Intelligent management system and method for bear gall powder storage environment
Through deep learning technology, the status and storage environment humidity of bear bile powder are analyzed, and whether the humidity needs to be adjusted is solved, which solves the problem of bear bile powder being easily damp, effectively preventing moisture and mold, and ensuring product quality and storage effect.
Patent Information
- Application Number
- CN202411054910.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-02
- Publication Date
- 2024-12-27
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Bear bile powder is easily dampened and causes the drug properties to weaken or deteriorate, affecting the efficacy of the drug. The prior art is difficult to effectively prevent it from getting damp and moldy.
By obtaining the status data of bear bile powder extracted by the database, the images collected by the camera and the storage environment humidity data collected by the sensor, using deep learning technology for feature extraction and correlation analysis, we can determine whether the storage environment humidity needs to be adjusted to prevent the bear bile powder from getting damp and get mouldy.
Effectively prevent bear bile powder from getting damp and moldy, reduce production costs, ensure product quality, and improve storage effect and shelf life.
Smart Images
Figure CN119206601A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of storage environment management, and more specifically, to an intelligent management system and method for the storage environment of bear bile powder. Background Art
[0002] Bear bile powder is a precious Chinese medicinal material and is often used in traditional Chinese medicine. Its effects include clearing away heat and detoxifying, reducing swelling and relieving pain, etc. It is widely used to treat fever, inflammation and other diseases. It has a fine texture, is yellow-white in color, has a bitter taste, and is usually made into medicine or ointment. In traditional Chinese medicine concepts, bear bile powder is regarded as a precious medicinal material with important medicinal value.
[0003] Bear bile powder is a precious Chinese medicinal material with fine texture and excellent efficacy, and is widely used in Chinese medicine treatment. However, bear bile powder easily absorbs moisture. Once it is damp, it may weaken the medicinal properties or even deteriorate, affecting the efficacy of the drug.
[0004] Therefore, an intelligent management system and method for the bear bile powder storage environment is desired. Summary of the invention
[0005] In order to solve the above technical problems, this application is proposed. The embodiment of this application provides a bear bile powder storage environment intelligent management system and method, which first obtains the bear bile powder status data extracted from the database, the bear bile powder image collected by the camera and the storage environment humidity data collected by the sensor, and then uses deep learning technology to perform feature extraction and association analysis on the three, and finally uses a classifier to determine whether the storage environment humidity needs to be adjusted. Timely adjustment of the storage environment humidity can effectively prevent the bear bile powder from getting damp, moldy and other problems, thereby reducing production costs and ensuring product quality.
[0006] According to one aspect of the present application, a bear bile powder storage environment intelligent management system is provided, which includes:
[0007] A bear bile powder storage data acquisition module is used to acquire the bear bile powder status data extracted from the database, the bear bile powder image collected by the camera, and the storage environment humidity data collected by the sensor;
[0008] A bear bile powder storage data extraction module, used to extract a bear bile powder storage state associated feature vector and a storage environment humidity feature vector from the bear bile powder state data extracted from the database, the bear bile powder image collected by the camera, and the storage environment humidity data collected by the sensor;
[0009] The storage environment humidity adjustment judgment module is used to judge whether the storage environment humidity needs to be adjusted based on the bear bile powder storage state associated feature vector and the storage environment humidity feature vector.
[0010] According to another aspect of the present application, a method for intelligent management of a bear bile powder storage environment is provided, comprising:
[0011] Obtain bear bile powder status data extracted from a database, bear bile powder images captured by a camera, and storage environment humidity data captured by a sensor;
[0012] Extracting a bear bile powder storage state associated feature vector and a storage environment humidity feature vector from the bear bile powder state data extracted from the database, the bear bile powder image collected by the camera, and the storage environment humidity data collected by the sensor;
[0013] Based on the bear bile powder storage state associated feature vector and the storage environment humidity feature vector, it is determined whether the storage environment humidity needs to be adjusted.
[0014] Compared with the prior art, the present application provides an intelligent management system and method for the storage environment of bear bile powder, which first obtains the bear bile powder status data extracted from the database, the bear bile powder image collected by the camera, and the storage environment humidity data collected by the sensor, and then uses deep learning technology to perform feature extraction and correlation analysis on the three, and finally uses a classifier to determine whether the storage environment humidity needs to be adjusted. Timely adjustment of the storage environment humidity can effectively prevent the bear bile powder from getting damp and moldy, thereby reducing production costs and ensuring product quality. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.
[0016] Figure 1 This is a block diagram of the bear bile powder storage environment intelligent management system according to an embodiment of the present application.
[0017] Figure 2 This is a block diagram of a bear bile powder storage data extraction module in the bear bile powder storage environment intelligent management system according to an embodiment of the present application.
[0018] Figure 3 This is a block diagram of a bear bile powder feature extraction unit in the bear bile powder storage environment intelligent management system according to an embodiment of the present application.
[0019] Figure 4 This is a block diagram of a storage environment humidity adjustment judgment module in a bear bile powder storage environment intelligent management system according to an embodiment of the present application.
[0020] Figure 5This is a flow chart of the intelligent management method of the bear bile powder storage environment according to an embodiment of the present application.
[0021] Figure 6 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0022] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.
[0023] Exemplary Systems
[0024] Figure 1 This is a block diagram of the intelligent management system for the bear bile powder storage environment of the embodiment of the present application. Figure 1 As shown, according to the embodiment of the present application, the intelligent management system 100 for the storage environment of bear bile powder includes: a bear bile powder storage data acquisition module 110, which is used to acquire the bear bile powder status data extracted from the database, the bear bile powder image collected by the camera and the storage environment humidity data collected by the sensor; a bear bile powder storage data extraction module 120, which is used to extract the bear bile powder storage status associated feature vector and the storage environment humidity feature vector from the bear bile powder status data extracted from the database, the bear bile powder image collected by the camera and the storage environment humidity data collected by the sensor; a storage environment humidity adjustment judgment module 130, which is used to judge whether the storage environment humidity needs to be adjusted based on the bear bile powder storage status associated feature vector and the storage environment humidity feature vector.
[0025] In the above-mentioned bear bile powder storage environment intelligent management system 100, the bear bile powder storage data acquisition module 110 is used to obtain the bear bile powder status data extracted from the database, the bear bile powder image collected by the camera and the storage environment humidity data collected by the sensor. It should be understood that bear bile powder, as a precious Chinese medicinal material, is highly respected by the Chinese medicine community. Its efficacy covers many aspects such as clearing away heat and detoxification, reducing swelling and relieving pain, and is often used to treat diseases such as fever and inflammation. It has a fine texture, is yellow-white in color, and has a bitter taste. It is often made into medicine or ointment. In the traditional Chinese medicine concept, bear bile powder is regarded as a precious medicinal material with important medicinal value. As a rare Chinese medicinal material, bear bile powder has a fine texture and significant efficacy, and is widely used in Chinese medicine treatment. However, bear bile powder is susceptible to moisture. Once it is damp, the medicinal properties may be weakened, or even corrupted and deteriorated, affecting the efficacy. Therefore, in the technical solution of the present application, by obtaining the bear bile powder status data extracted from the database, the bear bile powder image captured by the camera and the storage environment humidity data collected by the sensor, and combining with deep learning technology, it is judged whether the storage environment humidity needs to be adjusted, so as to effectively prevent the occurrence of problems such as moisture and mold of the bear bile powder.
[0026] Specifically, the bear bile powder status data extracted from the database contains important information such as historical storage status and change trends, which can be used to analyze the storage history of bear bile powder, identify potential problems and perform predictive maintenance. Such data provides a comprehensive understanding of the bear bile powder storage process and helps to formulate effective management strategies. The bear bile powder images collected by the camera can provide intuitive visual information, including the appearance characteristics and changes of the bear bile powder. This image information can be used to identify the status, quality and possible abnormalities of the bear bile powder, so as to take timely measures to adjust and manage it. The storage environment humidity data collected by the sensor is one of the key indicators for monitoring storage environment conditions. Considering that humidity is crucial to the preservation of bear bile powder, too high or too low humidity may affect the quality of bear bile powder. By monitoring humidity data in real time, the system can adjust the storage environment in time and keep it within an appropriate humidity range to ensure the quality and preservation effect of bear bile powder. In this way, the system can comprehensively monitor the status, appearance and storage environment conditions of bear bile powder, provide managers with timely and accurate information feedback, help them make scientific decisions, optimize the storage management of bear bile powder, and improve storage effect and shelf life.
[0027] In the above-mentioned bear bile powder storage environment intelligent management system 100, the bear bile powder storage data extraction module 120 is used to extract the bear bile powder storage state associated feature vector and the storage environment humidity feature vector from the bear bile powder state data extracted from the database, the bear bile powder image collected by the camera, and the storage environment humidity data collected by the sensor. It should be understood that extracting the bear bile powder storage state associated feature vector and the storage environment humidity feature vector from the bear bile powder state data extracted from the database, the bear bile powder image collected by the camera, and the storage environment humidity data collected by the sensor can comprehensively utilize the information from different data sources, and realize intelligent monitoring and management of the bear bile powder storage state and environmental humidity through feature extraction and association analysis. This comprehensive feature extraction method can improve the system's understanding and control of the bear bile powder storage environment, thereby improving storage effects and quality assurance, so as to more comprehensively and accurately monitor and evaluate the storage state and environmental conditions of bear bile powder, provide strong support for intelligent management decisions, and ensure the quality and preservation effect of bear bile powder.
[0028] Figure 2 FIG. 1 is a block diagram of a bear bile powder storage data extraction module in a bear bile powder storage environment intelligent management system according to an embodiment of the present application. Figure 2As shown, in a specific embodiment of the present application, the bear bile powder storage data extraction module 120 includes: a bear bile powder state semantic encoding unit 121, which is used to semantically encode the bear bile powder state data extracted from the database to obtain a global feature vector of the bear bile powder state; a bear bile powder feature extraction unit 122, which is used to extract features from the bear bile powder image collected by the camera to obtain a bear bile powder feature vector of interest; a bear bile powder storage state feature association unit 123, which is used to associate the bear bile powder state global feature vector with the bear bile powder feature vector of interest to obtain the bear bile powder storage state association feature vector; a storage environment humidity feature extraction unit 124, which is used to perform feature extraction on the storage environment humidity data collected by the sensor to obtain the storage environment humidity feature vector.
[0029] It should be understood that semantic coding can convert the bear bile powder status data in the database into a more semantically informative representation. By encoding the data, key features and patterns in the data can be extracted to better describe the storage status of the bear bile powder. Such an encoding process can help the system better understand the bear bile powder status data and extract potential information from it. The global feature vector of the bear bile powder status obtained through semantic coding can reduce the dimensionality of the data and retain important information of the data.
[0030] Furthermore, by performing feature extraction on the bear bile powder image captured by the camera, various visual features of the bear bile powder, such as color, texture, shape, etc., can be extracted from the image. These features can help the system distinguish bear bile powder in different states, identify possible abnormal situations, and take timely measures to deal with them. In this way, feature extraction of the bear bile powder image captured by the camera can extract the most representative and distinguishing features from the image data, so that the system can more accurately identify and describe the key features of the bear bile powder and realize the monitoring and management of its storage status. This feature vector can more intuitively reflect the appearance characteristics and morphological information of the bear bile powder, and provide more comprehensive data support for the system. Secondly, feature extraction can convert complex image data into high-dimensional feature vectors to realize information compression and extraction of bear bile powder images. Such a feature vector can better describe the characteristics of bear bile powder, provide the system with a more intuitive and accurate data representation, and help the system monitor and evaluate the status of bear bile powder.
[0031] Furthermore, combining the overall state characteristics and local visual features of bear bile powder can more comprehensively and accurately describe the storage state of bear bile powder, thereby comprehensively considering the overall and local characteristics of bear bile powder, providing the system with richer and multi-dimensional data support, and facilitating a more comprehensive and accurate analysis and management of the storage state of bear bile powder. Here, associating the global feature vector of the bear bile powder state with the feature vector of interest of bear bile powder can effectively integrate the overall state characteristics and local features of bear bile powder. The global feature vector reflects the overall state and storage history of bear bile powder, while the feature vector of interest extracts the key visual features in the bear bile powder image. By associating these two feature vectors, the overall state of bear bile powder can be combined with image features to more comprehensively describe the storage state of bear bile powder.
[0032] In particular, by extracting features from the storage environment humidity data collected by the sensor, key humidity features can be extracted from the data, such as average humidity, humidity fluctuation range, humidity change rate, etc. These features can help the system understand the humidity status of the storage environment, determine whether it meets the storage requirements of bear bile powder, and whether there are any abnormal humidity conditions.
[0033] In a specific embodiment of the present application, the bear bile powder status semantic coding unit 121 includes: passing the bear bile powder status data extracted from the database through a bear bile powder status text semantic coding model to obtain a plurality of bear bile powder status feature vectors; and splicing the plurality of bear bile powder status feature vectors to obtain the bear bile powder status global feature vector.
[0034] It should be understood that by processing the bear bile powder status data extracted from the database through the bear bile powder status text semantic encoding model, the original text data can be converted into high-dimensional semantic feature vectors. These feature vectors not only contain the basic information of the bear bile powder status data, but also contain the semantic associations and implicit information therein. In this way, the system can understand and describe the state changes and characteristics of the bear bile powder more comprehensively and accurately. Among them, each feature vector represents the representation of the bear bile powder status data in different semantic spaces, thereby providing the system with diversified feature information. This helps the system to capture the characteristics and change laws of the bear bile powder status data more comprehensively. Specifically, the bear bile powder status data extracted from the database is segmented to obtain a word sequence; the embedding layer of the bear bile powder status text semantic encoding model is used to map each word in the word sequence to a word embedding vector to obtain a sequence of word embedding vectors; the converter-based Bert model of the bear bile powder status text semantic encoding model is used to perform global context semantic encoding on the sequence of word embedding vectors to obtain multiple bear bile powder status feature vectors.
[0035] Furthermore, the purpose of splicing multiple bear bile powder status feature vectors is to comprehensively consider the information of each feature vector, so as to describe the status of the bear bile powder more comprehensively and accurately. By combining different feature vectors, a richer and more comprehensive feature representation can be obtained, which helps the system to better understand and evaluate the overall status of the bear bile powder. Here, splicing multiple bear bile powder status feature vectors can integrate the information of each feature into a global feature vector, so that the system can consider multiple aspects of the feature at the same time. Doing so helps to comprehensively analyze the various aspects of the bear bile powder, such as appearance characteristics, texture characteristics, humidity characteristics, etc., so as to more comprehensively evaluate the overall condition of the bear bile powder. In addition, splicing multiple feature vectors can increase the dimension and richness of the features, so that the system can better capture the complexity and diversity of the bear bile powder status.
[0036] Figure 3 FIG. 1 is a block diagram of a bear bile powder feature extraction unit in an intelligent management system for a bear bile powder storage environment according to an embodiment of the present application. Figure 3 As shown, in a specific embodiment of the present application, the bear bile powder feature extraction unit 122 includes: a bear bile powder image feature encoding subunit 1221, used to perform feature encoding on the bear bile powder image collected by the camera to obtain a bear bile powder feature map of interest; a bear bile powder feature pooling subunit 1222, used to perform pooling on the bear bile powder feature map of interest based on the average value of a feature matrix with a preset size to obtain the bear bile powder feature vector of interest.
[0037] It should be understood that by feature encoding the bear bile powder images captured by the camera, the image information can be converted into the form of high-dimensional feature vectors. These feature vectors can capture important features such as color, texture, and shape in the image, helping the system understand the content and structure of the bear bile powder image, so as to more accurately analyze the state of the bear bile powder. Secondly, feature encoding can extract and compress the bear bile powder image to extract the most representative feature information. Such feature representation can help the system better distinguish different bear bile powder images, identify the specific features and states of bear bile powder, provide the system with a more accurate image feature description, and help the system monitor and evaluate the storage of bear bile powder.
[0038] Furthermore, the feature map of interest of the bear bile powder is subjected to a process of average pooling based on a feature matrix with a preset size, aiming to compress and extract the image features to obtain a more compact and representative feature vector representation. Through this step, the system can more effectively capture the key features of the bear bile powder image. Among them, by calculating the average value of each area in the feature matrix, a feature vector with a smaller dimension but retaining important features can be obtained. Such a feature vector can better represent the key features of the bear bile powder image, which helps the system to understand and describe the image content more accurately. In addition, average pooling based on a feature matrix with a preset size can control the dimension and size of the feature vector. By setting the size of the feature matrix, the dimension of the feature vector can be controlled to avoid the problems of information overload and excessive computational complexity. The feature vector of interest to the bear bile powder obtained in this way not only has a high information content, but also has a low dimension, which is easier to process and store.
[0039] In a specific embodiment of the present application, the bear bile powder image feature encoding subunit 1221 includes: performing target detection on the bear bile powder image captured by the camera to obtain a bear bile powder region of interest; passing the bear bile powder region of interest through a bear bile powder significant target detector of interest to obtain the bear bile powder feature map of interest.
[0040] It should be understood that target detection is an important task in the field of computer vision, which aims to identify and locate the position of a specific target in an image. In the intelligent management system for the storage environment of bear bile powder, the position and bounding box of the bear bile powder in the image can be effectively extracted through target detection technology, so as to achieve accurate positioning and identification of the area of interest of the bear bile powder. Among them, target detection usually involves the use of deep learning models, such as convolutional neural networks or their variants, to perform feature extraction and target recognition on images. After a lot of training, these models can learn the feature representations of different targets in the image, so that they can accurately detect the specific target of bear bile powder. By performing target detection on the bear bile powder image captured by the camera, the system can obtain the location information of the area of interest of the bear bile powder, thereby achieving accurate monitoring and management of the bear bile powder. Such precise positioning not only helps with subsequent feature extraction and analysis, but also improves the accuracy and reliability of the system's storage status of the bear bile powder. Specifically, the target detection network is used to process the bear bile powder image captured by the camera with the following target detection formula to obtain the bear bile powder area of interest;
[0041] Among them, the target detection formula is:
[0042] ROI=H(ψ det ,B)=(cls(ψ det ,B),Regr(ψ det ,B)
[0043] Among them, ψ det is the bear bile powder image collected by the camera, B is the anchor frame, ROI is the bear bile powder region of interest, cls(ψ det ,B) indicates classification, Regr(ψ det ,B) indicates regression.
[0044] Furthermore, the bear bile powder region of interest is passed through the bear bile powder salient object detector of interest in order to further extract and strengthen the important features related to the bear bile powder, so as to more accurately describe and analyze the state of the bear bile powder. This step uses the target detection technology to locate and extract the key targets or features in the bear bile powder region of interest, so that the system can focus on and analyze the key parts of the bear bile powder more finely, thereby improving the system's understanding and monitoring capabilities of the bear bile powder state. Through the bear bile powder salient object detector of interest, the system can identify and locate the salient targets or regions related to the bear bile powder in the bear bile powder image. This target detection technology can help the system automatically find the important parts of the bear bile powder image, such as the shape, color, texture and other features of the bear bile powder, so as to effectively screen and extract information related to the state of the bear bile powder. The bear bile powder feature map of interest obtained by the bear bile powder salient object detector of interest can highlight the key features and structures in the bear bile powder image and strengthen the expression and recognition of bear bile powder related information. This feature map can better highlight the important parts of the bear bile powder. Specifically, each layer of the bear bile powder salient object detector performs the following operations on the input data in the forward pass of the layer: convolution processing is performed on the input data using a first convolution kernel to obtain a first convolution feature map; convolution processing is performed on the first convolution feature map using a second convolution kernel to obtain a second convolution feature map, wherein the size of the first convolution kernel is larger than the size of the second convolution kernel; and, pooling processing is performed on the second convolution feature map to obtain a pooled feature map; and, activation processing is performed on the pooled feature map to obtain an activated feature map; wherein the output of the last layer of the first convolution neural network model is the bear bile powder interest feature map, and the input of the first layer of the first convolution neural network model is the bear bile powder interest region.
[0045] In a specific embodiment of the present application, the storage environment humidity feature extraction unit 124 includes: arranging the storage environment humidity data collected by the sensor to obtain a storage environment humidity input vector; passing the storage environment humidity input vector through a storage environment humidity feature encoder based on a convolutional neural network to obtain the storage environment humidity feature vector.
[0046] It should be understood that the humidity data collected by the sensor is usually recorded in time sequence, with each time point corresponding to a humidity value. The process of arranging these time series data into an input vector involves integrating the time dimension and the humidity value together to form a data representation with a specific structure. Such an arrangement allows the model to better understand the correlation and change patterns between the data.
[0047] Furthermore, the storage environment humidity input vector is passed through a storage environment humidity feature encoder based on a convolutional neural network, aiming to use deep learning technology to extract and learn higher-level abstract features from humidity data, so as to better describe and understand the humidity change law of the storage environment. This feature encoding process converts the original humidity data into a more representative and interpretable feature vector through the hierarchical structure and feature extraction ability of the convolutional neural network. Among them, the storage environment humidity feature encoder based on the convolutional neural network can gradually extract the spatial and temporal features in the humidity data through multi-layer convolution and pooling operations. This hierarchical structure can capture the local patterns and global trends in the humidity data, and effectively convert the input vector into a higher-dimensional and more abstract feature representation. The storage environment humidity feature vector obtained by the storage environment humidity feature encoder can better express the key features and laws in the humidity data. These feature vectors contain important information about the humidity data learned by the deep learning model, and can better describe the characteristics such as the change trend and periodic law of the storage environment humidity, providing the system with a richer and more meaningful data representation. Specifically, each layer of the storage environment humidity feature encoder based on the convolutional neural network is used to perform convolution processing, pooling processing and nonlinear activation processing on the input data in the forward pass of the layer so that the last layer of the storage environment humidity feature encoder based on the convolutional neural network outputs the storage environment humidity feature vector, wherein the input of the storage environment humidity feature encoder based on the convolutional neural network is the storage environment humidity input vector.
[0048] In the above-mentioned intelligent management system 100 for the storage environment of bear bile powder, the storage environment humidity adjustment judgment module 130 is used to judge whether the storage environment humidity needs to be adjusted based on the storage state-related feature vector of the bear bile powder and the storage environment humidity feature vector. It should be understood that through the storage state-related feature vector of the bear bile powder, the system can understand the storage conditions, historical change trends and other relevant information of the bear bile powder. These feature vectors contain a comprehensive description of the storage state of the bear bile powder, which can reflect information on the stability, quality characteristics and other aspects of the bear bile powder. In addition, combined with the storage environment humidity feature vector, the system can comprehensively consider the relationship between the storage state of the bear bile powder and the ambient humidity. By jointly analyzing these two feature vectors through a deep learning model, the potential correlation and influence between them can be found, so as to judge whether the current storage environment humidity meets the optimal conditions. Based on the results of the comprehensive analysis, the system can judge whether the storage environment humidity needs to be adjusted. If the model finds that there is a mismatch or unfavorable correlation between the storage environment humidity and the storage state of the bear bile powder, the system can make corresponding adjustment suggestions, such as adjusting the humidity control equipment, changing the ventilation conditions, etc., to maintain the quality and stability of the bear bile powder.
[0049] Figure 4 FIG. 1 is a block diagram of a storage environment humidity adjustment judgment module in a bear bile powder storage environment intelligent management system according to an embodiment of the present application. Figure 4 As shown, in a specific embodiment of the present application, the storage environment humidity adjustment judgment module 130 includes: a storage environment feature fusion unit 131, which is used to fuse the bear bile powder storage state associated feature vector and the storage environment humidity feature vector to obtain a storage environment humidity adjustment classification feature matrix; a storage environment feature optimization unit 132, which is used to perform a scattering response depth correlation correction based on the class divergence space on the storage environment humidity adjustment classification feature matrix to obtain an optimized storage environment humidity adjustment classification feature matrix; a storage environment humidity adjustment generation unit 133, which is used to pass the optimized storage environment humidity adjustment classification feature matrix through a classifier to obtain a classification result, and the classification result is used to determine whether the storage environment humidity needs to be adjusted.
[0050] It should be understood that the fusion of the bear bile powder storage state associated feature vector and the storage environment humidity feature vector can combine the actual storage situation of the bear bile powder with environmental factors. By fusing and analyzing these two feature vectors through a deep learning model, we can more comprehensively understand the association between the storage state of the bear bile powder and the environmental humidity, thereby improving the accuracy and reliability of adjusting the storage environment humidity.
[0051] In particular, in the technical solution of the present application, the storage environment humidity adjustment classification feature matrix is a key information carrier that integrates the bear bile powder state data, the bear bile powder image features and the storage environment humidity data, and is used to determine whether the storage environment humidity needs to be adjusted. Improving the feature significance of the storage environment humidity adjustment classification feature matrix and avoiding feature redundancy are crucial to ensuring the accuracy and effectiveness of storage environment control. Specifically, significant features help to more accurately determine whether the storage state and environmental humidity of the bear bile powder are suitable, so as to make correct adjustment decisions. Significant features can speed up the processing speed of the classifier, so that the system can respond to environmental changes in a timely manner and avoid possible damage. In the face of different storage conditions and environmental changes, significant features help the system maintain stable performance and reduce misjudgments. At the same time, removing redundant features can reduce the computational burden of the model, increase the data processing speed, and make the system more efficient. Redundant features will take up more storage space, and avoiding feature redundancy helps to reduce storage costs. A significant storage environment humidity adjustment classification feature matrix helps to achieve accurate control of the storage environment humidity. Avoiding unnecessary adjustments can save energy and maintenance costs and improve economic benefits. Significant features and avoiding redundancy help reduce improper operations caused by misjudgments and improve the reliability of the system. Based on this, the storage environment humidity adjustment classification feature matrix is corrected for the scattering response depth correlation based on the class divergence space to obtain an optimized storage environment humidity adjustment classification feature matrix.
[0052] Specifically, the storage environment humidity adjustment classification feature matrix is corrected for the scattering response depth correlation based on the class divergence space to obtain an optimized storage environment humidity adjustment classification feature matrix, including: flattening the storage environment humidity adjustment classification feature matrix to obtain a storage environment humidity adjustment classification feature vector; and correcting the storage environment humidity adjustment classification feature vector for the scattering response depth correlation based on the class divergence space using the following optimization formula to obtain an optimized storage environment humidity adjustment classification feature vector, wherein the optimization formula is:
[0053]
[0054] Wherein, V1 represents the storage environment humidity adjustment classification feature vector, v i represents the eigenvalue of the i-th position of the storage environment humidity adjustment classification feature vector, represents the mean of the storage environment humidity adjustment classification feature vector, L represents the length of the storage environment humidity adjustment classification feature vector, ε represents a predetermined hyperparameter, ⊙ represents the position point multiplication, V1 ′Representing the optimized storage environment humidity adjustment classification feature vector; performing reverse feature aggregation on the optimized storage environment humidity adjustment classification feature vector in the feature flattening manner to obtain the optimized storage environment humidity adjustment classification feature matrix.
[0055] Among them, the storage environment humidity adjustment classification feature vector is subjected to a scattering response depth correlation correction based on the class divergence space to obtain an optimized storage environment humidity adjustment classification feature vector, including: determining the mean of the storage environment humidity adjustment classification feature vector; accumulating and summing the storage environment humidity adjustment classification feature vectors to obtain a sum value of the storage environment humidity adjustment classification feature vectors; subtracting the mean of the storage environment humidity adjustment classification feature vector from the sum value of the storage environment humidity adjustment classification feature vector, dividing the result by a predetermined hyperparameter, and then dividing the result by the length of the storage environment humidity adjustment classification feature vector to obtain a first quotient value; calculating an exponential function value with a natural constant as the base for the first quotient to obtain a first natural exponential function value; performing position point multiplication of the first natural exponential function value and the storage environment humidity adjustment classification feature vector to obtain an optimized storage environment humidity adjustment classification feature vector.
[0056] More specifically, in order to improve the feature significance of the storage environment humidity adjustment classification feature matrix and avoid feature redundancy, in the technical solution of the present application, the storage environment humidity adjustment classification feature matrix is subjected to a scattering response depth correlation correction based on a class divergence space, which uses the global mean of the storage environment humidity adjustment classification feature matrix as its dynamically formed deep anchor feature, and applies a coherent attention response mechanism based on the deep anchor feature to the original feature distribution, so as to perform a position scattering response depth correlation correction in a class divergence space with a depth difference, thereby making the original feature distribution have a highly significant deep correlation distribution characteristic, so as to improve the feature significance of the storage environment humidity adjustment classification feature matrix and avoid feature redundancy.
[0057] Furthermore, by classifying the optimized storage environment humidity adjustment classification feature matrix through a classifier, the system can quickly and accurately determine whether the storage environment humidity needs to be adjusted, providing more scientific and intelligent support for the storage management of bear bile powder. Among them, the classification results obtained by the classifier can directly indicate whether the storage environment humidity is within an appropriate range. If the classification results indicate that the humidity needs to be adjusted, the system can take corresponding measures in a timely manner, such as adjusting the humidity control equipment or changing the ventilation conditions, to maintain the quality and stability of the bear bile powder. This intelligent decision-making method can improve the efficiency and accuracy of storage environment management and ensure that the bear bile powder is stored under optimal storage conditions, thereby effectively optimizing the storage environment control process and improving the preservation quality and effect of the bear bile powder.
[0058] In summary, the embodiment of the present application first obtains the bear bile powder status data extracted from the database, the bear bile powder image collected by the camera, and the storage environment humidity data collected by the sensor, and then uses deep learning technology to perform feature extraction and association analysis on the three. Finally, a classifier is used to determine whether the storage environment humidity needs to be adjusted. Timely adjustment of the storage environment humidity can effectively prevent the bear bile powder from getting damp and moldy, thereby reducing production costs and ensuring product quality.
[0059] As described above, the bear bile powder storage environment intelligent management system 100 according to the embodiment of the present application can be implemented in various terminal devices. In one example, the bear bile powder storage environment intelligent management system 100 can be integrated into the terminal device as a software module and / or a hardware module. For example, the bear bile powder storage environment intelligent management system 100 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 bear bile powder storage environment intelligent management system 100 can also be one of the many hardware modules of the terminal device.
[0060] Alternatively, in another example, the bear bile powder storage environment intelligent management system 100 and the terminal device may also be separate devices, and the bear bile powder storage environment intelligent management system 100 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.
[0061] Exemplary Methods
[0062] Figure 5 Flow chart of the intelligent management method of the bear bile powder storage environment according to the embodiment of the present application. Figure 5 As shown, according to the intelligent management method of the bear bile powder storage environment of the embodiment of the present application, it includes: S110, acquiring the bear bile powder status data extracted from the database, the bear bile powder image collected by the camera and the storage environment humidity data collected by the sensor; S120, extracting the bear bile powder storage status associated feature vector and the storage environment humidity feature vector from the bear bile powder status data extracted from the database, the bear bile powder image collected by the camera and the storage environment humidity data collected by the sensor; S130, judging whether the storage environment humidity needs to be adjusted based on the bear bile powder storage status associated feature vector and the storage environment humidity feature vector.
[0063] Here, those skilled in the art will appreciate that the specific operations of each step in the above-mentioned bear bile powder storage environment intelligent management method have been referenced above. Figures 1 to 4 The description of the bear bile powder storage environment intelligent management system has been introduced in detail, and therefore, its repeated description will be omitted.
[0064] Exemplary Electronic Devices
[0065] Below, reference Figure 6 To describe an electronic device according to an embodiment of the present application.
[0066] like Figure 6 As shown, the electronic device 10 includes an input device 11, an input interface 12, a central processing unit 13, a memory 14, an output interface 15, an output device 16, and a bus 17. The input interface 12, the central processing unit 13, the memory 14, and the output interface 15 are connected to each other through the bus 17, and the input device 11 and the output device 16 are connected to the bus 17 through the input interface 12 and the output interface 15, respectively, and then connected to other components of the electronic device 10.
[0067] Specifically, the input device 11 receives input information from the outside and transmits the input information to the central processing unit 13 through the input interface 12; the central processing unit 13 processes the input information based on the computer executable instructions stored in the memory 14 to generate output information, temporarily or permanently stores the output information in the memory 14, and then transmits the output information to the output device 16 through the output interface 15; the output device 16 outputs the output information to the outside of the electronic device 10 for user use.
[0068] In one embodiment, Figure 6 The electronic device 10 shown can be implemented as a network device, which may include: a memory configured to store programs; a processor configured to run the programs stored in the memory to execute any one of the bear bile powder storage environment intelligent management methods described in the above embodiments.
[0069] According to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network, and / or installed from a removable storage medium.
[0070] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.
[0071] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present application, but the present application is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and substance of the present application, and these modifications and improvements are also considered to be within the scope of protection of the present application.
Claims
1. An intelligent management system for the storage environment of bear bile powder, characterized in that: include: A bear bile powder storage data acquisition module is used to acquire the bear bile powder status data extracted from the database, the bear bile powder image collected by the camera, and the storage environment humidity data collected by the sensor; A bear bile powder storage data extraction module, used to extract a bear bile powder storage state associated feature vector and a storage environment humidity feature vector from the bear bile powder state data extracted from the database, the bear bile powder image collected by the camera, and the storage environment humidity data collected by the sensor; The storage environment humidity adjustment judgment module is used to judge whether the storage environment humidity needs to be adjusted based on the bear bile powder storage state associated feature vector and the storage environment humidity feature vector.
2. The intelligent management system for bear bile powder storage environment according to claim 1 is characterized in that: The bear bile powder storage data extraction module includes: A bear bile powder state semantic encoding unit, used for semantically encoding the bear bile powder state data extracted from the database to obtain a global feature vector of the bear bile powder state; A bear bile powder feature extraction unit, used for extracting features from the bear bile powder image collected by the camera to obtain a feature vector of interest of the bear bile powder; A bear bile powder storage state feature association unit, used for associating the bear bile powder state global feature vector with the bear bile powder interest feature vector to obtain the bear bile powder storage state association feature vector; The storage environment humidity feature extraction unit is used to extract features from the storage environment humidity data collected by the sensor to obtain the storage environment humidity feature vector.
3. The intelligent management system for bear bile powder storage environment according to claim 2 is characterized in that: The bear bile powder state semantic coding unit comprises: The bear bile powder state data extracted from the database is passed through a bear bile powder state text semantic coding model to obtain a plurality of bear bile powder state feature vectors; The multiple bear bile powder state feature vectors are concatenated to obtain the bear bile powder state global feature vector.
4. The intelligent management system for bear bile powder storage environment according to claim 3 is characterized in that: The bear bile powder feature extraction unit comprises: A bear bile powder image feature encoding subunit, used for performing feature encoding on the bear bile powder image collected by the camera to obtain a feature map of interest of the bear bile powder; The bear bile powder feature pooling subunit is used to perform pooling on the bear bile powder feature map of interest based on the average value of a feature matrix with a preset size to obtain the bear bile powder feature vector of interest.
5. The intelligent management system for bear bile powder storage environment according to claim 4 is characterized in that: The bear bile powder image feature encoding subunit comprises: Performing target detection on the bear bile powder image captured by the camera to obtain a bear bile powder region of interest; The bear bile powder region of interest is passed through a bear bile powder salient object detector to obtain the bear bile powder feature map of interest.
6. The intelligent management system for bear bile powder storage environment according to claim 5, characterized in that: The storage environment humidity feature extraction unit comprises: Arranging the storage environment humidity data collected by the sensor to obtain a storage environment humidity input vector; The storage environment humidity input vector is passed through a storage environment humidity feature encoder based on a convolutional neural network to obtain the storage environment humidity feature vector.
7. The intelligent management system for bear bile powder storage environment according to claim 6, characterized in that: The storage environment humidity adjustment judgment module includes: A storage environment feature fusion unit, used for fusing the bear bile powder storage state associated feature vector and the storage environment humidity feature vector to obtain a storage environment humidity adjustment classification feature matrix; A storage environment feature optimization unit, used for performing a scattering response depth correlation correction based on a class divergence space on the storage environment humidity adjustment classification feature matrix to obtain an optimized storage environment humidity adjustment classification feature matrix; The storage environment humidity adjustment generation unit is used to pass the optimized storage environment humidity adjustment classification feature matrix through a classifier to obtain a classification result, and the classification result is used to determine whether the storage environment humidity needs to be adjusted.
8. The intelligent management system for bear bile powder storage environment according to claim 7, characterized in that: The storage environment characteristic optimization unit includes: Flattening the storage environment humidity adjustment classification feature matrix to obtain a storage environment humidity adjustment classification feature vector; Performing a scattering response depth correlation correction based on a class divergence space on the storage environment humidity adjustment classification feature vector to obtain an optimized storage environment humidity adjustment classification feature vector; The optimized storage environment humidity adjustment classification feature vector is subjected to reverse feature aggregation in the feature flattening manner to obtain the optimized storage environment humidity adjustment classification feature matrix.
9. The intelligent management system for bear bile powder storage environment according to claim 8, characterized in that: The storage environment humidity adjustment classification feature vector is subjected to a scattering response depth correlation correction based on a class divergence space to obtain an optimized storage environment humidity adjustment classification feature vector, including: Determining a mean value of the storage environment humidity adjustment classification feature vector; Accumulating and summing the storage environment humidity adjustment classification feature vectors to obtain a total value of the storage environment humidity adjustment classification feature vectors; Subtracting the mean of the storage environment humidity adjustment classification feature vector from the sum of the storage environment humidity adjustment classification feature vectors and dividing the sum by a predetermined hyperparameter and then by the length of the storage environment humidity adjustment classification feature vector to obtain a first quotient value; Calculating an exponential function value with a natural constant as a base for the first quotient value to obtain a first natural exponential function value; The first natural exponential function value is multiplied by the storage environment humidity adjustment classification feature vector at a position point to obtain an optimized storage environment humidity adjustment classification feature vector.
10. A method for intelligent management of bear bile powder storage environment, characterized in that: include: Obtain bear bile powder status data extracted from a database, bear bile powder images captured by a camera, and storage environment humidity data captured by a sensor; Extracting a bear bile powder storage state associated feature vector and a storage environment humidity feature vector from the bear bile powder state data extracted from the database, the bear bile powder image collected by the camera, and the storage environment humidity data collected by the sensor; Based on the bear bile powder storage state associated feature vector and the storage environment humidity feature vector, it is determined whether the storage environment humidity needs to be adjusted.