Standard substance intelligent sorting method and device, electronic equipment and storage medium

Abstract

The application provides a standard substance intelligent sorting method and device, electronic equipment and storage medium, the method comprises the following steps: obtaining the basic variable parameter of drug standard substance sorting and the daily average sorting workload of drug standard substance; based on the basic variable parameter and the daily average sorting workload, the preset sorting key control index is comprehensively calculated, the optimal sorting path, the storage grid capacity and the workload allocation mode suitable for each sorting user in the drug standard substance are obtained; the optimal sorting path, the storage grid capacity and the workload allocation mode of each sorting user are intelligently strengthened, and the sorting implementation strategy corresponding to each sorting user is obtained; the optimal sorting path and the sorting implementation strategy are sent to the sorting execution terminal, so that the sorting execution terminal instructs the sorting user to complete the sorting task of the standard substance according to the optimal sorting path and the sorting implementation strategy. The application saves manpower and improves the sorting efficiency.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a method, apparatus, electronic device and storage medium for intelligent sorting of standard materials. Background Technology

[0002] With the increasing public health demands and the continuous improvement of drug control standards and testing technologies, the variety and market demand for drug reference materials have increased significantly. Currently, the number of drug reference material varieties, annual order volume, and external distribution volume have all increased dramatically compared to the past. Therefore, improving the sorting efficiency of reference materials is of paramount importance.

[0003] In related technologies, standard substances (such as pharmaceuticals) are stored in warehouses in partitioned and categorized sections. The sorting paths are fixed, typically arranged according to user orders, with warehouse capacity evenly distributed and workload evenly distributed based on the number of standard substance products, without considering factors such as order quantity and variety. Sorting personnel must travel to multiple locations in the warehouse to pick out pharmaceuticals one by one according to user orders. This process involves multiple back-and-forth trips, resulting in high workload and long sorting times. This not only increases the workload of sorting personnel but also prolongs order sorting time, thereby reducing sorting efficiency.

[0004] Therefore, how to effectively improve the sorting efficiency of standard substances is a problem that needs to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for intelligent sorting of standard substances, to at least solve the problem in related technologies where sorting personnel frequently have to backtrack, resulting in time and labor costs and reduced sorting efficiency. The technical solution of this application is as follows: According to a first aspect of the embodiments of this application, a method for intelligent sorting of standard substances is provided, comprising: Obtain the basic variable parameters for sorting pharmaceutical reference materials, as well as the average daily sorting workload of pharmaceutical reference materials; Based on the aforementioned basic variable parameters and average daily sorting workload, a comprehensive calculation is performed according to the preset key sorting control indicators to obtain the optimal sorting path, storage capacity, and workload allocation method for each sorting user in the pharmaceutical standard material. Intelligent reinforcement learning is performed on the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain the sorting implementation strategy for each sorting user. The optimal sorting path and the sorting implementation strategy are sent to the sorting execution terminal so that the sorting execution terminal can instruct the sorting user to complete the sorting task of the standard substance according to the optimal sorting path and the sorting implementation strategy.

[0006] Optionally, the basic variable parameters for sorting pharmaceutical reference materials, and the average daily sorting workload of pharmaceutical reference materials, include: Statistical analysis was conducted on the sorting implementation strategy during a set time period in the sorting process of pharmaceutical reference materials to obtain the basic variable parameters of the optimal sorting path, storage capacity, and workload allocation method for pharmaceutical reference materials. The daily average sorting workload of pharmaceutical standard substances is collected in real time. The daily average sorting workload includes: daily workload, characteristics of each order, capacity of sorting unit, and sorting habits.

[0007] Optionally, the step of performing comprehensive calculations based on the basic variable parameters and average daily sorting workload, according to preset key sorting control indicators, to obtain the optimal sorting path, storage capacity, and workload allocation method for each sorting user in the pharmaceutical standard materials, includes: Based on the order type, type layout, location number and sorting habits in the basic variable parameters, the average daily sorting workload is comprehensively calculated according to the preset key sorting control indicators to obtain the optimal sorting path for each sorting user. Based on the product sales speed, packaging materials, replenishment frequency, and storage compartment capacity limits in the basic variable parameters, the average daily sorting workload is comprehensively calculated according to the preset key sorting control indicators to obtain a reasonable storage compartment capacity. Based on the order quantity, order variety, order quantity, and user sorting efficiency in the basic variable parameters, the average daily sorting workload is comprehensively calculated according to the preset key sorting control indicators to obtain a balanced workload distribution method.

[0008] Optionally, the step of performing intelligent reinforcement learning on the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain the sorting implementation strategy for each sorting user includes: The optimal sorting path, storage capacity constraints, and workload allocation method for each sorting user are fused according to a set weight coefficient to obtain the fusion vector for the corresponding sorting user. The fusion vector of each sorting user is input into the trained joint optimization model for reinforcement learning to obtain a sorting implementation strategy suitable for the corresponding sorting user. The joint optimization model is obtained by reinforcement iterative training based on artificial intelligence reinforcement learning algorithm.

[0009] Optionally, the method further includes: iteratively training the joint optimization model based on an artificial intelligence reinforcement learning algorithm in the following manner to obtain a trained joint optimization model: Obtain a training set, which includes optimal sorting path samples, storage cell capacity samples, and workload allocation method samples for multiple sorting users; as well as sorting implementation strategy samples for the corresponding sorting users; The optimal sorting path sample, storage cell capacity sample, and workload allocation method sample for each sorting user are fused according to the set weight coefficients to obtain the fused vector sample for the corresponding sorting user. The fusion vector sample of each sorting user is input into the joint optimization model for training. During the training process, the sorting implementation strategy output by the joint optimization model that is adapted to each sorting user is compared with the sorting implementation strategy sample of the corresponding sorting user, the difference is calculated, and the difference is used as the loss value. Based on the loss value, the parameters of the joint optimization model are adjusted through the backpropagation mechanism. After multiple iterations, the joint optimization model converges, and the trained joint optimization model is obtained.

[0010] Optionally, the method further includes: After receiving the sorting execution terminal to complete the sorting task based on the optimal sorting path and the sorting implementation strategy, the actual sorting time, the location movement trajectory and the task completion time data are transmitted back in real time. Based on the actual sorting time, location movement trajectory, and task completion time data, the weight coefficients of the optimal sorting path, storage capacity, and workload allocation method for the sorting user are iteratively adjusted.

[0011] According to a second aspect of the embodiments of this application, a standard substance intelligent sorting device is provided, comprising: The acquisition module is used to acquire the basic variable parameters for the sorting of pharmaceutical standard substances, as well as the average daily sorting workload of pharmaceutical standard substances. The comprehensive calculation module is used to perform comprehensive calculations based on the basic variable parameters and the average daily sorting workload, according to the preset key sorting control indicators, to obtain the optimal sorting path, storage capacity and workload allocation method for each sorting user in the pharmaceutical standard material. The sorting implementation strategy determination module is used to perform intelligent reinforcement learning on the optimal sorting path, storage capacity and workload allocation method of each sorting user to obtain the sorting implementation strategy for each sorting user. The sending module is used to send the optimal sorting path and the sorting implementation strategy to the sorting execution terminal, so that the sorting execution terminal can instruct the sorting user to complete the sorting task of the standard substance according to the optimal sorting path and the sorting implementation strategy.

[0012] Optionally, the acquisition module includes: The statistical analysis module is used to perform statistical analysis on the sorting implementation strategy during a set time period in the pharmaceutical standard substance sorting process, and to obtain the basic variable parameters of the optimal sorting path, storage capacity, and workload allocation method for pharmaceutical standard substance sorting. The data acquisition module is used to collect the average daily sorting workload of pharmaceutical standard substances in real time. The average daily sorting workload includes: daily workload, characteristics of each order, capacity of sorting unit, and sorting habits.

[0013] Optionally, the integrated computing module includes: The sorting path comprehensive calculation module is used to perform comprehensive calculations on the average daily sorting workload based on the order type, type layout, storage location number and sorting habits in the basic variable parameters, according to the preset key sorting control indicators, to obtain the optimal sorting path suitable for each sorting user. The storage compartment capacity comprehensive calculation module is used to perform comprehensive calculations on the average daily sorting workload based on the product sales speed, packaging materials, replenishment frequency, and storage compartment capacity limits in the basic variable parameters, according to preset key sorting control indicators, to obtain a reasonable storage compartment capacity. The workload allocation comprehensive calculation module is used to perform comprehensive calculations on the average daily sorting workload based on the order quantity, order variety, order quantity, and user sorting efficiency in the basic variable parameters, and to obtain a balanced workload allocation method.

[0014] Optionally, the sorting implementation strategy determination module includes: The fusion module is used to fuse the optimal sorting path, storage capacity, and workload allocation method of each sorting user according to the set weight coefficients to obtain the fusion vector of the corresponding sorting user. The reinforcement learning module is used to input the fusion vector of each sorting user into the trained joint optimization model for reinforcement learning, so as to obtain a sorting implementation strategy suitable for the corresponding sorting user. The joint optimization model is obtained by reinforcement iterative training based on artificial intelligence reinforcement learning algorithm.

[0015] Optionally, the apparatus further includes a training module, configured to iteratively train the joint optimization model in advance using an artificial intelligence reinforcement learning algorithm in the following manner to obtain a trained joint optimization model.

[0016] Optionally, the training module includes: The training set acquisition module is used to acquire a training set, which includes optimal sorting path samples, storage cell capacity samples, and workload allocation method samples for multiple sorting users; as well as sorting implementation strategy samples for the corresponding sorting users. The sample fusion module is used to fuse the optimal sorting path sample, storage cell capacity sample, and workload allocation method sample of each sorting user according to the set weight coefficients to obtain the fusion vector sample of the corresponding sorting user. The model training module is used to input the fusion vector samples of each sorting user into the joint optimization model for training. During the training process, the sorting implementation strategy output by the joint optimization model that is adapted to each sorting user is compared with the sorting implementation strategy sample of the corresponding sorting user, the difference is calculated, and the difference is used as the loss value. Based on the loss value, the parameters of the joint optimization model are adjusted through the backpropagation mechanism. After multiple iterations, the joint optimization model converges, and the trained joint optimization model is obtained.

[0017] Optionally, the device further includes: The receiving module is used to receive the actual sorting time, location movement trajectory and task completion time data transmitted back in real time by the sorting execution terminal after completing the sorting task based on the optimal sorting path and the sorting implementation strategy. The weight adjustment module is used to iteratively adjust the weight coefficients of the optimal sorting path, storage capacity, and workload allocation method of the sorting user based on the actual sorting time, storage location movement trajectory, and task completion time data.

[0018] According to a third aspect of the embodiments of this application, an electronic device is provided, comprising: The variable parameter storage module is used to store the basic variable parameters for sorting pharmaceutical standard substances; The input module is used to acquire and input the average daily sorting workload, which includes: daily workload, characteristics of a single order, and capacity of a sorting unit; The I / O interface is connected to the variable parameter storage module, the input module and the calculation module respectively, and is used to transmit the basic variable parameters input by the variable parameter storage module and the average daily sorting workload input by the input module to the calculation module. The computing module, connected to both the CPU and I / O interface module, is used to pre-configure the computing logic for key control indicators. Based on the basic variable parameters and the average daily sorting workload, it performs comprehensive calculations according to the preset computing logic for the corresponding key sorting control indicators to obtain the optimal sorting path, storage capacity, and workload allocation method for each sorting user in the pharmaceutical standard material. Furthermore, it performs intelligent reinforcement learning on the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain the sorting implementation strategy for each sorting user. The CPU, connected to the computing module, is used to control the computing module to perform global sorting optimization logic operations and scheduling according to the pre-configured corresponding key sorting control indicators. The output module, connected to the CPU, is used to receive the sorting implementation strategy generated by the computing module for each sorting user, and to send the sorting implementation strategy to the sorting execution terminal so that the sorting execution terminal can instruct the sorting user to complete the sorting task of standard substances according to the optimal sorting path and the sorting implementation strategy.

[0019] According to a fourth aspect of the embodiments of this application, another electronic device is provided, comprising: It includes a processor, a memory; and a program or instructions stored in the memory and executable on the processor, which, when executed by the processor, implement the steps of the standard material intelligent sorting method as described above.

[0020] According to a fifth aspect of the embodiments of this application, a readable storage medium is provided, on which a program or instructions are stored, which, when executed by a processor of an electronic device, implement the steps of the standard material intelligent sorting method as described above.

[0021] According to a sixth aspect of the embodiments of this application, a computer program product is provided, including a computer program or instructions, which, when executed by a processor of an electronic device, implement the steps of the standard material intelligent sorting method as described above.

[0022] The technical solutions provided by the embodiments of this application have at least the following beneficial effects: This application obtains the basic variable parameters for sorting pharmaceutical standard substances, as well as the average daily sorting workload. Based on the basic variable parameters and the average daily sorting workload, it performs comprehensive calculations according to preset key sorting control indicators to obtain the optimal sorting path, storage capacity, and workload allocation method for each sorting user. Intelligent reinforcement learning is then applied to the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain the corresponding sorting implementation strategy. The optimal sorting path and the sorting implementation strategy are sent to the sorting execution terminal so that the terminal can instruct the sorting user to complete the sorting task of the standard substances according to the optimal sorting path and implementation strategy. This application, based on basic variable parameters and the average daily sorting workload, performs comprehensive calculations and sorting according to preset key sorting control indicators, changing the traditional sorting by order demand sequence, average allocation of storage capacity, and average allocation of workload by order quantity, saving manpower and improving sorting efficiency.

[0023] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0024] The accompanying drawings, incorporated in and forming part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the principles of this application. They do not constitute an undue limitation of this application. To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a standard material intelligent sorting method provided in an embodiment of this application.

[0026] Figure 2 This is a block diagram of a standard material intelligent sorting device provided in an embodiment of this application.

[0027] Figure 3 This is a block diagram of an acquisition module provided in an embodiment of this application.

[0028] Figure 4 This is a block diagram of a comprehensive computing module provided in an embodiment of this application.

[0029] Figure 5 This is a block diagram of a sorting implementation strategy determination module provided in an embodiment of this application.

[0030] Figure 6 This is another block diagram of a standard material intelligent sorting device provided in the embodiments of this application.

[0031] Figure 7 This is a block diagram of an electronic device provided in an embodiment of this application.

[0032] Figure 8 This is another block diagram of an electronic device provided in the embodiments of this application.

[0033] Figure 9 This is another block diagram of an electronic device provided in the embodiments of this application.

[0034] Figure 10 This is a block diagram of an apparatus for intelligent sorting of standard substances provided in an embodiment of this application. Detailed Implementation

[0035] To enable those skilled in the art to better understand the technical solutions of this application, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.

[0036] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0037] Please see Figure 1 This is a flowchart of a standard material intelligent sorting method provided in an embodiment of this application, such as... Figure 1 As shown, the method includes the following steps: Step 101: Obtain the basic variable parameters for sorting pharmaceutical reference materials, as well as the average daily sorting workload of pharmaceutical reference materials.

[0038] Step 102: Based on the basic variable parameters and the average daily sorting workload, perform comprehensive calculations according to the preset key sorting control indicators to obtain the optimal sorting path, storage capacity, and workload allocation method for each sorting user in the pharmaceutical standard material.

[0039] Step 103: Perform intelligent reinforcement learning on the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain the sorting implementation strategy for each sorting user.

[0040] Step 104: Send the optimal sorting path and the sorting implementation strategy to the sorting execution terminal so that the sorting execution terminal can instruct the sorting user to complete the sorting task of the standard substance according to the optimal sorting path and the sorting implementation strategy.

[0041] The intelligent sorting method for standard materials described in this application can be applied to terminals, vehicles, servers, etc., without limitation. The terminal implementation device can be an electronic device such as a smartphone, laptop, tablet, desktop computer, personal digital assistant (PDA), and wearable device. The server can be an independent server, a server cluster, or a server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, or big data and artificial intelligence platforms, without limitation.

[0042] The following is combined with Figure 1 The specific implementation steps of a standard material intelligent sorting method provided in the embodiments of this application will be described in detail.

[0043] In step 101, the basic variable parameters for sorting drug reference materials and the average daily sorting workload of drug reference materials are obtained.

[0044] In this step, statistical analysis is performed on the sorting implementation strategy within a set time period during the pharmaceutical standard substance sorting process. This yields the basic variable parameters for the optimal sorting path, storage compartment capacity, and workload allocation method. The set time period can be configured according to actual needs, such as 12 months, 6 months, 3 months, 1 month, or 15 days; this embodiment does not impose any limitations. Various statistical analysis methods exist, which are well-known to those skilled in the art and will not be elaborated upon here.

[0045] The basic variable parameters for the optimal sorting path can include: order type, sorting site layout, location numbering, employee sorting habits, etc. The purpose is to calculate the optimal sorting path for each sorting user (i.e., sorting employee) based on these basic variable parameters.

[0046] The basic variable parameters for storage capacity can include: product sales speed, packaging materials, replenishment frequency, storage capacity limits, etc. The purpose is to calculate a reasonable storage capacity based on these basic variable parameters, so as to calculate the sales volume and replenishment procedures for each standard product in about three months (of course, this is just an example, and in actual applications, it is not limited to this).

[0047] The basic variable parameters of the workload allocation method (or approach) may include: number of orders, number of order varieties, and number of orders. These are weighted to form workload units, which are then assigned to sorting users according to their own workload unit task quantity, thereby achieving allocation based on work done and improving sorting efficiency.

[0048] In this embodiment, the average daily sorting workload of pharmaceutical standard substances can be collected in real time. For example, the average daily sorting workload of the pharmaceutical standard substance distribution room or sorting area can be collected in real time. Of course, in practical applications, it is not limited to this and can also include other partitioned distribution rooms or partitioned sorting areas, etc. This embodiment does not impose any restrictions. The average daily sorting workload can include: daily workload, characteristics of each order, sorting unit capacity, and sorting habits. Of course, in specific applications, it is not limited to this.

[0049] In this embodiment, daily workload, characteristics of each order, sorting unit capacity, and sorting habits can be referred to as four statistical dimensions in the standard substance sorting process. Specifically, this embodiment uses four dimensions as an example for the sorting of pharmaceutical standard substances; however, it is not limited to these in actual applications. Specifically: 11) Daily workload, i.e., the average daily sorting order workload is approximately 480 orders (≈120,000 orders / 250 days), and the average daily number of items sorted is approximately 12,000 units (≈3 million units / 250 days). That is, the total number of orders to be sorted throughout the year is approximately 120,000 orders. After deducting holidays and maintenance days, the actual annual working days total 250 days. Calculated, the average daily sorting order workload is 480 orders. The total number of items to be sorted throughout the year is approximately 3 million units. After deducting holidays, equipment maintenance, and other downtime, the actual annual sorting working days are 250 days, resulting in an average daily sorting of approximately 12,000 units.

[0050] 12) The characteristics of each order: According to statistics, there is no pattern to the types of items ordered in each order. These may include various standard substances, such as traditional Chinese medicine, chemical drugs, antibiotics, biochemical drugs, excipients, packaging materials, and medical devices. The storage temperature is also not fixed and may include room temperature, refrigeration, and freezing.

[0051] 13) Regarding the capacity of the sorting unit, the overall space of the sorting area is approximately 600 square meters, with a storage capacity of approximately 1 million units. Calculations show that the storage capacity for each product type is limited, averaging approximately 180 units per type (≈1 million units / 5600 product types). In other words, the total area of ​​the sorting area is 600 square meters, and the maximum total quantity of goods that can be stored is 1 million units. The area stores a total of 5600 different product types. After distributing the total quantity across categories, it can be seen that the storage space for each category is limited, with an average of only about 180 units per product type. However, order demand for each product varies, resulting in varying quantities, thus requiring frequent replenishment to ensure stock availability during sorting.

[0052] 14) Sorting habits: Generally speaking, the sorting efficiency of sorting users is basically the same or similar, but their sorting habits are different. Some users are used to sorting by order, while others are used to sorting by product category.

[0053] In step 102, based on the basic variable parameters and the average daily sorting workload, a comprehensive calculation is performed according to the preset key sorting control indicators to obtain the optimal sorting path, storage capacity, and workload allocation method for each sorting user in the pharmaceutical standard material.

[0054] In this step, after sorting and refining historical sorting data, the key control indicators for sorting in this embodiment can be described from three dimensions. The first is the sorting path, whose basic variable parameters may include: product layout, product number, storage location number, employee sorting habits, etc. The second is the storage capacity, whose basic variable parameters may include: product storage temperature, product sales speed, product packaging materials, replenishment frequency, storage capacity limits, etc. The third is the workload allocation method, whose basic variable parameters may include: daily order quantity, order variety quantity, order number of pieces, employee sorting efficiency. This step includes: 21) Based on the order type, type layout, location number and sorting habits in the basic variable parameters, the average daily sorting workload is comprehensively calculated according to the preset key sorting control indicators to obtain the optimal sorting path for each sorting user.

[0055] In other words, this step involves establishing the optimal sorting path. Traditional sorting paths are arranged according to user requests, without considering the product layout and order within the sorting area, leading to time and labor consumption. In this application, however, by analyzing historical sorting data, the influencing factors of the sorting path include parameters such as order type, sorting area conditions, product layout, warehouse location numbering, and employee sorting habits. Based on these influencing factors, a comprehensive calculation is performed to obtain the optimal sorting path suitable for each sorting user.

[0056] 211) Variety layout: Usually, the sorting area is divided into three zones according to the storage temperature of the varieties: room temperature variety zone, refrigerated variety zone and frozen variety zone.

[0057] The ambient temperature zone (10℃~30℃), marked as Zone A, with zone numbers from A01 to A20, is generally used to store highly stable substances such as pure chemicals and Chinese medicinal herbs. It should be stored away from light and ventilation, and kept away from heat sources and organic solvents.

[0058] Refrigerated area (2℃~8℃): designated as Zone B, with zone numbers from B01 to B07. Frost-free refrigerators are used to store microbial standards and clinical testing standard substances (such as serum calibrators). Temperature and humidity are monitored in real time to prevent condensation from affecting the integrity of the packaging.

[0059] Freezing zone (-20℃ and below): designated as zone C, with zone numbers from C01 to C07. It uses ultra-low temperature freezers and is generally used to store pharmaceutical standard materials that have extremely high requirements for low temperature, such as enzyme preparations and bioactive substances (e.g., antibodies, cytokines).

[0060] 212) Storage location numbering. Based on the product layout area, this embodiment takes the product storage location in the sorting area as an example, which is subdivided into four levels. However, in actual application, it is not limited to this and includes: temperature zone, horizontal row, vertical column, and storage cell number. For example, A01-02-03-04 represents the ambient temperature zone 01, row 02, column 03, and storage cell 04, etc.

[0061] 213) Sorting Habits. Some sorting users are used to sorting by order, that is, they sort one order before moving on to the next; while other sorting users are used to sorting by product category, that is, they sort one type of product or one temperature range of product before moving on to the next, etc.

[0062] This embodiment breaks away from the traditional method of determining the sorting path based on the order of product types requested by the user. Instead, it proposes a method based on product layout, location numbering, and sorting habits. Through computer algorithms and intelligent analysis (e.g., product layout: ambient temperature first, refrigerated in the middle, frozen last; location numbering: from smallest to largest, i.e., from front to back of the site; user sorting habits: arranged by order type or by the temperature distribution of all products to be sorted that day, etc.), the sorting order is reorganized to derive a sorting implementation strategy (i.e., a sorting implementation plan) suitable for each sorting user. Furthermore, the sorting implementation strategy can be printed in the outbound operation manual, facilitating sorting users to accurately locate the standard materials, thereby improving sorting efficiency.

[0063] 22) Based on the basic variable parameters such as product sales speed, packaging materials, replenishment frequency, and storage compartment capacity limits, the average daily sorting workload is comprehensively calculated according to preset key sorting control indicators to obtain a reasonable storage compartment capacity. This is to indicate the sales volume and replenishment procedure for each standard substance product within a set time.

[0064] In other words, this step involves establishing a reasonable storage capacity. In this embodiment, the storage cell refers to the physical location where standard material varieties are stored, and the capacity of the storage cell is reasonable and effective. If the storage cell capacity is unreasonable, it will affect sorting efficiency and replenishment frequency. Of course, frequently empty storage cells will also affect the work morale of sorting users. Based on this, this embodiment of the application, after analyzing historical storage cell capacity data, finds that the influencing factors of storage cell capacity can include: product sales speed, packaging materials, replenishment frequency, and storage cell capacity limitations. 221) Product sales speed. This application's embodiments, through analysis of historical data over many years, yielded a weighted formula for the product's sales speed:

[0065] In this formula, a1 and a3 (i.e., a) 1-3), a5 (i.e., a in the formula) 1-5 The numbers n1 and n3 represent the sales volume of this variety in the past 1 year, 3 years, and 5 years, respectively, where n1 and n3 are the sales volumes in the formula. 1-3 ), n5 (i.e., n in the formula) 1-5 The numbers 0.5, 0.3, and 0.2 represent the natural day durations of the past 1, 3, and 5 years, respectively, starting from the calculation date. These are weighting coefficients, but this weighting system can be adapted to meet actual needs, and this embodiment does not impose any restrictions.

[0066] 222) Packaging Materials. There are six commonly used packaging materials: 2ml penicillin packaging materials, 7ml penicillin packaging materials, 3ml ampoule packaging materials, 3ml straight tube packaging materials, 10ml straight tube packaging materials, and plastic bottle packaging materials. Depending on the specifications of the packaging materials, the number of standard substances that can be stored in one storage cell (i.e., storage location cell) varies. For example, a storage cell for 2ml penicillin packaging materials can store about 260 units.

[0067] 223) Replenishment Frequency. In this embodiment, after analyzing data over many years, the optimal storage cell capacity was determined to be approximately three months' worth of sales for that product (i.e., the optimal storage capacity per cell is set to approximately three months' worth of sales for the corresponding product). Simultaneously, considering storage cell capacity and packaging materials, the storage cell capacity for each product was determined. Based on this storage cell capacity standard, an algorithm-driven intelligent replenishment program was built. The system automatically pushes replenishment reminders and optimal replenishment quantities periodically. That is, based on the storage cell capacity for each product, and using this as a basis, a replenishment program was designed through computer algorithms to periodically issue replenishment reminders and recommended replenishment quantities. This effectively reduces replenishment frequency, fully optimizes storage space utilization, stabilizes inventory supply, and improves overall sorting efficiency.

[0068] 23) Based on the order quantity, order variety, order quantity, and user sorting efficiency among the basic variable parameters, the average daily sorting workload is comprehensively calculated according to preset key sorting control indicators to obtain a balanced workload allocation method. This allows sorting users to choose the appropriate number of workload units to achieve allocation based on work done.

[0069] In other words, this step involves establishing a balanced workload allocation method. In recent years, the order demand and supply of pharmaceutical standard substances have increased significantly, from 1.8 million units to approximately 3 million units. A balanced workload is crucial for sorting and is an important part of the sorting implementation strategy (sorting implementation plan). After analyzing historical data, the influencing factors of balanced workload were identified, including: order quantity, number of order varieties, and number of units per order. This embodiment, based on years of practical experience in sorting operations, integrates three core workload indicators: total order volume, number of units per order (i.e., total number of goods), and number of order categories. A standardized workload calculation unit is constructed using weighted coefficients, forming a workload unit (i.e., workload unit = number of orders × 0.2 + number of units per order × 0.5 + number of order varieties × 0.3). Simultaneously, considering the efficiency of sorting users, each sorting user can independently assign one or more workload unit tasks, achieving a mechanism of "more work, more pay" and allocation based on performance. In step 103, intelligent reinforcement learning is performed on the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain the sorting implementation strategy for each sorting user.

[0070] In this step, firstly, the optimal sorting path, storage capacity constraints, and workload allocation method for each sorting user are fused according to set weight coefficients to obtain a fusion vector for that user. Then, the fusion vector for each user is input into a trained joint optimization model for reinforcement learning to obtain a sorting implementation strategy suitable for that user. The joint optimization model is obtained through iterative reinforcement learning training based on an artificial intelligence reinforcement learning algorithm. The sorting implementation strategy balances multiple objectives such as sorting timeliness, storage space utilization, personnel workload, and equipment wear and tear.

[0071] In another embodiment, the joint optimization model can be iteratively trained using an artificial intelligence reinforcement learning algorithm to obtain a trained joint optimization model as follows: A training set is obtained, comprising optimal sorting path samples, storage cell capacity samples, and workload allocation method samples for multiple sorting users; and sorting implementation strategy samples for the corresponding sorting users; the optimal sorting path samples, storage cell capacity samples, and workload allocation method samples for each sorting user are fused according to a set weight coefficient to obtain a fused vector sample for the corresponding sorting user; the fused vector sample for each sorting user is input into the joint optimization model for training. During training, the sorting implementation strategy output by the joint optimization model that is adapted to each sorting user is compared with the sorting implementation strategy sample for the corresponding sorting user, the difference is calculated, and the difference is used as the loss value. Based on the loss value, the parameters of the joint optimization model are adjusted through a backpropagation mechanism. After multiple iterations, the joint optimization model converges, resulting in a trained joint optimization model. The joint optimization model can be a large model, a convolutional neural network, or any model suitable for training with an artificial intelligence reinforcement learning algorithm; this example does not impose any restrictions.

[0072] In another embodiment, the optimal sorting path samples, storage cell capacity samples, and workload allocation method samples for each sorting user can be input into the joint optimization model for training. This yields a personalized sorting implementation strategy adapted to each sorting user. The personalized sorting implementation strategy is iteratively updated daily based on the day's work data, generating a daily sorting operation guide. Sorting users are guided to perform sorting operations according to the guide until the shortest sorting path, real-time storage cell supply, and balanced workload allocation for sorting personnel are achieved, resulting in a well-trained joint optimization model. The joint optimization model uses each sorting user as an independent optimization object, and obtains this model through reinforcement learning algorithms by jointly iteratively optimizing the optimal sorting path samples, storage cell capacity samples, and workload allocation method samples for each user. This joint iterative optimization is a global collaborative optimization of the operational dimension, aiming to minimize walking distance, maximize storage cell capacity utilization, and balance the workload of sorting users.

[0073] In this example, by combining the optimal sorting path, reasonable storage capacity, and balanced workload allocation method, the research team used artificial intelligence reinforcement learning algorithm to model and output a sorting implementation plan adapted to each employee. This plan was then incorporated into the sorting operation manual every day, achieving the shortest sorting path, real-time availability of goods in storage cells, and work-based allocation. This significantly improved sorting efficiency, reduced labor intensity, and effectively enhanced sorting quality.

[0074] In step 104, the optimal sorting path and the sorting implementation strategy are sent to the sorting execution terminal so that the sorting execution terminal instructs the sorting user to complete the sorting task of the standard substance according to the optimal sorting path and the sorting implementation strategy.

[0075] In this embodiment, the basic variable parameters for sorting pharmaceutical standard substances and the average daily sorting workload of pharmaceutical standard substances are obtained. Based on the basic variable parameters and the average daily sorting workload, a comprehensive calculation is performed according to preset key sorting control indicators to obtain the optimal sorting path, storage capacity, and workload allocation method suitable for each sorting user in the pharmaceutical standard substances. Intelligent reinforcement learning is then performed on the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain the corresponding sorting implementation strategy for each sorting user. The optimal sorting path and the sorting implementation strategy are sent to the sorting execution terminal so that the sorting execution terminal instructs the sorting user to complete the sorting task of the standard substances according to the optimal sorting path and the sorting implementation strategy. In other words, this embodiment, based on basic variable parameters and the average daily sorting workload, performs comprehensive calculations and sorting according to preset key sorting control indicators, changing the traditional sorting by order demand sequence, average allocation of storage capacity, and average allocation of workload by order quantity, saving manpower and improving sorting efficiency.

[0076] Furthermore, this application embodiment analyzes the sorting process, key nodes, and influencing factors of pharmaceutical standard substances based on demand data and order characteristics from previous years. Using computer algorithms, based on statistics and combined with employees' sorting habits, it obtains key sorting control indicators such as the optimal sorting path, the optimal capacity of the sorting unit, and the most suitable workload for sorting users. It also performs intelligent learning on all key sorting control indicators to obtain personalized sorting implementation plans for each sorting user, which not only saves manpower for sorting users but also improves sorting efficiency.

[0077] Optionally, in another embodiment, based on the above embodiments, the method may further include: receiving, in real time, the actual sorting time, location movement trajectory, and task completion time data transmitted back by the sorting execution terminal after completing the sorting task based on the optimal sorting path and the sorting implementation strategy; and iteratively adjusting the weight coefficients of the optimal sorting path, storage cell capacity, and workload allocation method of the sorting user based on the actual sorting time, location movement trajectory, and task completion time data.

[0078] In another embodiment, it is assumed that the number of pharmaceutical standard substances has reached 5,600, the annual supply has exceeded 3 million units, and the annual order volume has exceeded 120,000 orders, while the number of sorting users has not increased during the same period, resulting in a sharp increase in sorting pressure. By adopting the technical solution of this application embodiment, resources can be rationally allocated, effectively motivating sorting users and efficiently completing the sorting tasks of externally supplied pharmaceuticals within the specified time limit, saving time and improving sorting efficiency.

[0079] In another embodiment, the technical solution adopted in this application can effectively reduce the frequency of replenishment. With the order volume increasing year by year, the replenishment frequency has decreased from nearly 10,000 times five years ago to about 6,500 times now, a significant reduction in frequency, which promotes sorting efficiency, i.e., improves efficiency and speed.

[0080] It should be noted that, for the sake of simplicity, the method embodiments are all described as a series of actions. However, those skilled in the art should understand that this disclosure is not limited to the described order of actions, because according to this application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also understand that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily essential to this application.

[0081] Please also see Figure 2 This is a block diagram of a standard material intelligent sorting device provided in an embodiment of this application. The device includes: an acquisition module 201, a comprehensive calculation module 202, a sorting implementation strategy determination module 203, and a sending module 204, wherein... The acquisition module 201 is used to acquire the basic variable parameters for the sorting of pharmaceutical standard substances, as well as the average daily sorting workload of pharmaceutical standard substances. The comprehensive calculation module 202 is used to perform comprehensive calculations based on the basic variable parameters and the average daily sorting workload, according to the preset key sorting control indicators, to obtain the optimal sorting path, storage capacity and workload allocation method for each sorting user in the pharmaceutical standard material. The sorting implementation strategy determination module 203 is used to perform intelligent reinforcement learning on the optimal sorting path, storage capacity and workload allocation method of each sorting user to obtain the sorting implementation strategy for each sorting user. The sending module 204 is used to send the optimal sorting path and the sorting implementation strategy to the sorting execution terminal, so that the sorting execution terminal can instruct the sorting user to complete the sorting task of the standard substance according to the optimal sorting path and the sorting implementation strategy.

[0082] Optionally, in another embodiment, based on the above embodiment, the acquisition module 201 includes: a statistical analysis module 301 and a data acquisition module 302, the structural block diagram of which is shown below. Figure 3 As shown, where, Statistical analysis module 301 is used to perform statistical analysis on the sorting implementation strategy within a set time period of the pharmaceutical standard substance sorting process, and to obtain the basic variable parameters of the optimal sorting path, storage capacity, and workload allocation method for pharmaceutical standard substance sorting. The data acquisition module 302 is used to collect the average daily sorting workload of pharmaceutical standard substances in real time. The average daily sorting workload includes: daily workload, characteristics of each order, capacity of sorting unit, and sorting habits.

[0083] Optionally, in another embodiment, based on the above embodiment, the comprehensive calculation module 202 includes: a sorting path comprehensive calculation module 401, a storage compartment capacity comprehensive calculation module 402, and a workload allocation comprehensive calculation module 403, the structural block diagram of which is shown below. Figure 4 As shown, where, The sorting path comprehensive calculation module 401 is used to perform comprehensive calculations on the average daily sorting workload based on the order variety, variety layout, storage location number and sorting habits in the basic variable parameters, according to the preset key sorting control indicators, to obtain the optimal sorting path suitable for each sorting user. The storage compartment capacity comprehensive calculation module 402 is used to perform comprehensive calculations on the average daily sorting workload based on the product sales speed, packaging materials, replenishment frequency, and storage compartment capacity limits in the basic variable parameters, according to preset key sorting control indicators, to obtain a reasonable storage compartment capacity. The workload allocation comprehensive calculation module 403 is used to perform comprehensive calculations on the average daily sorting workload based on the order quantity, order variety, order quantity, and user sorting efficiency in the basic variable parameters, and to obtain a balanced workload allocation method.

[0084] Optionally, in another embodiment, based on the above embodiment, the sorting implementation strategy determination module 203 includes: a fusion module 501 and a reinforcement learning module 502, the structural block diagram of which is shown below. Figure 5 As shown, where, The fusion module 501 is used to fuse the optimal sorting path, storage capacity, and workload allocation method of each sorting user according to a set weight coefficient to obtain the fusion vector of the corresponding sorting user. The reinforcement learning module 502 is used to input the fusion vector of each sorting user into the trained joint optimization model for reinforcement learning to obtain a sorting implementation strategy suitable for the corresponding sorting user. The joint optimization model is obtained by reinforcement iterative training based on artificial intelligence reinforcement learning algorithm.

[0085] Optionally, in another embodiment, based on the above embodiments, the apparatus further includes: a training module, used to iteratively train the joint optimization model in advance according to the following manner based on an artificial intelligence reinforcement learning algorithm to obtain a trained joint optimization model.

[0086] Optionally, in another embodiment, based on the above embodiments, the training module includes: The training set acquisition module is used to acquire a training set, which includes optimal sorting path samples, storage cell capacity samples, and workload allocation method samples for multiple sorting users; as well as sorting implementation strategy samples for the corresponding sorting users. The sample fusion module is used to fuse the optimal sorting path sample, storage cell capacity sample, and workload allocation method sample of each sorting user according to the set weight coefficients to obtain the fusion vector sample of the corresponding sorting user. The model training module is used to input the fusion vector samples of each sorting user into the joint optimization model for training. During the training process, the sorting implementation strategy output by the joint optimization model that is adapted to each sorting user is compared with the sorting implementation strategy sample of the corresponding sorting user, the difference is calculated, and the difference is used as the loss value. Based on the loss value, the parameters of the joint optimization model are adjusted through the backpropagation mechanism. After multiple iterations, the joint optimization model converges, and the trained joint optimization model is obtained.

[0087] Optionally, in another embodiment, based on the above embodiments, the device further includes: a receiving module 601 and a weight adjustment module 602, the structural block diagram of which is shown below. Figure 6 As shown, where, The receiving module 601 is used to receive the actual sorting time, location movement trajectory and task completion time data transmitted back in real time by the sorting execution terminal after completing the sorting task based on the optimal sorting path and the sorting implementation strategy. The weight adjustment module 602 is used to iteratively adjust the weight coefficients of the optimal sorting path, storage capacity, and workload allocation method of the sorting user based on the actual sorting time, storage location movement trajectory, and task completion time data.

[0088] Optional, please also see Figure 7An electronic device provided in this application includes: a variable parameter storage module, an input module, an I / O interface, a processing module, a CPU, and an output module. The variable parameter storage module is used to store the basic variable parameters for sorting pharmaceutical standard substances. The input module is used to acquire and input the average daily sorting workload, which includes: daily workload, characteristics of a single order, and capacity of a sorting unit; The I / O interface is connected to the variable parameter storage module, the input module and the calculation module respectively, and is used to transmit the basic variable parameters input by the variable parameter storage module and the average daily sorting workload input by the input module to the calculation module. The computing module, connected to both the CPU and I / O interface module, is used to pre-configure the computing logic for key control indicators. Based on the basic variable parameters and the average daily sorting workload, it performs comprehensive calculations according to the preset computing logic for the corresponding key sorting control indicators to obtain the optimal sorting path, storage capacity, and workload allocation method for each sorting user in the pharmaceutical standard material. Furthermore, it performs intelligent reinforcement learning on the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain the sorting implementation strategy for each sorting user. The CPU, connected to the computing module, is used to control the computing module to perform global sorting optimization logic operations and scheduling according to the pre-configured corresponding key sorting control indicators. The output module, connected to the CPU, is used to receive the sorting implementation strategy generated by the computing module for each sorting user, and to send the sorting implementation strategy to the sorting execution terminal so that the sorting execution terminal can instruct the sorting user to complete the sorting task of standard substances according to the optimal sorting path and the sorting implementation strategy.

[0089] Optionally, embodiments of this application also provide an electronic device, including: It includes a processor, a memory; and a program or instructions stored in the memory and executable on the processor, which, when executed by the processor, implement the steps of the standard material intelligent sorting method as described above.

[0090] Optionally, embodiments of this application also provide a readable storage medium storing a program or instructions that, when executed by a processor of an electronic device, implement the steps of the standard material intelligent sorting method described above.

[0091] Optionally, embodiments of this application also provide a computer program product, including a computer program or instructions, which, when executed by a processor of an electronic device, implement the steps of the intelligent sorting method for standard materials as described in any one of claims 1 to 6.

[0092] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0093] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0094] Figure 8 This is a block diagram of an electronic device 800 provided in an embodiment of this application. For example, the electronic device 800 can be a mobile terminal or a server; in this embodiment, a mobile terminal is used as an example for explanation. For example, the electronic device 800 can be a mobile phone, computer, digital broadcasting terminal, messaging device, game console, tablet device, medical device, fitness equipment, personal digital assistant, etc.

[0095] Reference Figure 8 The electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0096] Processing component 802 typically controls the overall operation of electronic device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0097] Memory 804 is configured to store various types of data to support the operation of electronic device 800. Examples of such data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0098] Power supply component 806 provides power to various components of electronic device 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800.

[0099] Multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of the touch or swipe action but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front-facing camera and / or the rear-facing camera may receive external multimedia data. Each front-facing camera and rear-facing camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

[0100] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when electronic device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0101] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0102] Sensor assembly 814 includes one or more sensors for providing state assessments of various aspects of electronic device 800. For example, sensor assembly 814 may detect the on / off state of device 800, the relative positioning of components such as the display and keypad of electronic device 800, changes in position of electronic device 800 or a component of electronic device 800, the presence or absence of user contact with electronic device 800, orientation or acceleration / deceleration of electronic device 800, and temperature changes of electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0103] Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices. Electronic device 800 can access wireless networks based on communication standards, such as WiFi, carrier networks (such as 2G, 3G, 4G, or 5G), or combinations thereof. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, communication component 816 also includes a near-field communication (NFC) module to facilitate short-range communication. For example, the NFC module may be implemented based on radio frequency identification (RFID) technology, Infrared Data Association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

[0104] In the embodiments, the electronic device 800 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the various processes of the above-described embodiments of the intelligent sorting method for standard materials and achieve the same technical effect. To avoid repetition, it will not be described again here.

[0105] In this embodiment, a readable storage medium is also provided, on which a program or instruction is stored. When executed by a processor of a processing electronic device, the program or instruction implements the steps of the intelligent sorting method for standard materials as described above. The readable storage medium includes a computer-readable storage medium, such as a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0106] In this embodiment, a computer program product is also provided, including a computer program or instructions. When the computer program or instructions are executed by the processor 820 of the electronic device 800, the electronic device 800 performs the various processes of the above-described intelligent sorting method for standard materials and achieves the same technical effect. To avoid repetition, these will not be described again here.

[0107] Figure 9 This application provides a frame of an electronic device 900. Figure 9 As shown in the figure, it includes a processor 901, a communication interface 902, a memory 903, and a communication bus 904. The processor 901, the communication interface 902, and the memory 903 communicate with each other through the communication bus 904. Memory 903 is used to store the processor-executable instructions; The processor 901, when executing executable instructions on the memory 903, implements the method described above.

[0108] In this embodiment, the communication bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used to represent it in the figure, but this does not mean that there is only one bus or one type of bus.

[0109] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0110] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0111] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0112] In another embodiment provided in this application, a readable storage medium is also provided, on which a program or instruction is stored. When the program or instruction is executed by a processor of an electronic device, the processor is able to perform the various processes of the standard material intelligent sorting method embodiment described above, and achieve the same technical effect. To avoid repetition, it will not be described again here. For example, the readable storage medium includes computer-readable storage media, such as ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage devices.

[0113] In another embodiment provided in this application, a computer program product is also provided, including a computer program or instructions. When the computer program or instructions are executed by the processor of an electronic device, they implement the various processes of the above-described embodiment of the intelligent sorting method for standard materials and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0114] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially as a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk (SSD)).

[0115] Figure 10 This is a block diagram of an apparatus 1000 for intelligent sorting of standard materials, provided in an embodiment of this application. For example, apparatus 1000 can be provided as a server. See also... Figure 10 The apparatus 1000 includes a processing component 1022, which further includes one or more processors, and memory resources represented by memory 1032 for storing instructions, such as application programs, that can be executed by the processing component 1022. The application programs stored in memory 1032 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1022 is configured to execute instructions to perform the methods described above.

[0116] Device 1000 may also include a power supply component 1026 configured to perform power management of device 1000, a wired or wireless network interface 1050 configured to connect device 1000 to a network, and an input / output (I / O) interface 1058. Device 1000 can operate on an operating system stored in memory 1032, such as Windows Server™, MacOS X™, Unix™, Linux™, FreeBSD™, or similar.

[0117] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0118] The embodiments of this application have been described above with reference to the accompanying drawings. However, this application is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of this application without departing from the spirit and scope of the claims, and all of these forms are within the protection scope of this application.

Claims

1. A method for intelligent sorting of standard substances, characterized in that, include: Obtain the basic variable parameters for sorting pharmaceutical reference materials, as well as the average daily sorting workload of pharmaceutical reference materials; Based on the aforementioned basic variable parameters and average daily sorting workload, a comprehensive calculation is performed according to the preset key sorting control indicators to obtain the optimal sorting path, storage capacity, and workload allocation method for each sorting user in the pharmaceutical standard material. Intelligent reinforcement learning is performed on the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain the sorting implementation strategy for each sorting user. The optimal sorting path and the sorting implementation strategy are sent to the sorting execution terminal so that the sorting execution terminal can instruct the sorting user to complete the sorting task of the standard substance according to the optimal sorting path and the sorting implementation strategy.

2. The intelligent sorting method for standard substances according to claim 1, characterized in that, The basic variable parameters for sorting pharmaceutical reference materials, and the average daily sorting workload of pharmaceutical reference materials include: Statistical analysis was conducted on the sorting implementation strategy during a set time period in the sorting process of pharmaceutical reference materials to obtain the basic variable parameters of the optimal sorting path, storage capacity, and workload allocation method for pharmaceutical reference materials. The daily average sorting workload of pharmaceutical standard substances is collected in real time. The daily average sorting workload includes: daily workload, characteristics of each order, capacity of sorting unit, and sorting habits.

3. The intelligent sorting method for standard substances according to claim 1, characterized in that, Based on the aforementioned basic variable parameters and average daily sorting workload, and according to preset key sorting control indicators, a comprehensive calculation is performed to obtain the optimal sorting path, storage capacity, and workload allocation method suitable for each sorting user in the pharmaceutical standard materials, including: Based on the order type, type layout, location number and sorting habits in the basic variable parameters, the average daily sorting workload is comprehensively calculated according to the preset key sorting control indicators to obtain the optimal sorting path for each sorting user. Based on the product sales speed, packaging materials, replenishment frequency, and storage compartment capacity limits in the basic variable parameters, the average daily sorting workload is comprehensively calculated according to the preset key sorting control indicators to obtain a reasonable storage compartment capacity. Based on the order quantity, order variety, order quantity, and user sorting efficiency in the basic variable parameters, the average daily sorting workload is comprehensively calculated according to the preset key sorting control indicators to obtain a balanced workload distribution method.

4. The intelligent sorting method for standard substances according to claim 1, characterized in that, The process involves intelligent reinforcement learning of the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain a sorting implementation strategy for each user, including: The optimal sorting path, storage capacity constraints, and workload allocation method for each sorting user are fused according to a set weight coefficient to obtain the fusion vector for the corresponding sorting user. The fusion vector of each sorting user is input into the trained joint optimization model for reinforcement learning to obtain a sorting implementation strategy suitable for the corresponding sorting user. The joint optimization model is obtained by reinforcement iterative training based on artificial intelligence reinforcement learning algorithm.

5. The intelligent sorting method for standard substances according to claim 4, characterized in that, The method further includes: iteratively training the joint optimization model based on an artificial intelligence reinforcement learning algorithm in the following manner to obtain a trained joint optimization model: Obtain a training set, which includes optimal sorting path samples, storage cell capacity samples, and workload allocation method samples for multiple sorting users; as well as sorting implementation strategy samples for the corresponding sorting users; The optimal sorting path sample, storage cell capacity sample, and workload allocation method sample for each sorting user are fused according to the set weight coefficients to obtain the fused vector sample for the corresponding sorting user. The fusion vector sample of each sorting user is input into the joint optimization model for training. During the training process, the sorting implementation strategy output by the joint optimization model that is adapted to each sorting user is compared with the sorting implementation strategy sample of the corresponding sorting user, the difference is calculated, and the difference is used as the loss value. Based on the loss value, the parameters of the joint optimization model are adjusted through the backpropagation mechanism. After multiple iterations, the joint optimization model converges, and the trained joint optimization model is obtained.

6. The intelligent sorting method for standard substances according to any one of claims 1 to 5, characterized in that, The method further includes: After receiving the sorting execution terminal to complete the sorting task based on the optimal sorting path and the sorting implementation strategy, the actual sorting time, the location movement trajectory and the task completion time data are transmitted back in real time. Based on the actual sorting time, location movement trajectory, and task completion time data, the weight coefficients of the optimal sorting path, storage capacity, and workload allocation method for the sorting user are iteratively adjusted.

7. A standard substance intelligent sorting device, characterized in that, include: The acquisition module is used to acquire the basic variable parameters for the sorting of pharmaceutical standard substances, as well as the average daily sorting workload of pharmaceutical standard substances. The comprehensive calculation module is used to perform comprehensive calculations based on the basic variable parameters and the average daily sorting workload, according to the preset key sorting control indicators, to obtain the optimal sorting path, storage capacity and workload allocation method for each sorting user in the pharmaceutical standard material. The sorting implementation strategy determination module is used to perform intelligent reinforcement learning on the optimal sorting path, storage capacity and workload allocation method of each sorting user to obtain the sorting implementation strategy for each sorting user. The sending module is used to send the optimal sorting path and the sorting implementation strategy to the sorting execution terminal, so that the sorting execution terminal can instruct the sorting user to complete the sorting task of the standard substance according to the optimal sorting path and the sorting implementation strategy.

8. An electronic device, characterized in that, include: The variable parameter storage module is used to store the basic variable parameters for sorting pharmaceutical standard substances. The input module is used to acquire and input the average daily sorting workload, which includes: daily workload, characteristics of a single order, and capacity of a sorting unit; The I / O interface is connected to the variable parameter storage module, the input module and the calculation module respectively, and is used to transmit the basic variable parameters input by the variable parameter storage module and the average daily sorting workload input by the input module to the calculation module. The computing module, connected to both the CPU and I / O interface module, is used to pre-configure the computing logic for key control indicators. Based on the basic variable parameters and the average daily sorting workload, it performs comprehensive calculations according to the preset computing logic for the corresponding key sorting control indicators to obtain the optimal sorting path, storage capacity, and workload allocation method for each sorting user in the pharmaceutical standard material. Furthermore, it performs intelligent reinforcement learning on the optimal sorting path, storage capacity, and workload allocation method for each sorting user to obtain the sorting implementation strategy for each sorting user. The CPU, connected to the computing module, is used to control the computing module to perform global sorting optimization logic operations and scheduling according to the pre-configured corresponding key sorting control indicators. The output module, connected to the CPU, is used to receive the sorting implementation strategy generated by the computing module for each sorting user, and to send the sorting implementation strategy to the sorting execution terminal so that the sorting execution terminal can instruct the sorting user to complete the sorting task of standard substances according to the optimal sorting path and the sorting implementation strategy.

9. An electronic device, characterized in that, include: Including processor and memory; And a program or instructions stored on the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the steps of the standard material intelligent sorting method as described in any one of claims 1 to 6.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor of an electronic device, implement the steps of the standard material intelligent sorting method as described in any one of claims 1 to 6.

Images