, in response to the first test tube type not being recognized from the image to be recognized, control the loading mechanism 12 to sort the test tubes to be classified 13 based on the second test tube type, so as to complete the automatic classification and sorting of the test tubes to be classified 13, improve the error tolerance rate of image recognition, reduce the time of manual intervention and processing, and improve the sample analysis efficiency.

[0060] The embodiment of the present application further provides a sample analysis system, which includes the test tube classification device, the scheduling module, and the detection module according to any one of the above embodiments.

[0061] The test tube classification device is configured to obtain a plurality of test tubes to be classified 13 and sort the test tubes to be classified 13 onto the corresponding test tube racks 14; the scheduling module is configured to schedule the classified test tube racks 14 to the detection module, and the detection module is configured to detect the test tubes on the test tube racks 14.

[0062] Among them, the scheduling module may include a circulation component and a conveying component. The circulation component is configured to continuously provide blank test tube racks 14 to the sample analysis system, so that the test tube classification device sorts the test tubes to be classified 13 onto the corresponding test tube racks 14; the circulation component is further configured to receive the test tube racks 14 loaded with the tested test tubes, so as to unload the tested test tubes from the test tube racks 14 to the recycling area through the conveying component. The conveying component is configured to convey the blank test tube racks 14 to move the blank test tube racks 14 to the circulation component, and the conveying component is further configured to transport the classified test tube racks 14 to the detection module, so that the detection module detects the test tubes on the test tube racks 14.

[0063] It can be understood that in this embodiment, through the connection of the test tube classification device and the scheduling module, the pipeline transportation of test tubes, the automatic classification and sorting of test tubes, etc. are realized, the recycling of the test tube racks 14 is realized, and the automatic loading and unloading of test tubes are realized, saving a large amount of labor costs, reducing the time of manual intervention and processing, and further improving the sample analysis efficiency.

[0064] The embodiment of the present application further provides a test tube classification method. Please refer to Figure 2 , Figure 2 is a schematic flowchart of an embodiment of the test tube classification method provided by the present application. As Figure 2 shown, the test tube classification method includes the following steps:

[0065] Step S11: Receive a number of test tubes 13 to be classified, and perform image acquisition on the number of test tubes 13 to be classified to obtain the to-be-recognized images of the test tubes 13 to be classified.

[0066] Specifically, the test tube classification method in this embodiment performs image acquisition on a number of test tubes 13 to be classified to obtain the to-be-recognized images of the test tubes 13 to be classified. Among them, the to-be-recognized images can be images of the test tubes 13 to be classified on the test tube tray 11 acquired at multiple acquisition angles to improve the accuracy of image recognition.

[0067] Step S12: Extract image features from the to-be-recognized images to identify the test tube positions and the first test tube types of the test tubes 13 to be classified from the to-be-recognized images.

[0068] Extract image features from the to-be-recognized images, for example, perform feature recognition and extraction on the color features, graphic features, etc. of the to-be-recognized images to identify the test tube positions and the first test tube types of the test tubes 13 to be classified from the to-be-recognized images.

[0069] Step S13: Based on the test tube positions and the first test tube types, sort the test tubes 13 to be classified onto the corresponding test tube racks 14.

[0070] Based on the test tube positions and the first test tube types of the test tubes 13 to be classified, obtain the test tubes 13 to be classified from the test tube tray 11 and sort them onto the corresponding test tube racks 14 to achieve automatic classification and sorting of the test tubes 13 to be classified.

[0071] In the embodiment of the present application, the test tube classification method extracts image features from the to-be-recognized images of the test tubes 13 to be classified to obtain the test tube positions and the first test tube types of the test tubes 13 to be classified, and sorts the test tubes 13 to be classified onto the corresponding test tube racks 14 based on the test tube positions and the first test tube types to complete the automatic classification and sorting of the test tubes 13 to be classified, reduce the time of manual intervention and processing, and improve the sample analysis efficiency.

[0072] Please refer to Figure 3 , Figure 3 which is a schematic flowchart of another embodiment of the test tube classification method provided by the present application. As Figure 3 shown, the test tube classification method in this embodiment acquires the first image data of the test tube tray 11 through the first collector, extracts the color features of the first image data and obtains the color information, and extracts the edge features of the first image data and obtains the graphic information. By comparing the color information with the test tube hues of the stored sample tube types and comparing the graphic information with the test tube graphics of the stored sample tube types, the test tube types are determined.

[0073] In an alternative embodiment, the second image data of the test tube tray 11 can also be collected by the second collector, so as to perform visual recognition on the second image data and obtain the height of the test tube 13 to be classified. The loading mechanism 12 probes down a preset number of steps according to the height of the test tube 13 to be classified to grab the test tube, so as to sort the test tube 13 to be classified onto the corresponding test tube rack 14. The test tube classification method of this embodiment also obtains the test items of the test tube by scanning the barcode information of the test tube, so as to schedule the classified test tube rack 14 to the detection module for detection.

[0074] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of an embodiment of the computer-readable storage medium provided by the present application. As Figure 4 shown, the program instructions 111 capable of implementing all the above methods are stored in the computer-readable storage medium 110.

[0075] If the units integrated in the various functional units in the embodiments of the present application are implemented in the form of software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium 110. Based on such an understanding, the technical solution of the present 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. The computer-readable storage medium 110 includes several instructions in a program instruction 111 to enable a computer device (which can be a personal computer, a system server, or a network device, etc.), an electronic device (such as an MP3, an MP4, etc., can also be a mobile terminal such as a mobile phone, a tablet computer, a wearable device, etc., or a desktop computer, etc.) or a processor to execute all or part of the steps of the methods in the various embodiments of the present application.

[0076] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-readable storage media 110 (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0077] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and combinations of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer-readable storage medium 110. These computer-readable storage media 110 can be provided to the processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing device to generate a machine, such that the program instructions 111 executed by the processor of the computer or other programmable data processing device generate means for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0078] These computer-readable storage media 110 can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the program instructions 111 stored in the computer-readable storage media 110 generate a manufactured article including instruction means that implement the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0079] These computer-readable storage media 110 can also be loaded onto a computer or other programmable data processing device, such that a series of operational steps are performed on the computer or other programmable device to generate a computer-implemented process, and thus the program instructions 111 executed on the computer or other programmable device provide steps for implementing the functions specified in one Figure 1 flow or multiple flows and / or blocks Figure 1 or multiple blocks.

[0080] Any process or method description in the flowchart or described otherwise herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a specific logical function or process, and the scope of the preferred embodiments of the present application includes additional implementations, where the functions can be performed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed, which should be understood by those skilled in the technical field to which the embodiments of the present application pertain.

[0081] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus or device (which can be a personal computer, server, network device or other system that can fetch instructions from the instruction execution system, apparatus or device and execute the instructions), or used in combination with these instruction execution systems, apparatuses or devices. The above are only the embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

[0082] The above are only the embodiments of the present application, and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present application, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present application.

Claims

1. A test tube sorting device, characterized in that, Comprising: A test tube tray for placing a plurality of test tubes to be classified; An acquisition mechanism arranged above and / or on the side of the test tube tray for acquiring images of the test tubes to be classified to obtain the images to be recognized of the test tubes to be classified; A loading mechanism arranged on one side of the test tube tray; A processor respectively connected to the acquisition mechanism and the loading mechanism for extracting image features from the images to be recognized to identify the test tube positions and the first test tube types of the test tubes to be classified from the images to be recognized; The processor is further configured to control the loading mechanism to sort the test tubes to be classified onto corresponding test tube racks based on the test tube positions and the first test tube types.

2. The test tube sorting device according to claim 1, characterized in that, The acquisition mechanism includes at least one first collector arranged above the test tube tray. The first collector is configured to acquire images of the test tubes to be classified and obtain first image data. The processor is configured to extract color features from the first image data to obtain the color information of the first image data. The processor is further configured to obtain the corresponding first test tube type based on the color information.

3. The test tube sorting device according to claim 2, characterized in that, The processor is further configured to extract edge features from the first image data to extract the graphic information of the first image data. The processor is further configured to obtain the first test tube type based on the color information and the graphic information.

4. The test tube sorting device according to claim 2, characterized in that, The test tube tray is provided with a plurality of visual positioning marks. The processor is configured to obtain the coordinate data of the visual positioning marks in the first image data to correct the first image data according to the coordinate data.

5. The test tube sorting device according to claim 2, characterized in that, The acquisition mechanism further includes at least one second collector arranged on the side of the test tube tray. The second collector is configured to acquire images of the test tubes to be classified and obtain second image data. The processor is further configured to obtain the height of the test tubes to be classified based on the second image data and control the loading mechanism to lower by a preset number of steps based on the height, so that the loading mechanism grabs the test tubes to be classified and sorts them.

6. The test tube sorting device according to claim 5, characterized in that, The acquisition mechanism further includes a first second collector and a second second collector. The acquisition range of the first second collector is a first area, and the acquisition range of the second second collector is a second area. The first area and the second area intersect; Wherein, the processor is configured to control the first second collector and the second second collector to respectively acquire images of the test tube to be classified in response to the test tube to be classified being located in the intersection area of the first area and the second area; the processor is further configured to control the loading mechanism to lower by a preset number of steps based on the second image data acquired by the first second collector and the second second collector.

7. The test tube sorting device according to claim 6, characterized in that, The first second collector collects an image of the test tube to be classified to obtain third image data, and the second second collector collects an image of the test tube to be classified to obtain fourth image data. The processor is further configured to control the loading mechanism to lower by a first preset number of steps in response to identifying that the height of the test tube to be classified is a preset height from the third image data and / or the fourth image data.

8. The test tube sorting device according to claim 1, characterized in that, The test tube sorting device further includes a barcode scanning mechanism, which is disposed on one side of the test tube tray and connected to the processor. The barcode scanning mechanism is configured to scan the barcode information of the test tube to be classified to obtain the second test tube type of the test tube to be classified. Wherein, the processor is configured to control the loading mechanism to move the test tube to be classified to the abnormal handling area in response to the first test tube type and the second test tube type of the test tube to be classified being different, and / or, the processor is configured to sort the test tube to be classified by the loading mechanism based on the second test tube type in response to the first test tube type not being recognized from the to-be-recognized image.

9. A sample analysis system, characterized in that, Comprising: The test tube sorting device according to any one of claims 1-8, configured to obtain a plurality of test tubes to be classified and sort the test tubes to be classified onto corresponding test tube racks. A scheduling module and a detection module, the scheduling module is configured to schedule the classified test tube racks to the detection module, and the detection module is configured to detect the test tubes on the test tube racks.

10. A test tube sorting method, characterized in that, Comprising: Receiving a plurality of test tubes to be classified and collecting images of the plurality of test tubes to be classified to obtain a to-be-recognized image of the test tubes to be classified. Performing image feature extraction on the to-be-recognized image to identify the test tube position and the first test tube type of the test tube to be classified from the to-be-recognized image. Sorting the test tubes to be classified onto corresponding test tube racks based on the test tube position and the first test tube type.

Images