Chinese herbal medicine planting full process tracking management system and method

Abstract

The present application provides a whole-process tracking management system and method for Chinese herbal medicine planting, which relates to the field of intelligent management. It uses artificial intelligence-based data analysis and processing technology to perform time series correlation on the time queue data of inventory levels, and time series correlation and market demand forecast decoding on the time queue data of market demand information, so as to automatically judge whether the risk of out-of-stock exceeds a preset threshold based on the interactive response characteristics between the time series characteristics of inventory levels and the market demand forecast decoding characteristics. In this way, by acquiring the time series data of inventory levels and market demand information in real time, the system can continuously track market dynamics and provide more accurate market demand forecasts, thereby reducing the possibility of inventory shortages and improving the intelligence of inventory management.

Description

Technical Field

[0001] The present application relates to the field of intelligent management, and more specifically, to a full-process tracking management system and method for Chinese medicinal materials planting. Background Art

[0002] With the widespread application of traditional Chinese medicine around the world, the Chinese medicine industry has developed rapidly, and higher requirements have been placed on the quality and safety of Chinese medicinal materials. The full-process tracking management of Chinese medicinal materials planting can ensure the quality control of Chinese medicinal materials from planting, harvesting, processing, sales and other links, thereby ensuring the quality of Chinese medicine products.

[0003] In the whole process tracking and management of Chinese herbal medicine planting, inventory management is a complex and critical link. It is not only a bridge connecting planting and the market, but also a core link to ensure product quality, control costs, improve response speed and optimize resource allocation. However, the traditional inventory management model often relies on manual experience and simple statistical methods, which cannot accurately predict changes in market demand in real time, and easily lead to overstocking or out-of-stock situations. Especially in the management of special commodities such as Chinese herbal medicines, due to the large fluctuations in market demand and the long and unstable supply chain, the traditional management method is difficult to adapt to the rapidly changing market environment.

[0004] Therefore, an optimized tracking and management solution for the entire process of Chinese medicinal material planting is needed. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a whole-process tracking management system and method for Chinese medicinal materials planting, which uses artificial intelligence-based data analysis and processing technology to perform time series correlation on the time queue data of inventory levels, and time series correlation and market demand forecast decoding on the time queue data of market demand information, so as to automatically judge whether the risk of out-of-stock exceeds a preset threshold based on the interactive response characteristics between the time series characteristics of inventory levels and the market demand forecast decoding characteristics. In this way, by acquiring the time series data of inventory levels and market demand information in real time, the system can continuously track market dynamics and provide more accurate market demand forecasts, thereby reducing the possibility of inventory shortages and improving the intelligence of inventory management.

[0006] According to one aspect of the present application, a whole-process tracking and management system for Chinese medicinal material planting is provided, which includes:

[0007] Seed selection processing module, used to record and manage the source information, variety information and quality inspection reports of seeds of Chinese medicinal materials;

[0008] A seed field management module, used for real-time monitoring of the growth status of the seeds of the Chinese medicinal materials;

[0009] A harvesting plan formulation and processing module is used to formulate a harvesting plan and process the harvested Chinese medicinal materials;

[0010] A Chinese medicinal material detection module is used to perform quality detection on the processed Chinese medicinal materials;

[0011] An inventory management module, used to manage the inventory level of the Chinese medicinal materials;

[0012] The sales channel after-sales management module is used to record and manage the sales channels and customer information of the Chinese medicinal materials.

[0013] In the above-mentioned Chinese medicinal material planting full-process tracking and management system, the inventory management module includes: an inventory data acquisition unit, which is used to obtain a time queue of inventory levels; a market demand data acquisition unit, which is used to obtain a time queue of market demand information; an inventory level market demand sequence encoding unit, which is used to sequence the time queue of the inventory level and the time queue of the market demand information respectively to obtain an inventory level time series correlation feature vector and a market demand time series correlation feature vector; a market demand forecasting unit, which is used to perform market demand forecasting analysis on the market demand time series correlation feature vector to obtain a market demand forecast decoding representation vector; an inventory level-market demand forecast interactive response analysis unit, which is used to perform inventory level-market demand time series interactive response analysis on the market demand forecast decoding representation vector and the inventory level time series correlation feature vector to obtain inventory level-market demand forecast interactive response characteristics; a management result generation unit, which is used to generate a management result based on the inventory level-market demand forecast interactive response analysis. Interactive response characteristics are used to obtain management results, and the management results are used to indicate whether the risk of out-of-stock occurs exceeds a preset threshold; wherein the inventory level-market demand forecast interactive response analysis unit includes: an inventory level time series correlation feature decomposition subunit, used to perform feature decomposition on the inventory level time series correlation feature vector to obtain a sequence of inventory level local time series correlation feature vectors; an inventory level-market demand correlation subunit, used to calculate the correlation matrix between the market demand forecast decoding representation vector and each inventory level local time series correlation feature vector in the sequence of the inventory level local time series correlation feature vector to obtain a sequence of inventory level-market demand correlation matrices; an inventory level-market demand forecast local-global interactive impact analysis subunit, used to perform local-global interactive impact analysis on the sequence of the inventory level-market demand correlation matrix to obtain an inventory level-market demand forecast local-global interactive response matrix as the inventory level-market demand forecast interactive response feature.

[0014] In the above-mentioned full-process tracking and management system for Chinese medicinal materials planting, the inventory level market demand sequence encoding unit is used to: input the time queue of the inventory level and the time queue of the market demand information into a sequence encoder based on the Bi-LSTM model respectively to obtain the inventory level time series correlation feature vector and the market demand time series correlation feature vector.

[0015] In the above-mentioned Chinese medicinal material planting full-process tracking and management system, the market demand prediction unit is used to: input the market demand time series correlation feature vector into the decoder-based market demand predictor to obtain the market demand prediction decoding representation vector.

[0016] In the above-mentioned full-process tracking and management system for Chinese medicinal materials planting, the inventory level-market demand association subunit includes: a market demand forecast nonlinear transformation secondary subunit, which is used to perform a nonlinear transformation on the market demand forecast decoding representation vector to obtain the market demand forecast decoding representation vector after nonlinear transformation; a market demand forecast after nonlinear transformation-inventory level interaction secondary subunit, which is used to calculate the association matrix between the market demand forecast decoding representation vector after nonlinear transformation and each inventory level local time series association feature vector in the sequence of the inventory level local time series association feature vector to obtain the sequence of the inventory level-market demand association matrix.

[0017] In the above-mentioned full-process tracking and management system for Chinese medicinal materials planting, the nonlinear transformation market demand forecast-inventory level interaction secondary sub-unit is used to: vector multiply the transposed vector of the nonlinear transformation market demand forecast decoding representation vector and each inventory level local time series correlation feature vector in the sequence of the inventory level local time series correlation feature vector to obtain the sequence of the inventory level-market demand correlation matrix.

[0018] In the above-mentioned Chinese medicinal material planting full-process tracking and management system, the inventory level-market demand forecast local-global interactive impact analysis subunit includes: an inventory level-market demand characteristic interactive energy factor calculation secondary subunit, which is used to calculate the characteristic interactive energy factors of each inventory level-market demand association matrix in the sequence of the inventory level-market demand association matrix to obtain a sequence of inventory level-market demand characteristic interactive energy factors; an inventory level-market demand characteristic interactive energy factor normalization secondary subunit, which is used to input the sequence of inventory level-market demand characteristic interactive energy factors into a Sigmoid function to obtain a sequence of normalized inventory level-market demand characteristic interactive energy factors; an inventory level-market demand association matrix weighted processing secondary subunit, which is used to use the sequence of normalized inventory level-market demand characteristic interactive energy factors as a sequence of weights, and calculate the position-weighted sum of the sequence of the inventory level-market demand association matrix to obtain the inventory level-market demand forecast local-global interactive response matrix.

[0019] In the above-mentioned Chinese medicinal materials planting full-process tracking and management system, the inventory level-market demand characteristic interaction energy factor calculation secondary subunit is used to: respectively calculate the mean and variance of the inventory level-market demand association matrix to obtain the inventory level-market demand association mean and inventory level-market demand association variance; calculate the positional difference between the inventory level-market demand association matrix and the inventory level-market demand association mean to obtain the inventory level-market demand association difference matrix; calculate the fourth power of each eigenvalue in the inventory level-market demand association difference matrix to obtain the inventory level-market demand association modulated difference matrix; calculate the expected value of the inventory level-market demand association modulated difference matrix to obtain the inventory level-market demand association expected value; and multiply the inventory level-market demand association expected value by the square of the inventory level-market demand association variance. Divide to obtain the inventory level-market demand associated kurtosis value; calculate the sum of the inventory level-market demand associated variance and the hyperparameter to obtain the inventory level-market demand associated first energy factor; calculate the square of the difference between the inventory level-market demand associated kurtosis value and the inventory level-market demand associated mean to obtain the inventory level-market demand associated difference value; add the value obtained by multiplying the inventory level-market demand associated variance by constant two and the value obtained by multiplying the hyperparameter by constant two to the inventory level-market demand associated difference value to obtain the inventory level-market demand associated second energy factor; divide the inventory level-market demand associated first energy factor by the inventory level-market demand associated second energy factor to obtain the inventory level-market demand characteristic interaction energy factor corresponding to the inventory level-market demand association matrix.

[0020] In the above-mentioned full-process tracking and management system for Chinese medicinal materials planting, the management result generation unit is used to: input the inventory level-market demand forecast local-global interactive response matrix into the classifier-based inventory intelligent management module to obtain the management result, and the management result is used to indicate whether the risk of out-of-stock exceeds a preset threshold.

[0021] According to another aspect of the present application, a method for tracking and managing the entire process of Chinese medicinal material planting is provided, which includes:

[0022] Record and manage the source information, variety information and quality inspection reports of seeds of Chinese medicinal materials;

[0023] Real-time monitoring of the growth status of the seeds of the Chinese medicinal materials;

[0024] Formulate a harvesting plan and process the harvested Chinese medicinal materials;

[0025] Conducting quality inspection on the processed Chinese medicinal materials;

[0026] Managing the inventory levels of said Chinese medicinal materials;

[0027] Record and manage the sales channels and customer information of the Chinese medicinal materials.

[0028] Compared with the prior art, the Chinese medicinal material planting full-process tracking management system and method provided by the present application adopts artificial intelligence-based data analysis and processing technology to perform time series correlation on the time queue data of the inventory level, and time series correlation and market demand forecast decoding on the time queue data of the market demand information, so as to automatically judge whether the risk of out-of-stock exceeds the preset threshold according to the interactive response characteristics between the time series characteristics of the inventory level and the market demand forecast decoding characteristics. In this way, by acquiring the time series data of the inventory level and the market demand information in real time, the system can continuously track market dynamics and provide more accurate market demand forecasts, thereby reducing the possibility of inventory shortages and improving the intelligence of inventory management. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the embodiments of the present application 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 some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0030] Figure 1 This is a system block diagram of the full-process tracking and management system for Chinese medicinal materials planting according to an embodiment of the present application.

[0031] Figure 2It is a block diagram of the inventory management module in the full-process tracking and management system of Chinese medicinal materials planting according to an embodiment of the present application.

[0032] Figure 3 This is a schematic diagram of data flow in the inventory management module of the full-process tracking and management system for Chinese medicinal materials planting according to an embodiment of the present application.

[0033] Figure 4 It is a block diagram of the inventory level-market demand forecast interactive response analysis unit in the full-process tracking and management system of Chinese medicinal materials planting according to an embodiment of the present application.

[0034] Figure 5 It is a block diagram of the inventory level-market demand association subunit in the full-process tracking and management system of Chinese medicinal materials planting according to an embodiment of the present application.

[0035] Figure 6 It is a block diagram of the local-global interactive impact analysis subunit of inventory level-market demand forecast in the full-process tracking and management system of traditional Chinese medicine planting according to an embodiment of the present application.

[0036] Figure 7 This is a flow chart of a method for tracking and managing the entire process of Chinese medicinal material planting according to an embodiment of the present application. DETAILED DESCRIPTION

[0037] 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.

[0038] The widespread global application of traditional Chinese medicine has led to the rapid development of the Chinese medicine industry, which has put forward higher requirements on the quality and safety of Chinese medicinal materials. The full-process tracking and management of Chinese medicinal materials planting plays a vital role in ensuring the quality of Chinese medicinal materials. Inventory management, as a key link in the full-process tracking and management of Chinese medicinal materials planting, has a significant impact on ensuring product quality, controlling costs, improving response speed and optimizing resource allocation. However, traditional inventory management methods rely on manual experience and basic statistics, which makes it difficult to accurately predict market changes and easily lead to inventory backlogs or shortages. Especially in the field of Chinese medicinal materials, due to the instability of market demand and the complexity of the supply chain, traditional management models are difficult to meet the rapidly changing needs of the market.

[0039] Based on this, this application proposes a full-process tracking and management system for Chinese medicinal materials planting. Figure 1 : is a system block diagram of the whole process tracking management system of Chinese medicinal materials planting according to the embodiment of the present application. Figure 1As shown, in the whole process tracking and management system 100 of Chinese medicinal material planting, it includes: a seed selection processing module 110, which is used to record and manage the source information, variety information and quality inspection report of the seeds of Chinese medicinal materials; a seed field management module 120, which is used to monitor the growth status of the seeds of the Chinese medicinal materials in real time; a harvesting plan formulation and processing module 130, which is used to formulate a harvesting plan and process the harvested Chinese medicinal materials; a Chinese medicinal material inspection module 140, which is used to perform quality inspection on the processed Chinese medicinal materials; an inventory management module 150, which is used to manage the inventory level of the Chinese medicinal materials; a sales channel after-sales management module 160, which is used to record and manage the sales channels and customer information of the Chinese medicinal materials.

[0040] Accordingly, in the inventory management module, the technical concept of the present application is to obtain the time queue of inventory level and the time queue of market demand information, and use artificial intelligence-based data analysis and processing technology to perform time series association on the time queue of inventory level, and perform time series association and market demand forecast decoding on the time queue of market demand information, so as to automatically determine whether the risk of out-of-stock exceeds the preset threshold based on the interactive response characteristics between the time series characteristics of inventory level and the decoding characteristics of market demand forecast. In this way, by obtaining the time series data of inventory level and market demand information in real time, the system can continuously track market dynamics and provide more accurate market demand forecasts, thereby reducing the possibility of inventory shortages and improving the intelligence of inventory management.

[0041] Figure 2 It is a block diagram of the inventory management module in the full-process tracking and management system of Chinese medicinal materials planting according to an embodiment of the present application. Figure 3 Schematic diagram of data flow in the inventory management module of the whole process tracking management system of Chinese herbal medicine planting according to the embodiment of the present application. Figure 2 and Figure 3As shown, the inventory management module 150 includes: an inventory data acquisition unit 151, which is used to obtain the time queue of inventory level; a market demand data acquisition unit 152, which is used to obtain the time queue of market demand information; an inventory level market demand sequence encoding unit 153, which is used to sequence the time queue of the inventory level and the time queue of the market demand information respectively to obtain the inventory level time series correlation feature vector and the market demand time series correlation feature vector; a market demand forecasting unit 154, which is used to perform market demand forecasting analysis on the market demand time series correlation feature vector to obtain a market demand forecast decoding representation vector; an inventory level-market demand forecast interactive response analysis unit 155, which is used to perform inventory level-market demand time series interactive response analysis on the market demand forecast decoding representation vector and the inventory level time series correlation feature vector to obtain an inventory level-market demand forecast interactive response feature; a management result generation unit 156, which is used to obtain a management result based on the inventory level-market demand forecast interactive response feature, and the management result is used to indicate whether the risk of out-of-stock exceeds a preset threshold.

[0042] In an embodiment of the present application, the inventory data acquisition unit 151 and the market demand data acquisition unit 152 are respectively used to obtain a time queue for inventory levels and a time queue for obtaining market demand information. It should be understood that the time queue of inventory levels provides dynamic monitoring of the inventory status of Chinese herbal medicines, which can reflect the changing trend of Chinese herbal medicine inventory over time. The time queue of market demand information is the basis for demand forecasting, which can help companies understand consumer purchasing behavior and trends. By analyzing inventory levels and market demand information, it can be determined whether the current inventory of Chinese herbal medicines is sufficient to meet future market demand. If the predicted demand exceeds the current inventory, it may lead to a risk of out-of-stock. That is, by combining the analysis results of these two types of data, inventory levels and market demand information, companies can make more accurate decisions to ensure timely responses when demand fluctuates and avoid out-of-stock situations of Chinese herbal medicines.

[0043] In the embodiment of the present application, the inventory level market demand sequence encoding unit 153 is used to sequence encode the time queue of the inventory level and the time queue of the market demand information respectively to obtain the inventory level time series correlation feature vector and the market demand time series correlation feature vector. Specifically, in the embodiment of the present application, the inventory level market demand sequence encoding unit is used to: input the time queue of the inventory level and the time queue of the market demand information into the sequence encoder based on the Bi-LSTM model respectively to obtain the inventory level time series correlation feature vector and the market demand time series correlation feature vector. It should be understood that the time queue of the inventory level and the time queue of the market demand information have different time series feature information between different time spans, such as the trend of changes in inventory levels, fluctuations in market demand, etc. Based on this, in order to better understand the dynamic relationship and association of data between various time points, in the technical solution of the present application, the time queue of the inventory level and the time queue of the market demand information are respectively input into the sequence encoder based on the Bi-LSTM model to obtain the inventory level time series correlation feature vector and the market demand time series correlation feature vector.

[0044] In an embodiment of the present application, the market demand forecasting unit 154 is used to perform market demand forecasting analysis on the market demand time series correlation feature vector to obtain a market demand forecast decoding representation vector. Specifically, in an embodiment of the present application, the market demand forecasting unit is used to: input the market demand time series correlation feature vector into a decoder-based market demand forecaster to obtain the market demand forecast decoding representation vector. Accordingly, in order to more accurately capture the changing pattern of market demand and adjust the inventory level based on future market demand, in the technical solution of the present application, the market demand time series correlation feature vector is input into a decoder-based market demand forecaster to obtain a market demand forecast decoding representation vector. That is, the decoder can infer future market trends based on past market demand information (i.e., the features extracted by the encoder). This step is crucial for predicting future demand because it allows the system to make reasonable estimates of what may happen in the future while considering existing information, thereby more accurately assessing whether there is a risk of out-of-stock.

[0045] In an embodiment of the present application, the inventory level-market demand forecast interactive response analysis unit 155 is used to perform an inventory level-market demand time series interactive response analysis on the market demand forecast decoded representation vector and the inventory level time series associated feature vector to obtain an inventory level-market demand forecast interactive response feature. It should be understood that the market demand forecast decoded representation vector and the inventory level time series associated feature vector each contain rich information, but this information is often coupled together, that is, there is a certain correlation and response relationship between different features. Therefore, in order to analyze and capture the feature interaction relationship between each local time point more carefully and deeply, in the technical solution of the present application, the market demand forecast decoded representation vector and the inventory level time series associated feature vector are subjected to an inventory level-market demand time series interactive response analysis to obtain an inventory level-market demand forecast local-global interactive response matrix as an inventory level-market demand forecast interactive response feature. In particular, the time series interactive response analysis is a feature processing technology that integrates feature decoupling and feature interaction metric learning, and is intended to deeply analyze and integrate the information in the feature vector.

[0046] In detail, first, the inventory level time series correlation feature vector is feature-decomposed to obtain a sequence of inventory level local time series correlation feature vectors. That is, by decomposing the overall feature vector of the inventory level into a series of local feature vectors, the changes in the inventory level in different time periods can be observed more finely, providing support for the subsequent time series interaction with market demand. Next, the market demand forecast decoding representation vector is nonlinearly transformed to reveal the complex time series relationship in the market demand to obtain the market demand forecast decoding representation vector after nonlinear transformation. Furthermore, in order to analyze the local time series correlation relationship between the inventory level and the market demand in a fine-grained manner, the correlation matrix between each inventory level local time series correlation feature vector and the market demand forecast decoding representation vector after nonlinear transformation is calculated to obtain a sequence of inventory level-market demand correlation matrices. Then, the characteristic interaction energy factor is extracted from each inventory level-market demand correlation matrix to obtain a sequence of inventory level-market demand characteristic interaction energy factors. In particular, the feature interaction energy factor is calculated based on the kurtosis value, variance and mean of the matrix, which can be used to quantify the interaction intensity between inventory level and market demand forecast, help understand the degree of influence between the two, and highlight the key features that have an important impact on inventory level and market demand changes, so as to pay more attention to them in subsequent analysis and decision-making. After that, each feature interaction energy factor is input into the Sigmoid function for normalization to map the feature interaction energy factor to a fixed range [0,1], so as to convert it into a weight value to effectively capture the continuous changes between the feature interaction energy factors, so as to better reflect the dynamic relationship between inventory level and market demand, and reasonably allocate the contribution and attention of different interaction features. Finally, the normalized factors are used as weight values ​​to weight and sum the sequence of the inventory level-market demand association matrix to obtain the inventory level-market demand forecast local-global interaction response matrix.

[0047] Specifically, Figure 4 The block diagram is a block diagram of the inventory level-market demand forecast interactive response analysis unit in the whole process tracking management system of Chinese medicinal materials planting according to the embodiment of the present application. Figure 4As shown, the inventory level-market demand forecast interactive response analysis unit 155 includes: an inventory level time series correlation feature decomposition subunit 1551, which is used to perform feature decomposition on the inventory level time series correlation feature vector to obtain a sequence of inventory level local time series correlation feature vectors; an inventory level-market demand correlation subunit 1552, which is used to calculate the correlation matrix between the market demand forecast decoding representation vector and each inventory level local time series correlation feature vector in the sequence of inventory level local time series correlation feature vectors to obtain a sequence of inventory level-market demand correlation matrices; an inventory level-market demand forecast local-global interactive impact analysis subunit 1553, which is used to perform local-global interactive impact analysis on the sequence of inventory level-market demand correlation matrices to obtain an inventory level-market demand forecast local-global interactive response matrix as the inventory level-market demand forecast interactive response feature.

[0048] More specifically, Figure 5 FIG. 1 is a block diagram of a subunit for associating inventory level with market demand in a whole-process tracking and management system for Chinese medicinal materials planting according to an embodiment of the present application. Figure 5 As shown, the inventory level-market demand association subunit 1552 includes: a market demand forecast nonlinear transformation secondary subunit 15521, which is used to perform a nonlinear transformation on the market demand forecast decoding representation vector to obtain the market demand forecast decoding representation vector after nonlinear transformation; a market demand forecast after nonlinear transformation-inventory level interaction secondary subunit 15522, which is used to calculate the association matrix between the market demand forecast decoding representation vector after nonlinear transformation and each inventory level local time series association feature vector in the sequence of the inventory level local time series association feature vector to obtain the sequence of the inventory level-market demand association matrices.

[0049] In an embodiment of the present application, specifically, the market demand forecast nonlinear transformation secondary sub-unit is used to: multiply the market demand forecast decoding representation vector with the market demand forecast transformation matrix, and then positionally add the obtained market demand forecast transformation vector and market demand forecast bias vector to obtain the market demand forecast decoding representation vector after the nonlinear transformation.

[0050] In an embodiment of the present application, specifically, the nonlinear transformation market demand forecast-inventory level interaction secondary sub-unit is used to: vector multiply the transposed vector of the nonlinear transformation market demand forecast decoding representation vector and each inventory level local time series correlation feature vector in the sequence of the inventory level local time series correlation feature vector to obtain the sequence of the inventory level-market demand correlation matrix.

[0051] More specifically, Figure 6The block diagram is a subunit for analyzing the local-global interaction impact of inventory level-market demand forecast in the whole process tracking management system of Chinese herbal medicine planting according to the embodiment of the present application. Figure 6 As shown, the inventory level-market demand forecast local-global interaction impact analysis subunit 1553 includes: an inventory level-market demand characteristic interaction energy factor calculation secondary subunit 15531, which is used to calculate the characteristic interaction energy factors of each inventory level-market demand association matrix in the sequence of the inventory level-market demand association matrix to obtain a sequence of inventory level-market demand characteristic interaction energy factors; an inventory level-market demand characteristic interaction energy factor normalization secondary subunit 15532, which is used to input the sequence of inventory level-market demand characteristic interaction energy factors into a Sigmoid function to obtain a sequence of normalized inventory level-market demand characteristic interaction energy factors; an inventory level-market demand association matrix weighted processing secondary subunit 15533, which is used to use the sequence of normalized inventory level-market demand characteristic interaction energy factors as a sequence of weights, and calculate the position-weighted sum of the sequence of the inventory level-market demand association matrices to obtain the inventory level-market demand forecast local-global interaction response matrix.

[0052] More specifically, in an embodiment of the present application, the inventory level-market demand characteristic interaction energy factor calculation secondary subunit is used to: respectively calculate the mean and variance of the inventory level-market demand association matrix to obtain the inventory level-market demand association mean and the inventory level-market demand association variance; calculate the positional difference between the inventory level-market demand association matrix and the inventory level-market demand association mean to obtain the inventory level-market demand association difference matrix; calculate the fourth power of each eigenvalue in the inventory level-market demand association difference matrix to obtain the inventory level-market demand association modulated difference matrix; calculate the expected value of the inventory level-market demand association modulated difference matrix to obtain the inventory level-market demand association expected value; compare the inventory level-market demand association expected value with the square of the inventory level-market demand association variance Divide to obtain the inventory level-market demand associated kurtosis value; calculate the sum of the inventory level-market demand associated variance and the hyperparameter to obtain the inventory level-market demand associated first energy factor; calculate the square of the difference between the inventory level-market demand associated kurtosis value and the inventory level-market demand associated mean to obtain the inventory level-market demand associated difference value; add the value obtained by multiplying the inventory level-market demand associated variance by constant two and the value obtained by multiplying the hyperparameter by constant two to the inventory level-market demand associated difference value to obtain the inventory level-market demand associated second energy factor; divide the inventory level-market demand associated first energy factor by the inventory level-market demand associated second energy factor to obtain the inventory level-market demand feature interaction energy factor corresponding to the inventory level-market demand association matrix.

[0053] In the embodiment of the present application, specifically, the inventory level-market demand forecast interactive response analysis unit is used to: perform inventory level-market demand time series interactive response analysis on the market demand forecast decoding representation vector and the inventory level time series associated feature vector, which can be expressed by the formula: ; ; ; ; ; ; ;in, is the inventory level time series correlation feature vector, For feature decomposition operations, are the first, second,...,th in the sequence of the local time series correlation feature vectors of the inventory level respectively. ,..., The local time series correlation feature vector of inventory levels, is the number of feature vectors in the sequence of the local time series associated feature vectors of the inventory level, decoding a representation vector for the market demand forecast, and are the market demand forecast transformation matrix and the market demand forecast bias vector respectively, A decoding representation vector for the market demand forecast after the nonlinear transformation, yes The transposed vector of represents vector multiplication, For the The inventory level-market demand correlation matrix between the local time series correlation feature vectors of the inventory level and the decoded representation vector of the market demand forecast after the nonlinear transformation, yes The eigenvalues ​​at each position in , yes The mean of To calculate the expected value of a matrix, yes The variance of for The kurtosis value of is a hyperparameter, yes The corresponding inventory level-market demand characteristics interaction energy factor, yes function, yes The corresponding normalized inventory level-market demand characteristics interaction energy factor, It is the point multiplication by position. is the inventory level-market demand forecast local-global interaction response matrix.

[0054] In an embodiment of the present application, the management result generating unit 156 is used to obtain a management result based on the inventory level-market demand forecast interactive response feature, and the management result is used to indicate whether the risk of out-of-stock exceeds a preset threshold. Specifically, in an embodiment of the present application, the management result generating unit is used to: input the inventory level-market demand forecast local-global interactive response matrix into the classifier-based inventory intelligent management module to obtain the management result, and the management result is used to indicate whether the risk of out-of-stock exceeds a preset threshold. That is, the inventory level-market demand forecast interactive response feature obtained by performing a time series interactive response analysis between the market demand forecast decoding representation vector and the inventory level time series associated feature vector is used for classification processing, so as to automatically determine whether the risk of out-of-stock exceeds a preset threshold. In this way, by acquiring the time series data of inventory level and market demand information in real time, the system can continuously track market dynamics and provide more accurate market demand forecasts, thereby reducing the possibility of inventory shortages and improving the intelligence of inventory management.

[0055] In particular, the present application takes into account that the market demand forecast decoding representation vector and the inventory level time series correlation feature vector respectively represent the decoding prediction representation of the bidirectional short-range-long-range time series correlation characteristics of the market demand information and the bidirectional short-range-long-range time series correlation characteristics of the inventory level. When the inventory level-market demand time series interactive response analysis is performed, the time series correlation feature distribution pattern based on the source time series distribution and its decoding prediction representation pattern will also have local-global time series-decoding prediction interactive response differences. Therefore, it is expected to improve the detailed interactive response semantic aggregation expression effect of the inventory level-market demand forecast local-global interactive response matrix based on the association pattern representation differences.

[0056] In a preferred example, inputting the inventory level-market demand forecast local-global interactive response matrix into the classifier-based inventory intelligent management module to obtain a management result includes: calculating the sum of the absolute values ​​of each eigenvalue of the inventory level-market demand forecast local-global interactive response matrix to obtain a first inventory level-market demand forecast local-global interactive response and modulation value, and calculating the square root of the sum of the squares of each eigenvalue of the inventory level-market demand forecast local-global interactive response matrix to obtain a second inventory level-market demand forecast local-global interactive response and modulation value; performing dot-wise subtraction of the inventory level-market demand forecast local-global interactive response matrix from the second inventory level-market demand forecast local-global interactive response and modulation value, and performing dot-wise multiplication with the number of eigenvalues ​​of the inventory level-market demand forecast local-global interactive response matrix and the reciprocal of the first inventory level-market demand forecast local-global interactive response and modulation value, and taking the reciprocal of each eigenvalue to obtain the first inventory level-market demand forecast local-global interactive response and modulation value. Demand forecast local-global interactive response phase conversion matrix; after point-wise subtraction of the inventory level-market demand forecast local-global interactive response matrix and the first inventory level-market demand forecast local-global interactive response and modulation value, respectively multiply them with the square root of the number of eigenvalues ​​of the inventory level-market demand forecast local-global interactive response matrix and the inverse of the second inventory level-market demand forecast local-global interactive response and modulation value, and take the inverse of each eigenvalue to obtain the second inventory level-market demand forecast local-global interactive response phase conversion matrix; point-subtract the second inventory level-market demand forecast local-global interactive response phase conversion matrix from the first inventory level-market demand forecast local-global interactive response phase conversion matrix and the dot product matrix of the weighted hyperparameter to obtain the optimized inventory level-market demand forecast local-global interactive response matrix; input the optimized inventory level-market demand forecast local-global interactive response matrix into the classifier-based inventory intelligent management module to obtain the management result.

[0057] Here, the optimization of the inventory level-market demand forecast local-global interaction response matrix is ​​expressed as: ; ; ; ; ; ; ;in, is the inventory level-market demand forecast local-global interaction response matrix, and are the width and height of the local-global interactive response matrix of inventory level-market demand forecast, are the eigenvalues ​​of the inventory level-market demand forecast local-global interaction response matrix, is the number of eigenvalues ​​of the inventory level-market demand forecast local-global interaction response matrix, predicting local-global interaction responses and modulation values ​​for the first inventory level-market demand, Forecasting local-global interaction responses and modulation values ​​for the second inventory level-market demand, It means point multiplication by position. It means to subtract by position point. To take the inverse of each eigenvalue in the feature matrix, is the first inventory level-market demand forecast local-global interactive response phase transition matrix, The second inventory level-market demand forecast local-global interaction response phase transformation matrix is, is the weighted hyperparameter, is the set of real numbers, A local-global interaction response matrix is ​​predicted for the optimized inventory level-market demand.

[0058] That is, in the preferred example, the difference of the characteristic value of the local-global interaction response matrix of the inventory level-market demand forecast relative to the overall feature set of the local-global interaction response matrix of the inventory level-market demand forecast is used as the semantic change intensity information, and the phase-like conversion corresponding to the position-based intensity modulation is performed through the different and modulation representation forms, so that the aggregation enhancement of the semantic change phase perception can improve the axial aggregation receptive field along the feature aggregation direction by performing the spatial translation operation based on alternating stacking under the set scale equilibrium of the local-global interaction response matrix of the inventory level-market demand forecast, thereby improving the perception effect of the aggregation semantics of the local-global interaction response matrix of the inventory level-market demand forecast for the change of detailed semantics, so as to improve the expression effect of the local-global interaction response matrix of the inventory level-market demand forecast, and improve the accuracy of the management result obtained by inputting it into the inventory intelligent management module based on the classifier. In this way, by acquiring the time series data of inventory level and market demand information in real time, the system can continuously track market dynamics and provide more accurate market demand forecasts, thereby reducing the possibility of inventory shortages and improving the intelligence of inventory management.

[0059] In summary, the Chinese medicinal material planting full-process tracking management system 100 based on the embodiment of the present application is explained, which uses artificial intelligence-based data analysis and processing technology to perform time series correlation on the time queue data of the inventory level, and time series correlation and market demand forecast decoding on the time queue data of the market demand information, so as to automatically judge whether the risk of out-of-stock exceeds the preset threshold according to the interactive response characteristics between the time series characteristics of the inventory level and the market demand forecast decoding characteristics. In this way, by acquiring the time series data of the inventory level and the market demand information in real time, the system can continuously track market dynamics and provide more accurate market demand forecasts, thereby reducing the possibility of inventory shortages and improving the intelligence of inventory management.

[0060] As described above, the Chinese medicinal material planting full-process tracking management system 100 according to the embodiment of the present application can be implemented in various terminal devices, such as a server for Chinese medicinal material planting full-process tracking management. In one example, the Chinese medicinal material planting full-process tracking management system 100 according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the Chinese medicinal material planting full-process tracking management system 100 can be a software module in the operating system of the terminal device, or it can be an application developed for the terminal device; of course, the Chinese medicinal material planting full-process tracking management system 100 can also be one of the many hardware modules of the terminal device.

[0061] Alternatively, in another example, the Chinese medicinal materials planting full-process tracking management system 100 and the terminal device may also be separate devices, and the Chinese medicinal materials planting full-process tracking 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.

[0062] Figure 7 Flow chart of the whole process tracking and management method of Chinese medicinal materials planting according to the embodiment of the present application. Figure 7 As shown, in the whole process tracking and management method of Chinese medicinal materials planting, it includes: S110, recording and managing the source information, variety information and quality inspection report of the seeds of Chinese medicinal materials; S120, real-time monitoring of the growth status of the seeds of the Chinese medicinal materials; S130, formulating a harvesting plan and processing the harvested Chinese medicinal materials; S140, conducting quality inspection on the processed Chinese medicinal materials; S150, managing the inventory level of the Chinese medicinal materials; S160, recording and managing the sales channels and customer information of the Chinese medicinal materials.

[0063] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned Chinese medicinal material planting full-process tracking management method have been referenced above. Figures 1 to 6 The description of the full-process tracking management system for Chinese medicinal materials planting has been introduced in detail, and therefore, its repeated description will be omitted.

[0064] In summary, the whole process tracking and management method of Chinese medicinal materials planting based on the embodiment of the present application is explained, which uses artificial intelligence-based data analysis and processing technology to perform time series correlation on the time queue data of inventory levels, and time series correlation and market demand forecast decoding on the time queue data of market demand information, so as to automatically judge whether the risk of out-of-stock exceeds the preset threshold according to the interactive response characteristics between the time series characteristics of inventory levels and the market demand forecast decoding characteristics. In this way, by acquiring the time series data of inventory levels and market demand information in real time, the system can continuously track market dynamics and provide more accurate market demand forecasts, thereby reducing the possibility of inventory shortages and improving the intelligence of inventory management.

[0065] In the several embodiments provided in this application, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0066] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0067] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0068] It is obvious to those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and that the present application can be implemented in other specific forms without departing from the spirit or essential features of the present application.

Claims

1. A whole-process tracking and management system for Chinese medicinal materials planting, characterized in that: include: Seed selection processing module, used to record and manage the source information, variety information and quality inspection reports of seeds of Chinese medicinal materials; A seed field management module, used for real-time monitoring of the growth status of the seeds of the Chinese medicinal materials; A harvesting plan formulation and processing module is used to formulate a harvesting plan and process the harvested Chinese medicinal materials; A Chinese medicinal material detection module is used to perform quality detection on the processed Chinese medicinal materials; An inventory management module, used to manage the inventory level of the Chinese medicinal materials; A sales channel after-sales management module, used to record and manage the sales channels and customer information of the Chinese herbal medicines; Wherein, the inventory management module includes: Inventory data collection unit, used to obtain the time queue of inventory levels; A market demand data collection unit, used to obtain a time queue of market demand information; An inventory level market demand sequence encoding unit, used for respectively performing sequence encoding on the time queue of the inventory level and the time queue of the market demand information to obtain an inventory level time series correlation feature vector and a market demand time series correlation feature vector; A market demand forecasting unit, used for performing market demand forecasting analysis on the market demand time series correlation feature vector to obtain a market demand forecast decoding representation vector; An inventory level-market demand forecast interactive response analysis unit, configured to perform an inventory level-market demand time series interactive response analysis on the market demand forecast decoding representation vector and the inventory level time series associated feature vector to obtain an inventory level-market demand forecast interactive response feature; A management result generating unit, used to obtain a management result based on the inventory level-market demand forecast interactive response characteristics, wherein the management result is used to indicate whether the risk of out-of-stock exceeds a preset threshold; Wherein, the inventory level-market demand forecast interactive response analysis unit includes: An inventory level time series correlation feature decomposition subunit, used for performing feature decomposition on the inventory level time series correlation feature vector to obtain a sequence of inventory level local time series correlation feature vectors; An inventory level-market demand association subunit, used to calculate an association matrix between the market demand forecast decoding representation vector and each inventory level local time series association feature vector in the sequence of the inventory level local time series association feature vector to obtain a sequence of inventory level-market demand association matrices; The inventory level-market demand forecast local-global interaction impact analysis subunit is used to perform local-global interaction impact analysis on the sequence of the inventory level-market demand association matrix to obtain the inventory level-market demand forecast local-global interaction response matrix as the inventory level-market demand forecast interaction response feature.

2. The whole process tracking and management system of Chinese medicinal materials planting according to claim 1 is characterized in that: The inventory level market demand sequence encoding unit is used to: input the time queue of the inventory level and the time queue of the market demand information into a sequence encoder based on a Bi-LSTM model respectively to obtain the inventory level time series correlation feature vector and the market demand time series correlation feature vector.

3. The whole process tracking and management system of Chinese medicinal materials planting according to claim 2 is characterized in that: The market demand prediction unit is used to: input the market demand time series correlation feature vector into a decoder-based market demand predictor to obtain the market demand prediction decoding representation vector.

4. The whole process tracking and management system of Chinese medicinal materials planting according to claim 3 is characterized in that: The inventory level-market demand association subunit includes: A market demand forecast nonlinear transformation secondary subunit is used to perform a nonlinear transformation on the market demand forecast decoded representation vector to obtain a nonlinearly transformed market demand forecast decoded representation vector; The secondary sub-unit of market demand forecast after nonlinear transformation-inventory level interaction is used to calculate the correlation matrix between the decoding representation vector of the market demand forecast after nonlinear transformation and each inventory level local time series correlation feature vector in the sequence of the inventory level local time series correlation feature vector to obtain the sequence of the inventory level-market demand correlation matrix.

5. The whole process tracking and management system of Chinese medicinal materials planting according to claim 4 is characterized in that: The nonlinear transformed market demand forecast-inventory level interaction secondary sub-unit is used to: vector-multiply the transposed vector of the nonlinear transformed market demand forecast decoding representation vector and each inventory level local time series correlation feature vector in the sequence of the inventory level local time series correlation feature vector to obtain the sequence of the inventory level-market demand correlation matrix.

6. The whole process tracking and management system of Chinese medicinal materials planting according to claim 5 is characterized in that: The inventory level-market demand forecast local-global interactive impact analysis subunit includes: The inventory level-market demand characteristic interaction energy factor calculation secondary subunit is used to calculate the characteristic interaction energy factor of each inventory level-market demand association matrix in the sequence of the inventory level-market demand association matrix to obtain a sequence of inventory level-market demand characteristic interaction energy factors; The normalized secondary subunit of the inventory level-market demand characteristic interaction energy factor is used to input the sequence of the inventory level-market demand characteristic interaction energy factor into the Sigmoid function to obtain a sequence of normalized inventory level-market demand characteristic interaction energy factor; The secondary sub-unit for weighted processing of the inventory level-market demand association matrix is ​​used to calculate the position-weighted sum of the sequence of the inventory level-market demand association matrix using the sequence of the normalized inventory level-market demand characteristic interaction energy factors as the sequence of weights to obtain the local-global interaction response matrix of the inventory level-market demand forecast.

7. The whole process tracking and management system of Chinese medicinal materials planting according to claim 6 is characterized in that: The inventory level-market demand characteristic interaction energy factor calculation secondary subunit is used to: Calculating the mean and variance of the inventory level-market demand correlation matrix respectively to obtain the inventory level-market demand correlation mean and the inventory level-market demand correlation variance; Calculating the positional difference between the inventory level-market demand correlation matrix and the inventory level-market demand correlation mean to obtain an inventory level-market demand correlation difference matrix; Calculating the fourth power of each eigenvalue in the inventory level-market demand correlation difference matrix to obtain an inventory level-market demand correlation modulation difference matrix; Calculating the expected value of the inventory level-market demand association modulated difference matrix to obtain the inventory level-market demand association expected value; Dividing the expected value of the inventory level-market demand association by the square of the inventory level-market demand association variance to obtain the inventory level-market demand association kurtosis value; Calculating the sum of the inventory level-market demand correlation variance and the hyperparameter to obtain the inventory level-market demand correlation first energy factor; Calculating the square of the difference between the inventory level-market demand association kurtosis value and the inventory level-market demand association mean to obtain an inventory level-market demand association difference value; The second energy factor of the inventory level-market demand association is obtained by adding the value obtained by multiplying the inventory level-market demand association variance by constant 2 and the value obtained by multiplying the hyper parameter by constant 2 to the inventory level-market demand association difference value; The first energy factor associated with inventory level and market demand is divided by the second energy factor associated with inventory level and market demand to obtain the inventory level-market demand characteristic interaction energy factor corresponding to the inventory level-market demand association matrix.

8. The whole process tracking and management system of Chinese medicinal materials planting according to claim 7 is characterized in that: The management result generating unit is used to input the inventory level-market demand forecast local-global interactive response matrix into a classifier-based inventory intelligent management module to obtain the management result, and the management result is used to indicate whether the risk of out-of-stock exceeds a preset threshold.

9. A method for tracking and managing the entire process of planting Chinese medicinal materials, using the tracking and management system for the entire process of planting Chinese medicinal materials according to any one of claims 1 to 8, characterized in that: include: Record and manage the source information, variety information and quality inspection reports of seeds of Chinese medicinal materials; Real-time monitoring of the growth status of the seeds of the Chinese medicinal materials; Formulate a harvesting plan and process the harvested Chinese medicinal materials; Conducting quality inspection on the processed Chinese medicinal materials; Managing the inventory levels of said Chinese medicinal materials; Record and manage the sales channels and customer information of the Chinese medicinal materials.

Images