Laboratory area division method and device using decision tree model

Abstract

The application relates to a laboratory area division method and device using a decision tree model, which uses a decision tree model to calibrate corresponding laboratory area units for laboratory equipment data and laboratory personnel data. A region classification model is trained. The latest laboratory equipment data and laboratory personnel data are acquired and input into the region classification model, and laboratory area unit data is output. A laboratory area map is generated according to a similarity matrix and by analyzing the similarity of the laboratory area unit data; spatial optimization is carried out based on the laboratory area map, and a laboratory area division map used for representing laboratory area division is obtained. Based on this, the laboratory equipment data and the laboratory personnel data are subjected to laboratory area division by means of a data model and incorporation into a computer system, the data comprehensiveness of a laboratory management data model is improved, and a data processing technical means for laboratory area division is provided.

Description

Technical Field

[0001] This application relates to the field of laboratory data processing technology, and in particular to a method and apparatus for dividing laboratory areas using a decision tree model. Background Technology

[0002] Currently, with the increase in the number of researchers and the enrichment of research methods, research laboratories are becoming increasingly widespread and sharing is becoming commonplace. Laboratory management, including personnel management, drug management, equipment management, and safety management, can all be accomplished through big data. However, laboratory area management is unique; its division is related to various instruments, equipment, and personnel, making it difficult to manage laboratory areas using only a single set of data.

[0003] Therefore, the current division of laboratory areas by various institutions is mainly determined manually within each laboratory. The lack of a data model for laboratory area division in current laboratory management data models results in a lack of visual representation of laboratory management data. Summary of the Invention

[0004] Based on the above analysis, the present invention aims to provide a method and apparatus for laboratory area division using a decision tree model, in order to solve the problem that the existing technology lacks a data model for laboratory area division, resulting in an incomplete means of managing laboratory management data models.

[0005] This application provides a method for dividing laboratory areas using a decision tree model, including the following steps:

[0006] Obtain historical laboratory equipment data and laboratory personnel data stored on the cloud platform, and use a decision tree model to label the corresponding laboratory area units for the laboratory equipment data and laboratory personnel data;

[0007] The laboratory equipment data and laboratory personnel data are used as training samples, and the laboratory area units are used as result samples to train the area classification model.

[0008] Acquire the latest laboratory equipment data and laboratory personnel data and input them into the regional classification model to output laboratory regional unit data;

[0009] Based on the similarity matrix and by analyzing the similarity of the laboratory area unit data, a laboratory area map is generated;

[0010] Spatial optimization is performed based on the laboratory area map to obtain a laboratory area division map that characterizes the division of laboratory areas.

[0011] This application's embodiment utilizes a laboratory area division method based on a decision tree model. It acquires historical laboratory equipment and personnel data stored on a cloud platform and uses a decision tree model to label corresponding laboratory area units for these data. The laboratory equipment and personnel data are used as training samples, and the laboratory area units are used as result samples to train an area classification model. The latest laboratory equipment and personnel data are acquired and input into the area classification model, outputting laboratory area unit data. A laboratory area map is generated based on a similarity matrix and by analyzing the similarity of the laboratory area unit data. Spatial optimization is performed based on the laboratory area map to obtain a laboratory area division map representing the laboratory area division. Based on this, by incorporating the data model into a computer system, laboratory area division can be achieved using laboratory equipment and personnel data from a cloud platform, improving the data comprehensiveness of the laboratory management data model and providing data processing techniques for laboratory area division.

[0012] As one optional embodiment, before training the region classification model using the laboratory equipment data and laboratory personnel data as training samples and the laboratory area units as result samples, the following steps are also included:

[0013] The laboratory equipment data and laboratory personnel data are subjected to feature selection using a feature processing model to obtain data features;

[0014] The data features are subjected to dimensionality reduction processing to remove redundant features and obtain effective data features;

[0015] The effective data features are input into the feature processing model to deduce the laboratory equipment data and laboratory personnel data used as training samples.

[0016] As one optional embodiment, the process of acquiring historical laboratory equipment data and laboratory personnel data stored on a cloud platform, and using a decision tree model to label the laboratory equipment data and laboratory personnel data with corresponding laboratory area units, includes the following steps:

[0017] The laboratory area classification information of the laboratory equipment data and laboratory personnel data is determined based on the decision tree model.

[0018] The laboratory area classification information is labeled on the partition unit to obtain the laboratory area unit.

[0019] As one optional embodiment, the region classification model is a deep learning framework;

[0020] The process of training a region classification model using the laboratory equipment data and laboratory personnel data as training samples and the laboratory area units as result samples includes the following steps:

[0021] The training samples and the result samples are enhanced using gradient-weighted class activation mapping;

[0022] Based on the result samples and the training samples, the visualization of the laboratory area unit data output by the region classification model is improved.

[0023] As one optional embodiment, the process of generating a laboratory area map based on a similarity matrix and analyzing the similarity of the laboratory area unit data includes the following steps:

[0024] Adjacent regions are reshaped based on the similarity to obtain a preliminary map.

[0025] As one optional embodiment, the process of spatially optimizing the laboratory area map to obtain a laboratory area delineation map characterizing the laboratory area delineation includes the following steps:

[0026] The boundaries of the initial map are optimized using a boundary optimization algorithm to reduce boundary fragmentation.

[0027] As one optional embodiment, the process of spatially optimizing the laboratory area map to obtain a laboratory area delineation map characterizing the laboratory area delineation further includes the following steps:

[0028] The data of the laboratory area units are normalized, and groups are formed based on the normalization results;

[0029] By merging the laboratory area unit data of the same group, the laboratory area division map is obtained.

[0030] This application also provides a laboratory area division device using a decision tree model, including:

[0031] The data labeling module is used to acquire laboratory equipment data and laboratory personnel data stored in the cloud platform in history, and to use a decision tree model to label the laboratory equipment data and laboratory personnel data with corresponding laboratory area units.

[0032] The module training module is used to train the region classification model by using the laboratory equipment data and laboratory personnel data as training samples and the laboratory area units as result samples.

[0033] The data reconstruction module is used to acquire the latest laboratory equipment data and laboratory personnel data, input them into the regional classification model, and output laboratory regional unit data.

[0034] The map generation module is used to generate a map of the laboratory area based on the similarity matrix and by analyzing the similarity of the laboratory area unit data.

[0035] The map optimization module is used to perform spatial optimization based on the laboratory area map to obtain a laboratory area division map that represents the division of the laboratory area.

[0036] This application's embodiment utilizes a laboratory area division device based on a decision tree model. It acquires historical laboratory equipment and personnel data stored on a cloud platform and uses a decision tree model to label corresponding laboratory area units for these data. The laboratory equipment and personnel data are used as training samples, and the laboratory area units are used as result samples to train an area classification model. The latest laboratory equipment and personnel data are acquired and input into the area classification model, outputting laboratory area unit data. A laboratory area map is generated based on a similarity matrix and by analyzing the similarity of the laboratory area unit data. Spatial optimization is performed based on the laboratory area map to obtain a laboratory area division map representing the division of laboratory areas. Based on this, by incorporating the data model into a computer system, laboratory area division can be achieved using laboratory equipment and personnel data from a cloud platform, improving the data comprehensiveness of the laboratory management data model and providing data processing techniques for laboratory area division.

[0037] At least one embodiment of this application also provides a data control device, including:

[0038] One or more memories that store computer-executable instructions non-transitory;

[0039] One or more processors are configured to run computer-executable instructions, wherein the computer-executable instructions are executed by the one or more processors to implement the laboratory area division method using a decision tree model according to any embodiment of the present application.

[0040] The aforementioned data control device acquires historical laboratory equipment and personnel data stored on the cloud platform and uses a decision tree model to label corresponding laboratory area units for these data. The laboratory equipment and personnel data are used as training samples, and the laboratory area units are used as result samples to train the area classification model. The latest laboratory equipment and personnel data are acquired and input into the area classification model, outputting laboratory area unit data. Based on a similarity matrix and analysis of the similarity of the laboratory area unit data, a laboratory area map is generated. Spatial optimization is performed based on the laboratory area map to obtain a laboratory area division map representing the division of laboratory areas. Based on this, by incorporating the data model into the computer system, laboratory area division is achieved using laboratory equipment and personnel data from the cloud platform, improving the data comprehensiveness of the laboratory management data model and providing data processing techniques for laboratory area division.

[0041] At least one embodiment of this application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement a laboratory area division method using a decision tree model according to any embodiment of this application.

[0042] The aforementioned non-transitory computer-readable storage medium acquires historical laboratory equipment and personnel data stored on the cloud platform, and uses a decision tree model to label corresponding laboratory area units for the laboratory equipment and personnel data. The laboratory equipment and personnel data are used as training samples, and the laboratory area units are used as result samples to train the area classification model. The latest laboratory equipment and personnel data are acquired and input into the area classification model, outputting laboratory area unit data. Based on a similarity matrix and analysis of the similarity of the laboratory area unit data, a laboratory area map is generated; spatial optimization is performed based on the laboratory area map to obtain a laboratory area division map representing the division of laboratory areas. Based on this, by incorporating the data model into the computer system, laboratory area division is achieved using laboratory equipment and personnel data from the cloud platform, improving the data comprehensiveness of the laboratory management data model and providing data processing techniques for laboratory area division. Attached Figure Description

[0043] Figure 1 A flowchart illustrating a laboratory area division method using a decision tree model, according to an embodiment of the application;

[0044] Figure 2 A flowchart of a preferred embodiment of a laboratory area division method using a decision tree model;

[0045] Figure 3 This is a schematic diagram illustrating the classification of laboratory area unit data based on a convolutional neural network.

[0046] Figure 4 This is a structural diagram of a laboratory area division device using a decision tree model according to an embodiment of the application.

[0047] Figure 5 A schematic block diagram of a data control device provided by the present invention;

[0048] Figure 6 This is a schematic diagram of a non-transitory computer-readable storage medium provided by the present invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the described embodiments of this application without creative effort are within the scope of protection of this application.

[0050] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0051] To keep the following description of the embodiments of this application clear and concise, detailed descriptions of some known functions and components have been omitted.

[0052] This application provides a method for dividing laboratory areas using a decision tree model.

[0053] Figure 1 Here is a flowchart of a laboratory area division method using a decision tree model, as an embodiment of the application. Figure 1As shown, a laboratory area division method using a decision tree model according to one embodiment of the application includes steps S100 to S104:

[0054] S100: Obtain laboratory equipment data and laboratory personnel data stored historically on the cloud platform, and use a decision tree model to label the corresponding laboratory area units for the laboratory equipment data and laboratory personnel data.

[0055] S101, Using the laboratory equipment data and laboratory personnel data as training samples and the laboratory area units as result samples, train the area classification model.

[0056] S102, Obtain the latest laboratory equipment data and laboratory personnel data and input them into the regional classification model, then output laboratory regional unit data;

[0057] S103, Generate a laboratory area map based on the similarity matrix and by analyzing the similarity of the laboratory area unit data;

[0058] S104, Spatial optimization is performed based on the laboratory area map to obtain a laboratory area division map for characterizing the laboratory area division.

[0059] Both laboratory equipment data and laboratory personnel data are recorded on the laboratory data management platform. Laboratory equipment data includes equipment location information, while laboratory personnel information includes personnel activity range information. Laboratory area units are labeled based on the laboratory areas corresponding to the equipment location information, and similar labeling is performed based on the laboratory areas corresponding to the personnel activity range information. Based on pre-defined multiple categories of area units, laboratory equipment data and laboratory personnel data are labeled to their corresponding area units, and area units of the same category are merged into a single laboratory area unit.

[0060] Figure 2 Here is a flowchart of a laboratory area division method using a decision tree model, as an embodiment of the application. Figure 2 As shown, step S100, which involves acquiring historical laboratory equipment data and laboratory personnel data stored on the cloud platform and using a decision tree model to label the corresponding laboratory area units for the laboratory equipment data and laboratory personnel data, includes steps S200 and S201:

[0061] S200, determine the laboratory area classification information of the laboratory equipment data and laboratory personnel data based on the decision tree model;

[0062] S201, mark the laboratory area classification information on the partition unit to obtain the laboratory area unit.

[0063] The decision tree model is pre-trained based on data from the cloud platform and pre-classified multi-category regional units. Using the pre-trained model, laboratory equipment and personnel data are classified to obtain laboratory regional classification information corresponding to the regional units. This classification information is then labeled onto the regional units to obtain the laboratory regional units, facilitating subsequent training of the deep learning framework.

[0064] Preferably, such as Figure 2 As shown, before the process of training the region classification model in step S101, which uses the laboratory equipment data and laboratory personnel data as training samples and the laboratory area units as result samples, steps S202 to S204 are also included:

[0065] S202, Feature selection is performed on the laboratory equipment data and the laboratory personnel data using a feature processing model to obtain data features;

[0066] S203, Perform dimensionality reduction processing on the data features to remove redundant features and obtain effective data features;

[0067] S204, input the effective data features into the feature processing model, and deduce the laboratory equipment data and laboratory personnel data used as training samples.

[0068] To meet the data training requirements of deep learning frameworks, the feature processing model performs feature selection on the laboratory equipment data and laboratory personnel data to obtain data features. The feature processing module can utilize the underlying logic of the decision tree model, effectively extracting data features through continuous iterative data processing.

[0069] Simultaneously, an additional feature processing model can be deployed to extract data features, better adapting to the data requirements of subsequent deep learning frameworks. Preferably, the feature processing model uses a high-performance feature selection framework based on XGBoost, which, in conjunction with the decision tree model, can eliminate the data overfitting problem in the laboratory area unit calibration process and improve the accuracy of data feature extraction.

[0070] Dimensionality reduction eliminates data noise and makes data features more suitable for deep learning frameworks. Preferably, local linear embedding is used to reduce the dimensionality of data features. Local linear embedding can preserve the topological properties of effective data features and better cooperate with the merging of partitioned units in laboratory area unit calibration.

[0071] The feature processing model can be a computer model based on a back-inference algorithm. The back-inference algorithm can be an algorithm that can be deployed to the computer model, such as the Tagger back-inference algorithm, to back-infer the processed effective data features into laboratory equipment data and laboratory personnel data suitable for training deep learning frameworks.

[0072] Preferably, such as Figure 2 As shown, step S101, which uses the laboratory equipment data and laboratory personnel data as training samples and the laboratory area units as result samples to train the region classification model, includes steps S205 and S206:

[0073] S205, strengthen the training samples and the result samples using gradient-weighted class activation mapping;

[0074] S206, Based on the result samples and the training samples, improve the visualization of the laboratory area unit data output by the region classification model.

[0075] Before step S205, the result samples are visualized, and the laboratory area units are processed into visualized regions. Based on the visualization selection of the result samples, the training samples are processed simultaneously and converted into visualized data. Gradient-weighted class activation mapping is used to strengthen the mapping relationship of the data, improve the visualization of the laboratory area unit data output by the region classification model, facilitate subsequent visualization spatial processing, and improve the intuitiveness of region division.

[0076] Preferably, such as Figure 2 As shown, step S103, which generates a laboratory area map based on the similarity matrix and by analyzing the similarity of the laboratory area unit data, includes step S300:

[0077] S300, Reshape adjacent regions based on the similarity to obtain a preliminary map.

[0078] like Figure 3 As shown, the laboratory area unit data includes regional visual image classification and regional natural descriptions (image captioning). The regional natural descriptions serve as the basis for similarity analysis of the similarity matrix. Correspondingly, a deep learning framework based on convolutional neural networks is used for the regional classification model. Based on similarity, the laboratory area unit data is image merged, resulting in a reduction in the number of categories for the merged laboratory area units, forming a preliminary map.

[0079] Preferably, such as Figure 2 As shown, step S104, which involves spatial optimization based on the laboratory area map to obtain a laboratory area division map representing the laboratory area division, includes step S400:

[0080] S400 optimizes the boundaries of the preliminary map using a boundary optimization algorithm to reduce boundary fragmentation.

[0081] Preferably, the boundary optimization algorithm can be the K-means clustering algorithm to optimize the boundary division, merge similar areas in the preliminary map, and reduce the fragmentation of the partitions in the preliminary map.

[0082] Preferably, the boundary after processing by the boundary optimization algorithm as follows:

[0083]

[0084] in, Represents the boundary calibration point; This represents the position of the i-th boundary calibration point; This is the total number of boundary calibration points; Bandwidth determines the smoothness of the boundary function; It is a boundary smoothing function. By using boundary smoothing functions such as smoothing filtering and sequential smoothing, the boundaries of the preliminary map are optimized, boundary fragmentation is reduced, and the zoning effect of the preliminary map is improved, thus serving as a laboratory region division map representing the division of the laboratory region.

[0085] Preferably, such as Figure 2 As shown, step S104, which involves spatial optimization based on the laboratory area map to obtain a laboratory area division map representing the laboratory area division, further includes steps S500 and S501:

[0086] S500, normalize the data of the laboratory area units and divide them into groups according to the normalization results;

[0087] S501, merge the laboratory area unit data of the same group to obtain the laboratory area division map.

[0088] By normalizing the data and setting groups for the normalized data, regions with similar data belonging to the same group of laboratory area unit data are merged, further reducing the fragmentation of the visualized partitions in the laboratory area division map and ensuring the division effect.

[0089] Based on this, the laboratory area division map serves as a data supplement to the laboratory data management system in the cloud platform. On the basis of recording data such as laboratory equipment data and laboratory personnel data, it provides image-visualized laboratory area division, enriching the visualization presentation of the laboratory data management system.

[0090] This application's embodiment utilizes a laboratory area division method based on a decision tree model. It acquires historical laboratory equipment and personnel data stored on a cloud platform and uses a decision tree model to label corresponding laboratory area units for these data. The laboratory equipment and personnel data are used as training samples, and the laboratory area units are used as result samples to train an area classification model. The latest laboratory equipment and personnel data are acquired and input into the area classification model, outputting laboratory area unit data. A laboratory area map is generated based on a similarity matrix and by analyzing the similarity of the laboratory area unit data. Spatial optimization is performed based on the laboratory area map to obtain a laboratory area division map representing the laboratory area division. Based on this, by incorporating the data model into a computer system, laboratory area division can be achieved using laboratory equipment and personnel data from a cloud platform, improving the data comprehensiveness of the laboratory management data model and providing data processing techniques for laboratory area division.

[0091] This application also provides a laboratory area division device using a decision tree model.

[0092] Figure 4 This is a structural diagram of a laboratory area division device module using a decision tree model according to an embodiment of the application, as shown below. Figure 4 As shown, a laboratory area division device utilizing a decision tree model according to one embodiment of the application includes:

[0093] The data calibration module 100 is used to acquire laboratory equipment data and laboratory personnel data stored in the cloud platform in history, and to use a decision tree model to calibrate the corresponding laboratory area units for the laboratory equipment data and laboratory personnel data.

[0094] The module training module 101 is used to train the region classification model by using the laboratory equipment data and laboratory personnel data as training samples and the laboratory area units as result samples.

[0095] Data reconstruction module 102 is used to acquire the latest laboratory equipment data and laboratory personnel data and input them into the regional classification model, and output laboratory regional unit data;

[0096] The map generation module 103 is used to generate a laboratory area map based on the similarity matrix and by analyzing the similarity of the laboratory area unit data.

[0097] The map optimization module 104 is used to perform spatial optimization based on the laboratory area map to obtain a laboratory area division map that represents the division of the laboratory area.

[0098] This application's embodiment utilizes a laboratory area division device based on a decision tree model. It acquires historical laboratory equipment and personnel data stored on a cloud platform and uses a decision tree model to label corresponding laboratory area units for these data. The laboratory equipment and personnel data are used as training samples, and the laboratory area units are used as result samples to train an area classification model. The latest laboratory equipment and personnel data are acquired and input into the area classification model, outputting laboratory area unit data. A laboratory area map is generated based on a similarity matrix and by analyzing the similarity of the laboratory area unit data. Spatial optimization is performed based on the laboratory area map to obtain a laboratory area division map representing the division of laboratory areas. Based on this, by incorporating the data model into a computer system, laboratory area division can be achieved using laboratory equipment and personnel data from a cloud platform, improving the data comprehensiveness of the laboratory management data model and providing data processing techniques for laboratory area division.

[0099] At least one embodiment of this application also provides a data control device. Figure 5 This is a schematic block diagram of a data control device provided for at least one embodiment of this application. For example, such as... Figure 5 As shown, the data control device 20 may include one or more memories 200 and one or more processors 201. The memories 200 are used to store computer-executable instructions non-transitory; the processors 201 are used to run the computer-executable instructions, which, when run by the processors 201, can cause the processors 201 to perform one or more steps in the laboratory area division method using a decision tree model according to any embodiment of this application.

[0100] For the specific implementation and explanation of each step of the laboratory area partitioning method using the decision tree model, please refer to the relevant content in the above-described embodiment of the laboratory area partitioning method using the decision tree model, which will not be repeated here. It should be noted that... Figure 5 The components of the data control device 20 shown are merely exemplary and not limiting. The data control device 20 may have other components depending on the actual application requirements.

[0101] In one embodiment, the processor 201 and the memory 200 can communicate directly or indirectly with each other. For example, the processor 201 and the memory 200 can communicate via a network connection. The network can include wireless networks, wired networks, and / or any combination of wireless and wired networks; this application does not limit the type and function of the network. Alternatively, the processor 201 and the memory 200 can also communicate via a bus connection. The bus can be a Peripheral Component Interconnect Standard (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. For example, the processor 201 and the memory 200 can be located at a remote data server (cloud) or a distributed energy system (local), or at a client (e.g., a mobile device such as a mobile phone). For example, the processor 201 can be a central processing unit (CPU), a tensor processor (TPU), or a graphics processing unit (GPU), etc., with data processing and / or instruction execution capabilities, and can control other components in the data control device 20 to perform desired functions. The central processing unit (CPU) can be an x86 or ARM architecture, etc.

[0102] In one embodiment, memory 200 may include any combination of one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, erasable programmable read-only memory (EPROM), portable compact disc read-only memory (CD). ROM, USB memory, flash memory, etc. One or more computer-executable instructions can be stored on the computer-readable storage medium, and the processor 201 can execute the computer-executable instructions to implement various functions of the data control device 20. Various application programs and various data, as well as various data used and / or generated by the application programs, can also be stored in the memory 200.

[0103] It should be noted that the data control device 20 can achieve similar technical effects to the aforementioned laboratory area division method using decision tree models, and the repetitions will not be repeated.

[0104] At least one embodiment of this application also provides a non-transitory computer-readable storage medium. Figure 6 This is a schematic diagram of a non-transitory computer-readable storage medium provided for at least one embodiment of this application. For example, such as... Figure 6As shown, one or more computer-executable instructions 301 may be stored non-transitory on the non-transitory computer-readable storage medium 30. For example, when the computer-executable instructions 301 are executed by a computer, they may cause the computer to perform one or more steps in a laboratory area division method using a decision tree model according to any embodiment of this application.

[0105] In one embodiment, the non-transitory computer-readable storage medium 30 can be applied to the data control device 20 described above, for example, it can be the memory 200 in the data control device 20.

[0106] In one embodiment, the description of the non-transitory computer-readable storage medium 30 can be found in the description of the memory 200 in the embodiment of the data control device 20, and will not be repeated hereafter.

[0107] It should be noted that the memory 200 stores different non-transient computer-executable instructions, and the data control device 20 corresponds to the firmware upgrade device. When the computer-executable instructions are executed by the processor 201, the processor 201 can perform one or more steps in the laboratory area division method using a decision tree model according to any embodiment of this application.

[0108] The following points should be noted regarding this application:

[0109] (1) The accompanying drawings of the embodiments of this application only involve the structures involved in the embodiments of this application. Other structures can be referred to the general design.

[0110] (2) For clarity, the thickness and dimensions of layers or structures are enlarged in the accompanying drawings used to describe embodiments of the invention. It will be understood that when an element such as a layer, film, region, or substrate is referred to as being “above” or “below” another element, the element may be “directly” located “above” or “below” the other element, or there may be intermediate elements present.

[0111] (3) Where there is no conflict, the embodiments and features in the embodiments of this application can be combined with each other to obtain new embodiments. The above are only specific implementations of this application, but the protection scope of this application is not limited thereto, and the protection scope of this application shall be determined by the protection scope of the claims.

[0112] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0113] The above embodiments merely illustrate several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A laboratory area partitioning method using a decision tree model, characterized by, The method comprises the steps of: performing feature selection on the laboratory equipment data and the laboratory personnel data through a feature processing model to obtain data features; performing dimension reduction processing on the data features to remove redundant features in the data features and obtain effective data features; inputting the effective data features into the feature processing model to back-propagate laboratory equipment data and laboratory personnel data used as training samples; wherein the feature processing model is selected from a high-performance feature selection framework based on XGBoost; obtaining laboratory equipment data and laboratory personnel data stored in a cloud platform, and labeling corresponding laboratory area units for the laboratory equipment data and the laboratory personnel data by using a decision tree model; training a region classification model by taking the laboratory equipment data and the laboratory personnel data as training samples and taking the laboratory area units as result samples; inputting the latest laboratory equipment data and laboratory personnel data into the region classification model to output laboratory area unit data; generating a laboratory area map according to a similarity matrix and analyzing the similarity of the laboratory area unit data, comprising the steps of: performing adjacent region remodeling according to the similarity to obtain a preliminary map; performing spatial optimization based on the laboratory area map to obtain a laboratory area division map for representing laboratory area division, comprising the steps of: optimizing the boundary of the preliminary map by a boundary optimization algorithm to reduce boundary fragmentation; The boundary after being processed by the boundary optimization algorithm As follows: ； wherein, represents a boundary calibration point; represents a position of the i-th boundary calibration point; is the total number of boundary calibration points; is a bandwidth, which determines the smoothness of the boundary function; is a boundary smoothing function. 2.The laboratory region division method using a decision tree model according to claim 1, characterized in that, The process of obtaining laboratory equipment data and laboratory personnel data stored in a cloud platform and labeling corresponding laboratory area units for the laboratory equipment data and the laboratory personnel data by using a decision tree model comprises the steps of: determining laboratory region classification information of the laboratory equipment data and the laboratory personnel data according to the decision tree model; annotating the laboratory region classification information on the partition unit to obtain the laboratory area unit. 3.The laboratory region division method using a decision tree model according to claim 1, characterized in that, The region classification model is a deep learning framework; The process of training a region classification model by taking the laboratory equipment data and the laboratory personnel data as training samples and taking the laboratory area units as result samples comprises the steps of: strengthening the training samples and the result samples by using gradient weighted class activation mapping; improving the visualization degree of the region classification model outputting laboratory area unit data according to the result samples and the training samples. 4.The laboratory region division method using a decision tree model according to claim 1, characterized in that, The process of performing spatial optimization based on the laboratory area map to obtain a laboratory area division map for representing laboratory area division further comprises the steps of: performing normalization processing on the laboratory area unit data, and dividing groups according to the normalization processing result; merging the regions of the laboratory area unit data of the same group to obtain the laboratory area division map.

5. A laboratory area partitioning apparatus using a decision tree model, characterized by, The method comprises the steps of: performing feature selection on the laboratory equipment data and the laboratory personnel data through a feature processing model to obtain data features; performing dimension reduction processing on the data features to remove redundant features in the data features and obtain effective data features; The effective data features are input into the feature processing model, and laboratory equipment data and laboratory personnel data used as training samples are back-propagated; wherein the feature processing model selects a high-performance feature selection framework based on XGBoost; The data calibration module is configured to obtain laboratory equipment data and laboratory personnel data stored in the cloud platform, and calibrate corresponding laboratory area units for the laboratory equipment data and laboratory personnel data by using a decision tree model; The module training module is configured to train an area classification model by taking the laboratory equipment data and laboratory personnel data as training samples and taking the laboratory area units as result samples; The data reconstruction module is configured to obtain the latest laboratory equipment data and laboratory personnel data, input the laboratory equipment data and laboratory personnel data into the area classification model, and output laboratory area unit data; The map generation module is configured to generate a laboratory area map by analyzing the similarity of the laboratory area unit data according to a similarity matrix, including the steps of: remodeling adjacent areas according to the similarity to obtain a preliminary map; The map optimization module is configured to perform spatial optimization based on the laboratory area map to obtain a laboratory area division map for representing laboratory area division, including the steps of: optimizing the boundary of the preliminary map by a boundary optimization algorithm to reduce boundary fragmentation; The boundary after being processed by the boundary optimization algorithm As follows: ； wherein, represents a boundary calibration point; represents a position of the i-th boundary calibration point; is the total number of boundary calibration points; is a bandwidth, which determines the smoothness of the boundary function; is a boundary smoothing function.

6. A non-transitory computer-readable storage medium, comprising: A non-transitory computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the laboratory area division method using a decision tree model according to any one of claims 1 to 4.

7. A data control device, characterized by comprising: Comprise: one or more memories, non-transitory storage of computer-executable instructions; one or more processors configured to run computer-executable instructions, wherein the computer-executable instructions are executed by one or more processors to implement the laboratory area division method using a decision tree model according to any one of claims 1 to 4.

Images