CN117744002B - Laboratory data analysis method and laboratory information management platform - Google Patents
Laboratory data analysis method and laboratory information management platform Download PDFInfo
- Publication number
- CN117744002B CN117744002B CN202311795432.1A CN202311795432A CN117744002B CN 117744002 B CN117744002 B CN 117744002B CN 202311795432 A CN202311795432 A CN 202311795432A CN 117744002 B CN117744002 B CN 117744002B
- Authority
- CN
- China
- Prior art keywords
- data
- abnormal
- type
- target
- laboratory
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 58
- 238000007405 data analysis Methods 0.000 title claims abstract description 52
- 230000002159 abnormal effect Effects 0.000 claims abstract description 165
- 230000004044 response Effects 0.000 claims abstract description 38
- 238000013136 deep learning model Methods 0.000 claims abstract description 12
- 230000005856 abnormality Effects 0.000 claims description 33
- 238000004590 computer program Methods 0.000 claims description 17
- 230000015654 memory Effects 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 8
- 230000002093 peripheral effect Effects 0.000 claims description 8
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 3
- 229910052760 oxygen Inorganic materials 0.000 claims description 3
- 239000001301 oxygen Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 6
- 238000003672 processing method Methods 0.000 abstract 1
- 238000007726 management method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000004927 fusion Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Automatic Analysis And Handling Materials Therefor (AREA)
Abstract
The disclosure provides a laboratory data analysis method and a laboratory information management platform, which belong to the field of data analysis, and the method comprises the following steps: in response to receiving the first data, detecting whether the data value of each data in the first data is not in a corresponding preset numerical range. And detecting whether the first data contains the associated data of the first target data or not according to the fact that the data value of the certain data in the first data is not in the corresponding preset numerical range. And in response to the existence of the associated data of the first target data in the first data, inputting the first target data and the associated data of the first target data into a preset deep learning model to obtain the abnormal information corresponding to the first target data. And marking the first target data as second type of abnormal data in response to the abnormal information indicating that the data value of the first target data is abnormal. The intelligent laboratory data analysis and processing method can realize intelligent laboratory data analysis and processing.
Description
Technical Field
The disclosure belongs to the technical field of data analysis, and more particularly relates to a laboratory data analysis method and a laboratory information management platform.
Background
With the rapid development of computer technology, intelligent management of many instruments and devices has become a development trend in the production and life of today. With the great support of database technology, laboratory data analysis and management is becoming a new research hotspot. The laboratory is equipped with devices and instruments with various functions, all the devices and instruments need to perform data acquisition, summarization, management and analysis processes, and the process needs to consume a great deal of labor cost, and along with the continuous growth of data, the problems of error data statistics, deviation of data analysis, low information management efficiency and the like are easy to occur. How to realize the intelligent analysis of a large amount of laboratory data, automatically screen abnormal data and judge the reason for generating the abnormal data, and the intelligent management of laboratory information becomes the current urgent problem to be solved. There is a need for a laboratory data analysis method and laboratory information management platform that addresses the above-mentioned problems.
Disclosure of Invention
The purpose of the disclosure is to provide a laboratory data analysis method and a laboratory information management platform, so as to realize intelligent analysis of laboratory data and improve laboratory data analysis efficiency and information management level.
In a first aspect of embodiments of the present disclosure, a laboratory data analysis method is provided, including:
And in response to receiving the first data, detecting whether the data value of each data in the first data is in a corresponding preset numerical range. And the first data are laboratory data which are uploaded by the data acquisition end and are changed.
And detecting whether the first data contains the associated data of the first target data or not according to the fact that the data value of the certain data in the first data is not in the corresponding preset numerical value range. The first target data are data of which the data value is not in a corresponding preset numerical range, and the associated data are data of which the data value affects the first target data.
And marking the first target data as first type abnormal data in response to the first data not having associated data of the first target data. The first type of abnormal data is experimental data with abnormality or experimental data with abnormality of corresponding acquisition equipment.
And in response to the existence of the associated data of the first target data in the first data, inputting the first target data and the associated data of the first target data into a preset deep learning model to obtain the abnormal information corresponding to the first target data.
And responding to the abnormality information to display that the data value of the first target data is abnormal, and marking the first target data as second type abnormal data. The second type of abnormal data is experimental data with abnormality.
In a second aspect of embodiments of the present disclosure, there is provided a laboratory data analysis apparatus comprising:
The first judging module is used for responding to the received first data and detecting whether the data value of each data in the first data is in a corresponding preset numerical value range or not. And the first data are laboratory data which are uploaded by the data acquisition end and are changed.
And the second judging module is used for detecting whether the first data contains the associated data of the first target data or not in response to the fact that the data value of certain data in the first data is not in the corresponding preset numerical value range. The first target data are data of which the data value is not in a corresponding preset numerical range, and the associated data are data of which the data value affects the first target data.
And the third judging module is used for marking the first target data as first type abnormal data in response to the fact that the associated data of the first target data does not exist in the first data. The first type of abnormal data is experimental data with abnormality or experimental data with abnormality of corresponding acquisition equipment.
And the fourth judging module is used for responding to the first data and inputting the first target data and the associated data of the first target data into a preset deep learning model to obtain the abnormal information corresponding to the first target data.
And a fifth judging module, configured to respond to the abnormality information, and display that there is an abnormality in the data value of the first target data, and mark the first target data as second type abnormal data. The second type of abnormal data is experimental data with abnormality.
A third aspect of embodiments of the present disclosure provides a laboratory information management platform, comprising: an electronic device, the electronic device comprising: the system comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the steps of the laboratory data analysis method when executing the computer program.
In a fourth aspect of the disclosed embodiments, a computer readable storage medium is provided, which stores a computer program which, when executed by a processor, implements the steps of the laboratory data analysis method described above.
The laboratory data analysis method and the laboratory information management platform provided by the embodiment of the disclosure have the beneficial effects that:
According to the laboratory data analysis method provided by the embodiment of the disclosure, laboratory data which is changed, namely first data, is uploaded by the data acquisition end. When the server receives the first data, first-stage judgment is performed first, and data values of all data in the first data are checked to judge whether the data values are in a corresponding preset numerical range or not. If the data value of the first target data in the first data is not in the corresponding preset numerical range, performing second-level judgment, and detecting whether the first data contains the associated data of the first target data, wherein the associated data is data affecting the data value of the first target data. If the first data does not have the associated data of the first target data, the first target data is marked as first abnormal data, and the first abnormal data is experimental data with abnormality or experimental data with abnormality of corresponding acquisition equipment. If the associated data of the first target data exist in the first data, the first target data and the associated data of the first target data are input into a preset deep learning model, and abnormal information corresponding to the first target data is determined through model identification. And if the anomaly information shows that the data value of the first target data is abnormal, marking the first target data as second type of anomaly data, wherein the second type of anomaly data is experimental data with anomalies.
According to the laboratory data analysis method provided by the embodiment of the disclosure, after the first data is received, multistage judgment can be performed, the first target data exceeding the preset numerical range is determined, and according to the first target data and the related data thereof, the abnormal information corresponding to the first target data is determined, so that the reason for the change of the first target data is determined. The method can automatically collect and analyze the changed laboratory data, avoid the condition of missing detection of abnormal data caused by human errors, reduce the labor cost and improve the accuracy of laboratory data analysis. Through multistage judgment, the categories of the abnormal data are marked, so that a laboratory manager is helped to determine the reason of the abnormal data generation, the effectiveness of the laboratory data is improved, and the analysis efficiency of the laboratory data is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are required for the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a flow chart of a laboratory data analysis method according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a peripheral image data acquisition method according to an embodiment of the disclosure;
FIG. 3 is a diagram of an example of a fused image provided in an embodiment of the present disclosure;
FIG. 4 is a block diagram of a laboratory data analysis apparatus according to one embodiment of the present disclosure;
fig. 5 is a schematic block diagram of an electronic device provided in an embodiment of the present disclosure.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system configurations, techniques, etc. in order to provide a thorough understanding of the disclosed embodiments. However, it will be apparent to one skilled in the art that the present disclosure may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present disclosure with unnecessary detail.
For the purposes of promoting an understanding of the principles and advantages of the disclosure, reference will now be made to the embodiments illustrated in the drawings.
Referring to fig. 1, fig. 1 is a flow chart of a laboratory data analysis method according to an embodiment of the disclosure, where the method includes:
s101: in response to receiving the first data, detecting whether the data value of each data in the first data is in a corresponding preset numerical range. The first data is laboratory data that changes that is uploaded by the data acquisition end, and the laboratory data may include: temperature data, humidity data, pressure data, oxygen concentration data, illuminance data, and the like.
In this embodiment, the first data refers to the changed laboratory data uploaded by the data acquisition end, where the data acquisition end only uploads the changed laboratory data, and the changed laboratory data refers to the laboratory data inconsistent with the previous experimental result. After receiving the laboratory data which is uploaded by the data acquisition end and is changed, namely the first data, the server firstly detects the data value of each data in the first data and judges whether the data which is not in the corresponding preset numerical range exists or not. The preset numerical range refers to the numerical range of normal experimental data corresponding to each acquisition device.
S102: and detecting whether the first data contains the associated data of the first target data or not according to the fact that the data value of the certain data in the first data is not in the corresponding preset numerical range. The first target data are data of which the data value is not in a corresponding preset numerical range, and the associated data are data of which the data value affects the first target data.
In this embodiment, if there is a data value of a certain data in the first data that is not in the corresponding preset numerical range, then a next step of determining is performed, where the data value that is not in the corresponding preset numerical range is the first target data, and the first data is detected to determine whether the associated data of the first target data is included. The associated data refers to other data that changes relative to the first target data, and may be one or more associated data, and the associated data is an important determinant for performing the next determination on the first target data.
S103: and marking the first target data as first type abnormal data in response to the first target data not being associated with the first target data. The first type of abnormal data is experimental data with abnormality or experimental data with abnormality of corresponding acquisition equipment.
In this embodiment, if it is determined that there is no associated data of the first target data in the first data, that is, there is only the first target data, and there is no other data affecting the data value of the first target data, the first target data is marked as first-class abnormal data. The first type of abnormal data refers to experimental data with abnormality or experimental data with abnormality of corresponding acquisition equipment.
S104: and in response to the existence of the associated data of the first target data in the first data, inputting the first target data and the associated data of the first target data into a preset deep learning model to obtain the abnormal information corresponding to the first target data.
In this embodiment, if there is associated data of the first target data in the first data, that is, there is data value of other associated data affecting the first target data, the first target data and the associated data corresponding to the first target data are input into a preset deep learning model, where the preset deep learning model is a model capable of identifying abnormal information of data and is trained in advance, and the abnormal information corresponding to the first target data is obtained through identification of the model.
S105: and marking the first target data as second type of abnormal data in response to the abnormal information indicating that the data value of the first target data is abnormal. The second type of abnormal data is experimental data with abnormality.
In this embodiment, if the anomaly information corresponding to the first target data indicates that there is an anomaly in the data value of the first target data, the first target data is marked as the second type of anomaly data. The second type of abnormal data is experimental data with abnormality.
The present embodiment provides a reference example, for example, a preset numerical range corresponding to the humidity sensor is: 16-24, after the server receives the first data, the humidity value data in the first data is detected to be 12, and the humidity value data is not in the corresponding preset numerical range, namely the humidity value data is the first target data. If the first target data is detected to have no associated data, the first target data is marked as first type abnormal data. If further detected, the first target data has associated data of: and (3) inputting the first target data and the corresponding associated data thereof into a preset deep learning model according to the temperature value data of 38 ℃ and the illuminance data of 1080 Lux, identifying the model to obtain the abnormal information corresponding to the first target data, displaying that the data value of the first target data is abnormal, and marking the first target data as second type abnormal data.
From the above, the laboratory data analysis method can determine whether the first target data exists by judging whether the data value of each data in the first data is in the corresponding preset numerical value range. If the first target data exist, continuing to judge whether the first data contain the associated data of the first target data, and if the associated data of the first target data do not exist, marking the first target data as first type abnormal data; if the associated data of the first target data exist, the first target data and the associated data of the first target data are input into a preset deep learning model, and abnormal information corresponding to the first target data is determined through model identification. And if the abnormality information corresponding to the first target data at this time shows that the data value of the first target data is abnormal, marking the first target data as second type abnormal data.
According to the method, whether the abnormal data exist in the laboratory data or not can be rapidly locked through multistage judgment, and according to the abnormal data and analysis of associated data, the abnormal data are determined to belong to first-class abnormal data or second-class abnormal data. The method can automatically judge the abnormal data in the laboratory data, avoid manual missed detection or judgment errors, improve the accuracy of laboratory data analysis, reduce labor cost, improve the laboratory data analysis efficiency and realize the intelligent analysis and processing of the laboratory data.
In one embodiment of the present disclosure, the laboratory data analysis method further comprises:
And extracting the first type of abnormal data received and marked for the first N times to obtain historical first type of abnormal data.
Detecting repeated data in the historical first-type abnormal data and the first-type abnormal data received and marked at the time.
And in response to the repetition rate of the repeated data being greater than the preset repetition rate, changing the marks of the repeated data received for the previous N times and the current time from the first type of abnormal data to the third type of abnormal data. The third type of abnormal data is experimental data of abnormal conditions of the corresponding acquisition equipment.
In this embodiment, N is a preset value, and the first type of abnormal data received and marked for the previous N times is extracted to obtain the historical first type of abnormal data. Wherein N times are preset times by laboratory manager. Comparing the historical first-class abnormal data with the first-class abnormal data received and marked at the time, and detecting repeated data in the historical first-class abnormal data and the first-class abnormal data to obtain a repetition rate corresponding to the repeated data, wherein the calculation method of the repetition rate comprises the following steps: *100%. Wherein/> Representing repetition rate,/>Representing the number of occurrences of duplicate data. If the repetition rate of the repeated data is larger than the preset repetition rate, namely that the repeated data is frequently appeared, and the acquisition equipment corresponding to the repeated data is very likely to be abnormal, the labels of the repeated data received for the previous N times and the current time are changed from the first type of abnormal data to the third type of abnormal data. Wherein the preset repetition rate is set by a laboratory manager in a self-defining way; the third type of abnormal data represents experimental data of abnormal conditions of the corresponding acquisition equipment.
The present embodiment provides a reference example, for example, setting n=10, and presetting the repetition rate to be 50%. And extracting the first type of abnormal data which is received and marked for the first 10 times to obtain the historical first type of abnormal data. Comparing the historical first type of abnormal data with the first type of abnormal data received and marked at the time, and detecting repeated data in the historical first type of abnormal data and the first type of abnormal data, wherein the number of times of the repeated data is 8, and the repetition rate is the same as that of the repeated dataAt this time, the labels of the repeated data received for the previous 10 times and the current time are changed from the first type of abnormal data to the third type of abnormal data.
From the above, the laboratory data analysis method can self-define and extract the historical first type of abnormal data, compare the historical first type of abnormal data with the first type of abnormal data corresponding to the experiment, determine the reason of the occurrence of the first type of abnormal data by calculating the repetition rate of the repeated data, and correct the historical first type of abnormal data. By the method, whether abnormal data generation is related to the operation state of the corresponding acquisition equipment can be automatically analyzed, so that the operation state of the acquisition equipment is judged, the normal operation of each acquisition equipment in a laboratory is ensured, and the occurrence of error caused by equipment failure in experiments is avoided.
In one embodiment of the present disclosure, the laboratory data analysis method further comprises:
and in response to the repetition rate of the repeated data being less than or equal to the preset repetition rate, clearing the marks of the repeated data received for the previous N times.
In this embodiment, if the repetition rate of the repeated data is less than or equal to the preset repetition rate, that is, it is indicated that the first type of abnormal data marked in the present experiment only happens accidentally, possibly due to errors occurring in the experimental process, the collecting device itself does not have an abnormality, so that the marking of the repeated data received N times before is cleared.
The present embodiment provides a reference example, for example, setting n=10, and presetting the repetition rate to be 50%. And extracting the first type of abnormal data which is received and marked for the first 10 times to obtain the historical first type of abnormal data. Comparing the historical first type of abnormal data with the first type of abnormal data received and marked at the time, and detecting repeated data in the historical first type of abnormal data and the first type of abnormal data, wherein the number of times of the repeated data is 3, and the repetition rate is the same as that of the repeated dataAt this time, the labels of the repeated data received for the previous 10 times and the current time are changed from the first type of abnormal data to the third type of abnormal data.
According to the laboratory data analysis method, the first type of historical abnormal data can be automatically corrected by calculating the repetition rate of the repeated data, so that marking errors caused by human factors are avoided, and the accuracy of laboratory data analysis is improved.
In one embodiment of the present disclosure, the laboratory data analysis method further comprises:
And calling a first display strategy to display the data in response to the fact that the data is not the first type of abnormal data, the second type of abnormal data or the third type of abnormal data.
And calling a second display strategy to display the data in response to the data being the second type of abnormal data.
And calling a third display strategy to display the data in response to the data being the third type of abnormal data.
In this embodiment, in the present server, different display policies are invoked for different types of abnormal data to distinguish and display the different abnormal data. If some data is not the first type of abnormal data, the second type of abnormal data and the third type of abnormal data, a first display strategy is called for displaying the data; if the data is the second type abnormal data, a second display strategy is called for displaying the data; and if the data is the abnormal data of the third type, calling a third display strategy for the data to display.
The embodiment provides a reference example, for example, if a certain data is not the first type of abnormal data, the second type of abnormal data or the third type of abnormal data, a first display strategy is called to display the data, the first display strategy can be that the data are all displayed by green, the data are all displayed by the same brightness, and the data are all displayed in a first position area; if the data is the second type of abnormal data, a second display strategy is called to display the data, wherein the second display strategy can be to display the data by using yellow, display the data by using the first brightness, and display the data in a second position area; and if the data is abnormal data of a third type, invoking a third display strategy to display the data, wherein the third display strategy can be to display the data by using red, display the data by using second brightness, and display the data in a third position area.
According to the method, different display strategies can be called for different types of abnormal data to display, clear distinction contrast is shown for laboratory management staff, the laboratory management staff is helped to better analyze experimental data, and data analysis efficiency is improved.
In one embodiment of the present disclosure, the laboratory data analysis method further comprises:
and responding to certain data in the first data as text data or numerical data, and directly displaying the data.
And in response to certain data in the first data being image data, fusing the data with peripheral image data corresponding to the data based on a preset seam to obtain a fused image, and displaying the fused image.
In this embodiment, since there are multiple types of collection devices in the laboratory, the types of data collected by different collection devices also differ, so that there may be multiple types of data in the first data received by the server. If some data in the first data received by the server is text data or numerical data, the data can be directly displayed. If some data in the first data is image data, the image data can be fused, and the fused image after fusion is displayed. The fusion method can be as follows: and fusing the image data with peripheral image data corresponding to the image data according to a preset seam. The peripheral image data corresponding to the image data refers to the image data of the periphery of the data received last time. The "periphery" refers to the vicinity of the photographing angle corresponding to the data.
The present embodiment provides a schematic diagram of a peripheral image data acquisition method according to an embodiment of the present disclosure with reference to, for example, fig. 2. As shown in fig. 2, the device A, B, C, D represents four acquisition devices located in different orientations, respectively, each corresponding to a different acquisition range. If the image data collected by the device a is a certain data in the first data, the image data collected by the device B and the device D are peripheral image data of the device a.
According to the laboratory data analysis method, intelligent analysis of laboratory data can be achieved, and data in different formats can be displayed in different display modes, so that the application range of the laboratory data analysis method can be expanded, and analysis and processing of data in various different formats can be conducted.
In one embodiment of the present disclosure, the laboratory data analysis method further comprises:
The image extraction step is performed a plurality of times to obtain a plurality of first overlap region images.
The image extraction step comprises the following steps:
And acquiring a plurality of pieces of image data uploaded by the data acquisition terminal, and extracting overlapping area images of images adjacent to each two view angles to obtain a first overlapping image. The plurality of image data includes a plurality of images adjacent to a viewing angle.
And grouping the plurality of first overlapping images according to the physical positions corresponding to the first overlapping images to obtain a plurality of groups of first overlapping images. Each set of first overlapping images corresponds to a physical location.
And extracting the overlapping area image of each first overlapping image in a certain group of first overlapping images to obtain a second overlapping image, and selecting a position from the second overlapping image as a corresponding seam position.
In this embodiment, if a certain data in the first data is image data or video data, a plurality of first overlapping area images may be obtained by performing the image extraction step multiple times, where the image extraction step specifically includes: and receiving the plurality of pieces of image data uploaded by the data acquisition terminal, and extracting overlapping area images of images adjacent to each two view angles to obtain a first overlapping image. And grouping the plurality of first overlapping images according to the physical positions corresponding to the first overlapping images to obtain a plurality of groups of first overlapping images. Each set of first overlapping images corresponds to a physical location. And extracting the overlapping area image of each first overlapping image in a certain group of first overlapping images to obtain a second overlapping image, and selecting a position from the second overlapping image as a corresponding seam position. The steps can be detailed as follows:
And receiving a plurality of pieces of image data uploaded by the data acquisition terminal, wherein the plurality of pieces of image data comprise a plurality of images with adjacent visual angles. And extracting the overlapping area images of the images adjacent to each two view angles to obtain a first overlapping image. And grouping the plurality of first overlapped images, and grouping the images with the same physical positions corresponding to the first overlapped images into one group, so as to obtain a plurality of groups of first overlapped images, wherein each group of first overlapped images corresponds to the same physical position. And extracting the overlapping area image of each first overlapping image in a certain group of first overlapping images to obtain second overlapping images, namely dividing the image part containing the same area in each group of first overlapping images into second overlapping images, and selecting any position from the second overlapping images as a corresponding joint position so as to ensure that the obtained fusion image can be displayed without distortion.
The joint position refers to a joint position when two or more images with partial overlapping between two or more adjacent images are subjected to seamless joint. In the prior art, when images are seamlessly spliced, an intermediate position of an overlapping portion of two images is generally selected as a splice position. Although the method can realize seamless splicing, other interference factors possibly exist at the splicing position are ignored, for example, a certain object which is not supposed to exist in the area can exist at the position, and the spliced image is distorted. In this embodiment, the second overlapping images are divided by grouping and screening the first overlapping images, and the seam positions are selected from the second overlapping images. Therefore, the splice joint position is ensured to have no other interference factors, and the fusion image is ensured to be displayed without distortion.
In this embodiment, referring to fig. 3, for example, which is an exemplary diagram of a fused image provided in an embodiment of the present disclosure, as shown in fig. 3, i and ii respectively represent, for a certain set of first overlapping images, overlapping area images of two first overlapping images in the set are extracted, a second overlapping image, i.e., iii in the diagram, and a seam location, i.e., L, is selected from the second overlapping image.
According to the laboratory data analysis method, the overlapping area can be divided, the proper area is selected as the preset seam position, and the preset seam position can avoid the image area containing the existence of the person, so that the image data is displayed completely. And fusing certain image data according to the preset seam to obtain a fused image, so that the image data is displayed in a distortion-free manner, and the authenticity of experimental data is ensured.
In one embodiment of the present disclosure, the display policy includes display color, display brightness, and display location.
The first display policy, the second display policy, and the third display policy are different from one another.
In this embodiment, the present server calls different display policies for different types of abnormal data to display different abnormal data differently. The display strategies comprise display colors, display brightness and display positions, and the first display strategy, the second display strategy and the third display strategy are different from each other. Different types of abnormal data are displayed by using different display strategies so as to realize differential display.
According to the laboratory data analysis method, different color labels can be utilized to realize different display of different types of abnormal data, laboratory management staff is better helped to distinguish experimental data, and the situation of human judgment errors is avoided.
Corresponding to the laboratory data analysis method of the above embodiment, fig. 4 is a block diagram of a laboratory data analysis apparatus according to an embodiment of the present disclosure. For ease of illustration, only portions relevant to embodiments of the present disclosure are shown. Referring to fig. 4, the laboratory data analysis apparatus 20 includes: the first judgment module 21, the second judgment module 22, the third judgment module 23, the fourth judgment module 24, and the fifth judgment module 25.
The first determining module 21 is configured to detect, in response to receiving the first data, whether a data value of each data in the first data is within a corresponding preset numerical range. The first data is laboratory data which is uploaded by a data acquisition end and is changed.
The second determining module 22 is configured to detect whether the first data includes associated data of the first target data in response to a data value of the first data having a certain data value not within a corresponding preset numerical range. The first target data are data of which the data value is not in a corresponding preset numerical range, and the associated data are data of which the data value affects the first target data.
The third judging module 23 is configured to mark the first target data as first type abnormal data in response to the absence of the associated data of the first target data in the first data. The first type of abnormal data is experimental data with abnormality or experimental data with abnormality of corresponding acquisition equipment.
The fourth determining module 24 is configured to input the first target data and the associated data of the first target data into a preset deep learning model in response to the presence of the associated data of the first target data in the first data, so as to obtain the anomaly information corresponding to the first target data.
A fifth judging module 25, configured to respond to the abnormality information to display that there is an abnormality in the data value of the first target data, and mark the first target data as second type of abnormal data. The second type of abnormal data is experimental data with abnormality.
In one embodiment of the present disclosure, the third determining module 23 is specifically configured to:
And extracting the first type of abnormal data received and marked for the first N times to obtain historical first type of abnormal data.
Detecting repeated data in the historical first-type abnormal data and the first-type abnormal data received and marked at the time.
And in response to the repetition rate of the repeated data being greater than the preset repetition rate, changing the marks of the repeated data received for the previous N times and the current time from the first type of abnormal data to the third type of abnormal data. The third type of abnormal data is experimental data of abnormal conditions of the corresponding acquisition equipment.
In one embodiment of the present disclosure, the third determining module 23 is specifically configured to:
and in response to the repetition rate of the repeated data being less than or equal to the preset repetition rate, clearing the marks of the repeated data received for the previous N times.
In one embodiment of the present disclosure, the laboratory data analysis apparatus 20 further comprises:
And the display module 26 is configured to invoke a first display policy to display the data in response to the data not being the first type of abnormal data, the second type of abnormal data or the third type of abnormal data.
And calling a second display strategy to display the data in response to the data being the second type of abnormal data.
And calling a third display strategy to display the data in response to the data being the third type of abnormal data.
In one embodiment of the present disclosure, the display module 26 is specifically configured to:
and responding to certain data in the first data as text data or numerical data, and directly displaying the data.
And in response to certain data in the first data being image data, fusing the data with peripheral image data corresponding to the data based on a preset seam to obtain a fused image, and displaying the fused image.
In one embodiment of the present disclosure, the display module 26 is specifically configured to:
The image extraction step is performed a plurality of times to obtain a plurality of first overlap region images.
The image extraction step comprises the following steps:
And acquiring a plurality of pieces of image data uploaded by the data acquisition terminal, and extracting overlapping area images of images adjacent to each two view angles to obtain a first overlapping image. The plurality of image data includes a plurality of images adjacent to a viewing angle.
And grouping the plurality of first overlapping images according to the physical positions corresponding to the first overlapping images to obtain a plurality of groups of first overlapping images. Each set of first overlapping images corresponds to a physical location.
And extracting the overlapping area image of each first overlapping image in a certain group of first overlapping images to obtain a second overlapping image, and selecting a position from the second overlapping image as a corresponding seam position.
In one embodiment of the present disclosure, the display module 26 is specifically configured to:
the display policy includes display color, display brightness, and display position.
The first display policy, the second display policy, and the third display policy are different from one another.
Referring to fig. 5, fig. 5 is a schematic block diagram of an electronic device according to an embodiment of the disclosure. The electronic device 300 in the present embodiment as shown in fig. 5 may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processor 301, the input device 302, the output device 303, and the memory 304 communicate with each other via a communication bus 305. The memory 304 is used to store a computer program comprising program instructions. The processor 301 is configured to execute program instructions stored in the memory 304. Wherein the processor 301 is configured to invoke program instructions to perform the functions of the modules in the various device embodiments described above, such as the functions of the modules 21-25 shown in fig. 4.
It should be appreciated that in the disclosed embodiments, the Processor 301 may be a central processing unit (Central Processing Unit, CPU), which may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL processors, DSPs), application SPECIFIC INTEGRATED Circuits (ASICs), off-the-shelf Programmable gate arrays (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The input device 302 may include a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of a fingerprint), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.
The memory 304 may include read only memory and random access memory and provides instructions and data to the processor 301. A portion of memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store information of device type.
In a specific implementation, the processor 301, the input device 302, and the output device 303 described in the embodiments of the present disclosure may perform the implementation described in the first embodiment and the second embodiment of the laboratory data analysis method provided in the embodiments of the present disclosure, and may also perform the implementation of the electronic device described in the embodiments of the present disclosure, which is not described herein again.
In another embodiment of the disclosure, a computer readable storage medium is provided, where the computer readable storage medium stores a computer program, where the computer program includes program instructions, where the program instructions, when executed by a processor, implement all or part of the procedures in the method embodiments described above, or may be implemented by instructing related hardware by the computer program, where the computer program may be stored in a computer readable storage medium, where the computer program, when executed by the processor, implements the steps of each of the method embodiments described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, executable files or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The computer readable storage medium may be an internal storage unit of the electronic device of any of the foregoing embodiments, such as a hard disk or a memory of the electronic device. The computer readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk provided on the electronic device, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like. Further, the computer-readable storage medium may also include both internal storage units and external storage devices of the electronic device. The computer-readable storage medium is used to store a computer program and other programs and data required for the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.
Those of ordinary skill in the art will appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the electronic device and unit described above may refer to the corresponding process in the foregoing method embodiment, which is not repeated herein.
In the several embodiments provided in the present application, it should be understood that the disclosed electronic device and method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of elements is merely a logical functional division, and there may be additional divisions of actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via some interfaces or units, or may be an electrical, mechanical, or other form of connection.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purposes of the embodiments of the present disclosure.
In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The foregoing is merely a specific embodiment of the present disclosure, but the protection scope of the present disclosure is not limited thereto, and any equivalent modifications or substitutions will be apparent to those skilled in the art within the scope of the present disclosure, and these modifications or substitutions should be covered in the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (9)
1. A laboratory data analysis method, comprising:
in response to receiving first data, detecting whether data values of all data in the first data are in corresponding preset numerical value ranges; the first data are laboratory data which are uploaded by a data acquisition end and are changed; the laboratory data includes: temperature data, humidity data, pressure data, oxygen concentration data, illuminance data;
detecting whether the first data contains associated data of first target data or not according to the fact that the data value of certain data in the first data is not in a corresponding preset numerical value range; the first target data are data of which the data value is not in a corresponding preset numerical range, and the associated data are data affecting the data value of the first target data;
Marking the first target data as first type abnormal data in response to the first data not having associated data of the first target data; the first type of abnormal data is experimental data with abnormality or experimental data with abnormality of corresponding acquisition equipment;
Responding to the first data and the associated data of the first target data, and inputting the first target data and the associated data of the first target data into a preset deep learning model to obtain abnormal information corresponding to the first target data;
In response to the abnormality information, displaying that the data value of the first target data is abnormal, and marking the first target data as second type abnormal data; the second type of abnormal data is experimental data with abnormality;
Extracting first-class abnormal data received and marked for the first N times to obtain historical first-class abnormal data;
detecting repeated data in the historical first type abnormal data and the first type abnormal data received and marked at this time;
In response to the repetition rate of the repeated data being greater than a preset repetition rate, changing the marks of the repeated data received for the previous N times and the current time from the first type of abnormal data to the third type of abnormal data; the third type of abnormal data is experimental data of abnormal conditions of the corresponding acquisition equipment.
2. The laboratory data analysis method according to claim 1, further comprising:
and in response to the repetition rate of the repeated data being smaller than or equal to a preset repetition rate, clearing the marks of the repeated data received for the previous N times.
3. The laboratory data analysis method according to any one of claims 1 or 2, further comprising:
responding to that certain data is not the first type of abnormal data, the second type of abnormal data or the third type of abnormal data, and calling a first display strategy to display the data;
responding to that certain data is the second type of abnormal data, and calling a second display strategy to display the data;
And calling a third display strategy to display the data in response to the data being the third type of abnormal data.
4. The laboratory data analysis method according to claim 1, further comprising:
responding to certain data in the first data as text data or numerical data, and directly displaying the data;
and in response to the fact that certain data in the first data are image data, fusing the data with peripheral image data corresponding to the data based on a preset seam to obtain a fused image, and displaying the fused image.
5. The laboratory data analysis method according to claim 1, further comprising:
Performing the image extraction step for a plurality of times to obtain a plurality of first overlapping area images;
wherein the image extraction step includes:
Acquiring a plurality of pieces of image data uploaded by a data acquisition terminal, and extracting overlapping area images of images adjacent to each two view angles to obtain a first overlapping image; the plurality of image data comprises a plurality of images with adjacent view angles;
grouping the plurality of first overlapping images according to the physical positions corresponding to the first overlapping images to obtain a plurality of groups of first overlapping images; each group of first overlapping images corresponds to a physical position;
And extracting the overlapping area image of each first overlapping image in a certain group of first overlapping images to obtain a second overlapping image, and selecting a position from the second overlapping image as a corresponding seam position.
6. The laboratory data analysis method of claim 3, wherein the display policy comprises display color, display brightness, and display position;
the first display policy, the second display policy, and the third display policy are different from one another.
7. A laboratory data analysis apparatus, comprising:
The first judging module is used for responding to the received first data and detecting whether the data value of each data in the first data is in a corresponding preset numerical value range or not; the first data are laboratory data which are uploaded by a data acquisition end and are changed; the laboratory data includes: temperature data, humidity data, pressure data, oxygen concentration data, illuminance data;
The second judging module is used for detecting whether the first data contains the associated data of the first target data or not according to the fact that the data value of certain data in the first data is not in the corresponding preset numerical value range; the first target data are data of which the data value is not in a corresponding preset numerical range, and the associated data are data affecting the data value of the first target data;
The third judging module is used for marking the first target data as first type abnormal data in response to the fact that the associated data of the first target data does not exist in the first data; the first type of abnormal data is experimental data with abnormality or experimental data with abnormality of corresponding acquisition equipment;
A fourth judging module, configured to input the first target data and associated data of the first target data into a preset deep learning model in response to the presence of associated data of the first target data in the first data, so as to obtain abnormal information corresponding to the first target data;
a fifth judging module, configured to respond to the abnormality information, and display that there is an abnormality in the data value of the first target data, and mark the first target data as second type abnormal data; the second type of abnormal data is experimental data with abnormality;
Extracting first-class abnormal data received and marked for the first N times to obtain historical first-class abnormal data;
detecting repeated data in the historical first type abnormal data and the first type abnormal data received and marked at this time;
In response to the repetition rate of the repeated data being greater than a preset repetition rate, changing the marks of the repeated data received for the previous N times and the current time from the first type of abnormal data to the third type of abnormal data; the third type of abnormal data is experimental data of abnormal conditions of the corresponding acquisition equipment.
8. A laboratory information management platform, comprising: an electronic device;
The electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311795432.1A CN117744002B (en) | 2023-12-25 | 2023-12-25 | Laboratory data analysis method and laboratory information management platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311795432.1A CN117744002B (en) | 2023-12-25 | 2023-12-25 | Laboratory data analysis method and laboratory information management platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117744002A CN117744002A (en) | 2024-03-22 |
| CN117744002B true CN117744002B (en) | 2024-06-07 |
Family
ID=90282812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311795432.1A Active CN117744002B (en) | 2023-12-25 | 2023-12-25 | Laboratory data analysis method and laboratory information management platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117744002B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103278715A (en) * | 2013-05-16 | 2013-09-04 | 广东电网公司 | Electrical equipment testing method |
| WO2019146315A1 (en) * | 2018-01-29 | 2019-08-01 | 株式会社日立製作所 | Abnormality detection system, abnormality detection method, and program |
| CN112232529A (en) * | 2019-06-26 | 2021-01-15 | 豪夫迈·罗氏有限公司 | Maintenance method for laboratory system |
| CN117036123A (en) * | 2023-08-15 | 2023-11-10 | 深圳市残友细胞科技实验有限公司 | Laboratory monitoring method and device, electronic equipment and storage medium |
-
2023
- 2023-12-25 CN CN202311795432.1A patent/CN117744002B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103278715A (en) * | 2013-05-16 | 2013-09-04 | 广东电网公司 | Electrical equipment testing method |
| WO2019146315A1 (en) * | 2018-01-29 | 2019-08-01 | 株式会社日立製作所 | Abnormality detection system, abnormality detection method, and program |
| CN112232529A (en) * | 2019-06-26 | 2021-01-15 | 豪夫迈·罗氏有限公司 | Maintenance method for laboratory system |
| CN117036123A (en) * | 2023-08-15 | 2023-11-10 | 深圳市残友细胞科技实验有限公司 | Laboratory monitoring method and device, electronic equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| An early warning method of abnormal state of laboratory equipment based on Internet of things and running big data;Zheng, Guokai等;《Web Intelligence》;20230920;第21卷(第3期);261-270 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117744002A (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3799408B1 (en) | Image processing apparatus and image processing method | |
| US9111183B2 (en) | Performing a comparison between two images which are scaled to a common resolution | |
| CN111898540B (en) | Lane line detection method, lane line detection device, computer equipment and computer readable storage medium | |
| CN113160222A (en) | Production data identification method for industrial information image | |
| CN115035539B (en) | Document anomaly detection network model construction method and device, electronic equipment and medium | |
| CN112967221B (en) | Shield segment production and assembly information management system | |
| CN117744002B (en) | Laboratory data analysis method and laboratory information management platform | |
| CN115278217A (en) | Image picture detection method and device, electronic equipment and storage medium | |
| CN113554022B (en) | Automatic acquisition method and device for detection test data of electric power instrument | |
| CN116168345B (en) | Fire detection method and related equipment | |
| CN117274211A (en) | Screen defect detection method and device, terminal equipment and storage medium | |
| CN112418226A (en) | Method and device for identifying opening and closing states of fisheyes | |
| CN113012137B (en) | Panel defect inspection method, system, terminal device and storage medium | |
| CN113570560B (en) | Quick detection method for geometric model errors of remote sensing image | |
| CN116547661A (en) | Data labeling method and system for image segmentation and image segmentation device | |
| CN114359007A (en) | Image tracing method, device, equipment and storage medium | |
| CN114385837A (en) | Automatic media content detection and verification method and system | |
| CN116648721A (en) | Hair evaluation method, program, computer, and hair evaluation system | |
| CN108346213B (en) | Method and device for identifying characteristics of paper money image | |
| CN117789182B (en) | Industrial instrument data acquisition method and system | |
| CN112016606A (en) | Detection method, device and equipment for application program APP and storage medium | |
| CN113034430B (en) | Video authenticity verification and identification method and system based on time watermark change analysis | |
| CN116403098B (en) | Bill tampering detection method and system | |
| CN111310614A (en) | Method and device for extracting remote sensing image | |
| CN117095389B (en) | Image data processing method and system based on liquid crystal visual recognition unit |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |