Production management system and method for leprocaine cream

Through microscope acquisition and image analysis technology, the particle size distribution of Lipin doublecaine cream is automatically detected, which solves the problem of subjectivity and low efficiency of traditional detection methods, realizes rapid and accurate quality detection of cream, and improves production management Efficiency and quality control.

CN117530918BActive Publication Date: 2024-11-15JINGSHI (HANGZHOU) PHARM CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311555443.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-11-21
Publication Date
2024-11-15
Estimated Expiration
2043-11-21

AI Technical Summary

Technical Problem

The traditional quality detection method of lepradiocane cream relies on manual observation and optical microscopy, which has problems of subjectivity and low efficiency, resulting in inconsistent results and poor repeatability, making it difficult to meet the needs of large-scale production.

Method used

Microscope is used to collect microscope images of cream samples, and through image processing and analysis algorithms, it automatically detects whether the particle size distribution meets the predetermined standards, improving the accuracy and efficiency of the detection.

Benefits of technology

The rapid, accurate and objective quality testing of Riptyrocaine cream has been achieved, production management efficiency and quality control have been optimized, and the influence of human factors has been reduced.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117530918B_ABST
    Figure CN117530918B_ABST
Patent Text Reader

Abstract

The invention discloses a production management system and method for a leprocaine cream, wherein for the prepared leprocaine cream, a leprocaine cream sample is taken from the leprocaine cream and dotted on a glass slide, and n-decane is dripped on the surface of the leprocaine cream sample, and after covering with a cover glass, observation and quality inspection are performed under a microscope. In this way, the production management efficiency and quality of the leprocaine cream can be optimized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent production management, and in particular to a production management system and method for a levocaine cream. Background Art

[0002] Leprocaine is a local anesthetic that can be used for anesthesia of the skin, mucous membranes and nerves. Leprocaine cream is an external preparation that can be used to treat skin diseases such as pain, itching and inflammation. The production management method of Leprocaine cream involves the dissolution, emulsification, stirring, filling and sterilization of Leprocaine. In order to ensure product quality, quality inspection of Leprocaine cream is also required.

[0003] The quality inspection method of leprocaine cream is mainly to judge its stability and uniformity by observing the particle size distribution of leprocaine cream samples. However, the traditional particle size distribution detection method is carried out by manual visual inspection or optical microscope, which not only requires a lot of human resources and time, but also has subjective problems. Different operators may have different observation and judgment standards, resulting in inconsistent results. In addition, the traditional quality inspection method needs to observe and judge samples one by one, which is inefficient. Especially in large-scale production, the quality inspection process may become a bottleneck of production. In addition, due to the influence of human factors, the repeatability of the traditional quality inspection method is poor, and the same batch of samples may obtain different quality inspection results at different times or under different operators.

[0004] Therefore, an optimized production management plan for leprocaine cream is desired. Summary of the invention

[0005] The embodiment of the present invention provides a production management system and method for a leprocaine cream, wherein for the prepared leprocaine cream, a leprocaine cream sample is taken from the leprocaine cream and applied on a glass slide, and n-decane is dripped on the surface of the leprocaine cream sample, and after covering with a cover glass, observation and quality inspection are performed under a microscope. In this way, the production management efficiency and quality of the leprocaine cream can be optimized.

[0006] The embodiment of the present invention also provides a production management method of levocaine cream, which comprises:

[0007] Collecting raw materials, wherein the raw materials include leprocaine, an emulsifier, a stabilizer and a preservative;

[0008] Dissolving the leprocaine in water, heating to boiling, and cooling to room temperature to obtain a leprocaine solution;

[0009] The emulsifier, the stabilizer and the preservative are mixed in a predetermined ratio, heated to boiling and then cooled to room temperature to obtain an emulsified base;

[0010] The leprocaine solution and the emulsifying base are mixed in a predetermined ratio, and stirred with a high-speed stirrer to obtain a leprocaine cream;

[0011] Take a sample of the reprocaine cream from the reprocaine cream and apply it on a glass slide, add n-decane on the surface of the reprocaine cream sample, cover it with a cover glass, and observe and inspect it under a microscope;

[0012] The qualified leprocaine cream is filled into a sterile soft tube or can, and sealed and sterilized to obtain a finished leprocaine cream.

[0013] The embodiment of the present invention also provides a production management system for leprocaine cream, which includes:

[0014] A raw material collection module, used for collecting raw materials, wherein the raw materials include leprocaine, an emulsifier, a stabilizer and a preservative;

[0015] A levocaine solution generating module, used for dissolving the levocaine in water, heating the water to boiling, and cooling the water to room temperature to obtain a levocaine solution;

[0016] An emulsified matrix generation module, used for mixing the emulsifier, the stabilizer and the preservative in a predetermined ratio, heating them to boiling and then cooling them to room temperature to obtain an emulsified matrix;

[0017] A levocaine cream preparation module is used to mix the levocaine solution and the emulsifying base in a predetermined ratio, and stir them with a high-speed stirrer to obtain the levocaine cream;

[0018] An observation and quality inspection module, used for taking a sample of the relabicaine cream from the relabicaine cream and applying it on a glass slide, and dripping n-decane on the surface of the relabicaine cream sample, covering it with a cover slip, and then observing and inspecting it under a microscope;

[0019] The finished product production module of the leprocaine cream is used to fill the leprocaine cream that has passed the quality inspection into a sterile soft tube or can, and perform sealing and sterilization to obtain the finished product of the leprocaine cream. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0021] Figure 1 The present invention provides a flowchart of a production management method of a levocaine cream according to an embodiment of the present invention.

[0022] Figure 2 The present invention is a schematic diagram of a system architecture of a production management method for a leprocaine cream provided in an embodiment of the present invention.

[0023] Figure 3 The present invention provides a block diagram of a production management system for a levocaine cream according to an embodiment of the present invention.

[0024] Figure 4 This is an application scenario diagram of a production management method for leprocaine cream provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0026] Unless otherwise specified, all technical and scientific terms used in the embodiments of the present application have the same meaning as those commonly understood by those skilled in the art of the present application. The terms used in this application are only for the purpose of describing specific embodiments and are not intended to limit the scope of this application.

[0027] In the embodiments of the present application, it should be noted that, unless otherwise specified and limited, the term "connection" should be understood in a broad sense. For example, it can be an electrical connection or a connection between two components. It can be a direct connection or an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0028] It should be noted that the terms "first\second\third" involved in the embodiments of the present application are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that the specific order or sequence of "first\second\third" can be interchanged where permitted. It should be understood that the objects distinguished by "first\second\third" can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0029] The quality inspection methods of leprocaine cream can be introduced from multiple aspects, including physical properties, chemical composition and microbial contamination. Physical property inspection includes: particle size distribution inspection. The traditional method is to observe the size and distribution of particles in the sample by visual inspection or optical microscope. Modern methods can use laser particle size analysis, dynamic light scattering technology, image analysis technology, etc. to measure and analyze particle size distribution. Viscosity determination, using a viscometer to measure the viscosity of leprocaine cream to evaluate its fluidity and viscosity. pH value determination, using a pH meter to measure the acidity and alkalinity of leprocaine cream to determine its applicability and stability.

[0030] Chemical component testing includes: drug content determination, using analytical techniques such as high performance liquid chromatography (HPLC) or gas chromatography (GC) to determine the content of active ingredients (lidocaine and procaine) in leprocaine cream to ensure that it meets the specified standards. Excipient component determination, through chemical analysis methods, determine the composition and content of excipients in leprocaine cream, including emulsifiers, preservatives, stabilizers, etc.

[0031] Microbial contamination testing includes: total colony count, using the colony count method to test the total number of microorganisms in the leprocaine cream to assess its microbial contamination. Pathogen detection, using culture and separation techniques to detect whether there are pathogenic bacteria in the leprocaine cream, such as Escherichia coli and Staphylococcus aureus.

[0032] In addition to the above detection methods, other related properties can also be tested according to specific needs, such as appearance inspection, solubility determination, stability test, residual solvent detection, etc.

[0033] There are some defects in the traditional quality inspection methods of leprocaine cream, including: some of the tests in the traditional methods rely on human observation and judgment, such as visual inspection of particle size and distribution, which are highly subjective to the results and are easily affected by subjective factors of operators, resulting in inconsistency and inaccuracy of the results. Some of the tests in the traditional methods require a lot of time and manpower, such as visual inspection of particle distribution and manual measurement of viscosity, which limits the efficiency of the inspection and the speed of the production line. Traditional methods usually require multiple steps and complex operation procedures. For large-scale production or high-throughput scenarios, the efficiency is low and cannot meet the needs of rapid detection and efficient production. Some test results in traditional methods may be affected by factors such as environmental conditions, operating skills and equipment differences, resulting in differences in results between different laboratories or different operators, and poor repeatability. Some tests in traditional methods can only provide limited information, such as visual inspection can only observe the size and distribution of particles, and cannot provide more detailed particle size distribution and morphology information.

[0034] In one embodiment of the present invention, Figure 1 Flow chart of a production management method of a levocaine cream provided in an embodiment of the present invention. Figure 1 As shown, the production management method of the leprocaine cream according to an embodiment of the present invention includes: 110, collecting raw materials, wherein the raw materials include leprocaine, an emulsifier, a stabilizer and a preservative; 120, dissolving the leprocaine in water, heating it to boiling, and then cooling it to room temperature to obtain a leprocaine solution; 130, mixing the emulsifier, the stabilizer and the preservative in a predetermined proportion, heating them to boiling and then cooling them to room temperature to obtain an emulsified base; 140, mixing the leprocaine The solution and the emulsified matrix are mixed in a predetermined ratio, and stirred with a high-speed stirrer to obtain a leprocaine cream; 150, a leprocaine cream sample is taken from the leprocaine cream and applied on a glass slide, and n-decane is dripped on the surface of the leprocaine cream sample, and a cover glass is added to observe and inspect the quality under a microscope; 160, the leprocaine cream that passes the quality inspection is filled into a sterile hose or can, and sealed and sterilized to obtain a finished leprocaine cream.

[0035] In view of the above technical problems, in the production process of the leprocaine cream, for the prepared leprocaine cream, a leprocaine cream sample is taken from the leprocaine cream and dotted on a glass slide, and n-decane is dripped on the surface of the leprocaine cream sample, and a cover glass is added to observe and inspect under a microscope. Specifically, in order to avoid the defects caused by traditional manual inspection, the technical concept of the present application is to collect the microscopic image of the leprocaine cream sample through a microscope, and then introduce an image processing and analysis algorithm at the back end to analyze the microscopic image of the leprocaine cream sample, so as to automatically detect and judge whether the particle size distribution of the leprocaine cream sample meets the predetermined standard, thereby realizing rapid, accurate and objective quality inspection of the leprocaine cream, so as to improve the accuracy and efficiency of quality inspection, and optimize the production management efficiency and quality of the leprocaine cream.

[0036] Figure 2 Schematic diagram of the system architecture of a production management method of a leprocaine cream provided in an embodiment of the present invention. Figure 2 As shown, a leprocaine cream sample is extracted from the leprocaine cream and dotted on a glass slide, and n-decane is dripped on the surface of the leprocaine cream sample, and a coverslip is covered and then observed and inspected under a microscope, including: first, a microscopic image of the leprocaine cream sample collected by the microscope is obtained; then, a local area feature analysis is performed on the microscopic image of the leprocaine cream sample to obtain a sequence of semantic feature vectors of the granularity of the microscopic image blocks of the leprocaine cream sample; then, a correlation semantic analysis is performed on any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors to obtain a granularity global correlation topological feature; finally, based on the granularity global correlation topological feature, it is determined whether the particle size distribution meets the predetermined standard.

[0037] First, obtain the microscopic image of the leprocaine cream sample, select the appropriate microscope and image acquisition equipment to ensure the acquisition of clear and high-quality microscopic images. Through the microscopic image, the particle morphology, size, and distribution information in the leprocaine cream sample can be observed. Then, the microscopic image is processed and segmented to divide the image into small blocks, and the local features of each image block, such as particle size and shape, are extracted. Through local area feature analysis, the granularity semantic feature vector sequence of each image block can be obtained, and these feature vectors reflect the granularity information of different regions in the sample.

[0038] Next, any two feature vectors in the image block granularity semantic feature vector sequence are subjected to correlation analysis, and correlation coefficients or other correlation measurement methods can be used. Through correlation semantic analysis, the global correlation topological features of granularity, that is, the granularity correlation between different image blocks, can be obtained. These features can reveal the global particle size distribution in the sample. Finally, according to the predetermined particle size distribution standard, the consistency of the global correlation topological features of granularity with the standard can be compared, and statistical methods or machine learning algorithms can be used for judgment. By determining whether the particle size distribution meets the predetermined standard, the quality of the leprocaine cream sample can be evaluated, and possible problems can be discovered and resolved in a timely manner. In this way, more detailed and comprehensive particle size distribution information can be provided to help pharmaceutical companies control quality and optimize production processes.

[0039] Specifically, in the technical solution of the present application, first, a microscopic image of a leprocaine cream sample collected by a microscope is obtained. Next, considering that the microscopic image of the leprocaine cream sample contains a large amount of detail information, and these detail information are particularly important for the detection of the uniformity of the particle size distribution of the leprocaine cream sample. Therefore, in the technical solution of the present application, the microscopic image of the leprocaine cream sample is further subjected to image block processing to obtain a sequence of microscopic image blocks of the leprocaine cream sample. By subjecting the microscopic image of the leprocaine cream sample to image block processing, the detailed features of the local area of ​​each image, including the size, shape and distribution of the particles, etc., can be better extracted, which is conducive to the detection of the particle size distribution of the leprocaine cream sample.

[0040] In a specific embodiment of the present application, local area feature analysis is performed on the microscopic image of the leprocaine cream sample to obtain a sequence of granularity semantic feature vectors of the microscopic image blocks of the leprocaine cream sample, including: performing image block processing on the microscopic image of the leprocaine cream sample to obtain a sequence of microscopic image blocks of the leprocaine cream sample; and performing feature extraction on the sequence of microscopic image blocks of the leprocaine cream sample by a granularity feature extractor based on a deep neural network model to obtain a sequence of granularity semantic feature vectors of the microscopic image blocks of the leprocaine cream sample.

[0041] Among them, the deep neural network model is a convolutional neural network model.

[0042] Then, the sequence of the microscopic image blocks of the leprocaine cream sample is subjected to feature mining in a granularity feature extractor based on a convolutional neural network model to extract the detailed implicit feature distribution information about the leprocaine cream sample in each microscopic image block of the leprocaine cream sample, thereby obtaining a sequence of granularity semantic feature vectors of the microscopic image blocks of the leprocaine cream sample.

[0043] Further, considering that the image blocks of each local area in the microscopic image of the leprocaine cream sample have a global correlation relationship based on the whole, this correlation relationship is crucial for the detection of particle size distribution. In other words, the particles in the leprocaine cream sample are often not isolated, they may aggregate, disperse or form a certain arrangement structure, and the quality of the leprocaine cream sample requires that the particles are evenly distributed to avoid local over-aggregation or over-dispersion. In addition, it is also considered that if the correlation between the particle size distribution characteristics of the leprocaine cream sample in each local area in the microscopic image of the leprocaine cream sample is high, it means that the uniformity of the particle size is high. Therefore, in order to further improve the accuracy of the particle size distribution detection of the leprocaine cream sample, in the technical solution of the present application, the correlation between any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors is calculated to obtain a granularity global correlation topological matrix. By calculating the correlation between any two leprocaine cream sample microscopic image block granularity semantic feature vectors, the correlation between the particle feature distribution of the leprocaine cream sample in each local area of ​​the image can be revealed, including the degree of aggregation, the degree of dispersion, and the arrangement regularity. This helps to understand the overall distribution of the leprocaine cream sample particles, as well as the interaction and uniformity between the distribution features of the leprocaine cream sample in each image block.

[0044] In a specific embodiment of the present application, a correlation semantic analysis is performed on any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors to obtain a granularity global correlation topological feature, including: calculating the correlation between any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors to obtain a granularity global correlation topological matrix; passing the granularity global correlation topological matrix through a topological feature extractor based on a convolutional neural network model to obtain a granularity global correlation topological feature matrix as the granularity global correlation topological feature.

[0045] Specifically, calculating the correlation between any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors to obtain a granularity global correlation topological matrix, including: calculating the correlation between any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors using the following correlation formula; wherein the correlation formula is: in, is the previous leprocaine cream sample microscopic image block granularity semantic feature vector of any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors, is the previous leprocaine cream sample microscopic image block granularity semantic feature vector of any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors, and are two different linear transformations, It is the correlation between the granularity semantic feature vector of the previous microscopic image block of the relabivacaine cream sample and the granularity semantic feature vector of the next microscopic image block of the relabivacaine cream sample.

[0046] Next, the particle size global correlation topological matrix is ​​subjected to feature mining in a topological feature extractor based on a convolutional neural network model to extract the correlation topological feature information between the distribution characteristics of the leprocaine cream sample particles in each leprocaine cream sample microscopic image block, thereby obtaining a particle size global correlation topological feature matrix.

[0047] Then, the particle size global correlation topological feature matrix is ​​passed through a classifier to obtain a classification result, and the classification result is used to indicate whether the particle size distribution meets the predetermined standard. That is, the correlation topological association feature information between the particle distribution features of the leprocaine cream sample in each local area in the microscopic image of the leprocaine cream sample is used for classification processing, so as to automatically detect and judge whether the particle size distribution of the leprocaine cream sample meets the predetermined standard, thereby realizing rapid, accurate and objective quality detection of the leprocaine cream.

[0048] In a specific embodiment of the present application, determining whether the particle size distribution meets the predetermined standard based on the particle size global correlation topological feature includes: passing the particle size global correlation topological feature matrix through a classifier to obtain a classification result, and the classification result is used to indicate whether the particle size distribution meets the predetermined standard.

[0049] In one embodiment of the present application, the production management method of the levocaine cream further includes a training step for training the granularity feature extractor based on the convolutional neural network model, the topological feature extractor based on the convolutional neural network model, and the classifier. The training step comprises: obtaining a microscopic image of a training leprocaine cream sample collected by the microscope; performing local area feature analysis on the microscopic image of the training leprocaine cream sample to obtain a sequence of semantic feature vectors of granularity of the microscopic image block of the training leprocaine cream sample; calculating the correlation between any two semantic feature vectors of granularity of the microscopic image block of the training leprocaine cream sample in the sequence of semantic feature vectors of granularity of the microscopic image block of the training leprocaine cream sample to obtain a training granularity global correlation topological matrix; passing the training granularity global correlation topological matrix through a topological feature extractor based on a convolutional neural network model to obtain a training granularity global correlation topological feature matrix; performing position-by-position feature value optimization on the training granularity global correlation topological feature matrix to obtain an optimized training granularity global correlation topological feature matrix; passing the optimized training granularity global correlation topological feature matrix through a classifier to obtain a classification loss function value; and training the granularity feature extractor based on the convolutional neural network model, the topological feature extractor based on the convolutional neural network model, and the classifier based on the classification loss function value.

[0050] In particular, in the technical solution of the present application, each training leprocaine cream sample microscopic image block granularity semantic feature vector in the sequence of training leprocaine cream sample microscopic image block granularity semantic feature vectors expresses the image semantic features in the local image source semantic space domain determined by the global image source semantic space domain through image segmentation, and considering the uneven distribution of image source semantics in each local image source semantic space domain under the global image source semantic space domain, the image semantic features in the local image source semantic space domain also have uneven correlation, so that the training granularity global correlation topological matrix obtained by calculating the correlation between any two training leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of training leprocaine cream sample microscopic image block granularity semantic feature vectors has subspace distribution differences, and the training granularity global correlation topological matrix is ​​passed through a topological feature extractor based on a convolutional neural network model, and the training granularity global correlation topological feature matrix obtained will further increase the subspace distribution differences on the basis of extracting local correlation features of spatial distribution.

[0051] Furthermore, considering that the difference in feature subspace distribution will bring about local feature distribution sparsification to the overall feature representation of the training granularity global correlation topological feature matrix, that is, the sparse submanifold outside the distribution relative to the overall high-dimensional feature manifold, this will result in poor convergence of the training granularity global correlation topological feature matrix to the predetermined regression probability representation in the probability space when the training granularity global correlation topological feature matrix is ​​mapped to a class probability through a classifier, thereby affecting the accuracy of the classification results.

[0052] Therefore, preferably, the training granularity global correlation topological feature matrix is ​​optimized by positional eigenvalues, specifically: the training granularity global correlation topological feature matrix is ​​optimized by positional eigenvalues ​​according to the following optimization formula to obtain an optimized training granularity global correlation topological feature matrix; wherein the optimization formula is: in, is the training granularity global correlation topological feature matrix The characteristic value of is the eigenvalue of the global correlation topological feature matrix of the optimized training granularity, Represents calculation of the natural exponential function raised to a value.

[0053] That is, the sparse distribution in the high-dimensional feature space is processed by regularization based on heavy probability to activate the training granularity global correlation topological feature matrix The natural distribution transfer from the geometric manifold in the high-dimensional feature space to the probability space is achieved by the global correlation topological feature matrix of the training granularity. The distributed sparse submanifold of the high-dimensional feature manifold is subjected to a smoothing regularization method based on re-probability to improve the convergence of the complex high-dimensional feature manifold with high spatial sparsity under the predetermined regression probability distribution, thereby improving the training granularity global correlation topological feature matrix The accuracy of the classification results obtained by the classifier. In this way, it is possible to automatically detect and judge whether the particle size distribution of the leprocaine cream sample meets the predetermined standard based on the analysis of the microscopic image of the leprocaine cream sample, thereby achieving rapid, accurate and objective quality detection of the leprocaine cream, so as to improve the accuracy and efficiency of quality inspection and optimize the production management efficiency and quality of the leprocaine cream.

[0054] In summary, the production management method of the leprocaine cream according to the embodiment of the present invention is explained. After collecting the microscopic image of the leprocaine cream sample through a microscope, an image processing and analysis algorithm is introduced at the back end to analyze the microscopic image of the leprocaine cream sample, so as to automatically detect and judge whether the particle size distribution of the leprocaine cream sample meets the predetermined standard, thereby realizing rapid, accurate and objective quality detection of the leprocaine cream, so as to improve the accuracy and efficiency of quality inspection, and optimize the production management efficiency and quality of the leprocaine cream.

[0055] Figure 3 FIG. 4 is a block diagram of a production management system of a levocaine cream provided in an embodiment of the present invention. Figure 3 As shown, a production management system 200 of a leprocaine cream comprises: a raw material collection module 210, for collecting raw materials, wherein the raw materials include leprocaine, an emulsifier, a stabilizer and a preservative; a leprocaine solution generation module 220, for dissolving the leprocaine in water, heating it to boiling, and then cooling it to room temperature to obtain a leprocaine solution; an emulsified matrix generation module 230, for mixing the emulsifier, the stabilizer and the preservative in a predetermined proportion, heating them to boiling and then cooling them to room temperature to obtain an emulsified matrix; a leprocaine cream generation module 240, for mixing the emulsifier, the stabilizer and the preservative in a predetermined proportion, heating them to boiling and then cooling them to room temperature to obtain an emulsified matrix; The leprocaine solution and the emulsifying matrix are mixed in a predetermined ratio and stirred with a high-speed stirrer to obtain a leprocaine cream; an observation and quality inspection module 250 is used to extract a leprocaine cream sample from the leprocaine cream, apply it on a glass slide, and drop n-decane on the surface of the leprocaine cream sample, cover it with a cover glass, and observe and inspect it under a microscope; a leprocaine cream finished product production module 260 is used to fill the leprocaine cream that has passed the quality inspection into a sterile hose or can, and seal and sterilize it to obtain a leprocaine cream finished product.

[0056] As described above, the production management system 200 of the leprocaine cream according to the embodiment of the present invention can be implemented in various terminal devices, such as a server for production management of the leprocaine cream, etc. In one example, the production management system 200 of the leprocaine cream according to the embodiment of the present invention can be integrated into the terminal device as a software module and / or a hardware module. For example, the production management system 200 of the leprocaine cream can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the production management system 200 of the leprocaine cream can also be one of the many hardware modules of the terminal device.

[0057] Alternatively, in another example, the production management system 200 of the leprocaine cream and the terminal device may also be separate devices, and the production management system 200 of the leprocaine cream may be connected to the terminal device via a wired and / or wireless network, and transmit interactive information in accordance with an agreed data format.

[0058] Those skilled in the art will appreciate that the specific operations of each step in the above-mentioned production management system of the levocaine cream have been described in the above reference. Figure 1 to Figure 2 The production management method of the levocaine cream has been described in detail, and therefore, its repeated description will be omitted.

[0059] Figure 4 FIG. 1 is an application scenario diagram of a production management method of a levocaine cream provided in an embodiment of the present invention. Figure 4 As shown, in this application scenario, first, a microscopic image of a levocaine cream sample collected by the microscope is obtained (for example, Figure 4 Then, the obtained microscopic image of the leprocaine cream sample is input into a server (for example, Figure 4 In S) as shown in , the server is capable of processing the microscopic image of the leprocaine cream sample based on the production management algorithm of the leprocaine cream to determine whether the particle size distribution meets the predetermined standard.

[0060] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A production management method for levocaine cream, characterized in that: include: Collecting raw materials, wherein the raw materials include leprocaine, an emulsifier, a stabilizer and a preservative; Dissolving the leprocaine in water, heating to boiling, and cooling to room temperature to obtain a leprocaine solution; The emulsifier, the stabilizer and the preservative are mixed in a predetermined ratio, heated to boiling and then cooled to room temperature to obtain an emulsified base; The leprocaine solution and the emulsifying base are mixed in a predetermined ratio, and stirred with a high-speed stirrer to obtain a leprocaine cream; Take a sample of the reprocaine cream from the reprocaine cream and apply it on a glass slide, add n-decane on the surface of the reprocaine cream sample, cover it with a cover glass, and observe and inspect it under a microscope; Filling the qualified leprocaine cream into a sterile soft tube or can, and sealing and sterilizing the can to obtain a finished leprocaine cream; Wherein, taking a sample of the leprocaine cream from the leprocaine cream and applying it on a glass slide, adding n-decane dropwise on the surface of the leprocaine cream sample, covering it with a cover slip, and observing and inspecting it under a microscope, including: Acquiring a microscopic image of the levocaine cream sample collected by the microscope; Performing local area feature analysis on the microscopic image of the leprocaine cream sample to obtain a sequence of semantic feature vectors of block granularity of the microscopic image of the leprocaine cream sample; Performing correlation semantic analysis on any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors to obtain a granularity global correlation topological feature; Based on the particle size global correlation topological feature, determining whether the particle size distribution meets a predetermined standard; The method of performing local area feature analysis on the microscopic image of the leprocaine cream sample to obtain a sequence of semantic feature vectors of block granularity of the microscopic image of the leprocaine cream sample comprises: Performing image block processing on the microscopic image of the leprocaine cream sample to obtain a sequence of microscopic image blocks of the leprocaine cream sample; Using a granularity feature extractor based on a deep neural network model, feature extraction is performed on the sequence of microscopic image blocks of the leprocaine cream sample to obtain a sequence of granularity semantic feature vectors of the microscopic image blocks of the leprocaine cream sample; Wherein, the deep neural network model is a convolutional neural network model; Among them, performing correlation semantic analysis on any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors to obtain granularity global correlation topological features, including: Calculating the correlation between any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors to obtain a granularity global correlation topological matrix; The granular global correlation topological matrix is ​​passed through a topological feature extractor based on a convolutional neural network model to obtain a granular global correlation topological feature matrix as the granular global correlation topological feature; The step of calculating the correlation between any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors to obtain a granularity global correlation topological matrix comprises: calculating the correlation between any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors using the following correlation formula; Wherein, the correlation formula is: ;in, is the previous leprocaine cream sample microscopic image block granularity semantic feature vector of any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors, is the next leprocaine cream sample microscopic image block granularity semantic feature vector of any two leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the leprocaine cream sample microscopic image block granularity semantic feature vectors, and are two different linear transformations, It is the correlation between the granularity semantic feature vector of the previous microscopic image block of the relabivacaine cream sample and the granularity semantic feature vector of the next microscopic image block of the relabivacaine cream sample.

2. The production management method of the levocaine cream according to claim 1, characterized in that: Determining whether the particle size distribution meets a predetermined standard based on the particle size global correlation topological feature includes: passing the particle size global correlation topological feature matrix through a classifier to obtain a classification result, and the classification result is used to indicate whether the particle size distribution meets the predetermined standard.

3. The production management method of the levocaine cream according to claim 2, characterized in that: It also includes a training step for training the granularity feature extractor based on the convolutional neural network model, the topological feature extractor based on the convolutional neural network model and the classifier.

4. The production management method of the levocaine cream according to claim 3, characterized in that: The training step comprises: acquiring a microscopic image of a training levocaine cream sample collected by the microscope; Performing local area feature analysis on the training leprocaine cream sample microscopic image to obtain a sequence of block granularity semantic feature vectors of the training leprocaine cream sample microscopic image; Calculating the correlation between any two training leprocaine cream sample microscopic image block granularity semantic feature vectors in the sequence of the training leprocaine cream sample microscopic image block granularity semantic feature vectors to obtain a training granularity global correlation topological matrix; Passing the training granularity global correlation topological matrix through a topological feature extractor based on a convolutional neural network model to obtain a training granularity global correlation topological feature matrix; Optimizing the position-by-position eigenvalues ​​of the training granularity global correlation topological feature matrix to obtain an optimized training granularity global correlation topological feature matrix; Passing the optimized training granularity global correlation topological feature matrix through a classifier to obtain a classification loss function value; The granularity feature extractor based on the convolutional neural network model, the topology feature extractor based on the convolutional neural network model, and the classifier are trained based on the classification loss function value.

5. A production management system for leprocaine cream according to the production management method of leprocaine cream according to claim 1, characterized in that: include: A raw material collection module, used for collecting raw materials, wherein the raw materials include leprocaine, an emulsifier, a stabilizer and a preservative; A levocaine solution generating module, used for dissolving the levocaine in water, heating the water to boiling, and cooling the water to room temperature to obtain a levocaine solution; An emulsified matrix generation module, used for mixing the emulsifier, the stabilizer and the preservative in a predetermined ratio, heating them to boiling and then cooling them to room temperature to obtain an emulsified matrix; A levocaine cream preparation module is used to mix the levocaine solution and the emulsifying base in a predetermined ratio, and stir them with a high-speed stirrer to obtain the levocaine cream; An observation and quality inspection module, used for taking a sample of the relabicaine cream from the relabicaine cream and applying it on a glass slide, and dripping n-decane on the surface of the relabicaine cream sample, covering it with a cover slip, and then observing and inspecting it under a microscope; The finished product production module of the leprocaine cream is used to fill the leprocaine cream that has passed the quality inspection into a sterile soft tube or can, and perform sealing and sterilization to obtain the finished product of the leprocaine cream.