An intelligent chain store AI-driven resource coordination scheduling method and system

Abstract

This invention relates to the fields of smart chain store management and pharmaceutical cold chain management, providing an AI-driven resource collaborative scheduling method and system for smart chain stores. The method includes: acquiring cold storage capacity information and current cold storage occupancy data for each store's refrigeration equipment; calculating the current cold storage utilization rate based on the current cold storage occupancy data; and acquiring historical sales data, in-transit refrigerated drug data, and store drug processing records for each store. This invention introduces cold storage shortage trend values ​​and cold storage occupancy value values ​​to quantitatively model and dynamically evaluate the cold storage resources of refrigerated drugs in chain pharmacies, realizing a shift from traditional static inventory management to future-oriented, prediction-driven resource scheduling. It can accurately reflect the future changing trends of cold storage resources and, combined with differences in drug status, finely differentiate cold storage occupancy, thereby improving the rationality and foresight of cold storage resource allocation.

Description

Technical Field

[0001] This invention belongs to the field of smart chain store management and pharmaceutical cold chain management technology, and particularly relates to a smart chain store AI-driven resource collaborative scheduling method and system. Background Technology

[0002] In existing technologies, chain pharmacies typically rely on a combination of store-level inventory systems and cold chain monitoring systems to manage refrigerated medicines, including temperature monitoring, inventory recording, and basic inbound and outbound management. The use of cold storage space is mainly controlled through refrigeration equipment capacity configuration and human experience; for example, the number of refrigerated display cases is configured based on historical inventory levels, or temporary allocations or expedited sales are used when cold storage is nearing saturation. Furthermore, while some systems incorporate data analysis, this often focuses on sales forecasting or inventory replenishment decisions, with less emphasis on systematic modeling and collaborative scheduling based on the underlying constraint of cold storage space.

[0003] However, the aforementioned existing technologies typically focus on managing "inventory levels" or "sales demand," without fully considering that cold storage space is a highly constrained physical resource. Its occupancy depends not only on inventory levels but also on the condition of the medications, processing procedures, and future resource changes. For example, in actual operation, when cold chain disruptions, equipment malfunctions, or concentrated deliveries occur, a large number of medications may enter a state of pending inspection, verification, or quarantine. Although these medications cannot be sold, they still require continued occupancy of cold storage space, leading to a rapid shortage of space in stores within a short period. Existing technologies often lack differentiation in the occupancy characteristics of medications in different states and fail to predict future cold storage space occupancy based on in-transit medications and historical sales data. This makes timely and effective resource allocation difficult, easily resulting in uneven utilization of cold storage resources and a shortage of cold storage space in some stores while other stores have surplus space.

[0004] Therefore, the key technical problem that needs to be solved in existing technologies is: how to predict the changes in the occupancy of cold storage space resources within a preset time period by comprehensively considering historical sales data, in-transit refrigerated drug data, and store drug handling records in a chain pharmacy scenario, and to conduct a refined quantitative assessment of cold storage space occupancy based on differences in drug status, thereby constructing an evaluation index that reflects the degree of cold storage space shortage, and on this basis, realizing cross-store collaborative scheduling and multi-strategy processing. This invention addresses the above problems by constructing a cold storage space shortage trend value and a cold storage space occupancy value value, thereby achieving dynamic assessment and optimized scheduling of cold storage space resources, improving the utilization efficiency of cold storage space resources and enhancing overall operational performance. Summary of the Invention

[0005] The purpose of this invention is to provide an AI-driven resource collaborative scheduling method and system for smart chain stores, aiming to solve the problems mentioned in the background art.

[0006] This invention is implemented as follows: an AI-driven resource collaborative scheduling method for smart chain stores, the method comprising:

[0007] Obtain information on the cold storage capacity of each store's refrigeration equipment and the current cold storage occupancy data. Calculate the current cold storage utilization rate based on the current cold storage occupancy data. Obtain historical sales data, in-transit refrigerated medicine data, and store medicine handling record data for each store.

[0008] Based on historical sales data and data on refrigerated medicines in transit, the trend of cold storage space occupancy in each store within a preset time period is predicted, and the cold storage space shortage trend value of each store within the preset time period is calculated in combination with the current cold storage space utilization rate.

[0009] The refrigerated medicines in the store are classified into four states: normal state, pending inspection state, pending verification state, and quarantine state.

[0010] Based on the drug status, the number of cold storage units occupied, the predicted duration of occupancy, and the cold storage shortage trend value, the cold storage occupancy value corresponding to each drug is calculated. The number of cold storage units occupied is determined based on the preset storage occupancy parameters corresponding to the drug. The occupancy duration is predicted from historical sales data or store drug processing records based on the drug status.

[0011] Based on the cold storage space occupancy value of each drug, a cold storage space release priority sequence is generated. When the cold storage space shortage trend value exceeds the preset threshold, cold storage space resource scheduling is performed according to the cold storage space release priority sequence to adjust the distribution or processing order of drugs among stores.

[0012] As a further limitation of the technical solution of this invention, the steps of predicting the trend of cold storage space occupancy in each store within a preset time period based on historical sales data and data on refrigerated medicines in transit, and calculating the cold storage space shortage trend value of each store within the preset time period in combination with the current cold storage space utilization rate, include:

[0013] Based on the historical sales data of each store, predict the expected sales volume of various refrigerated medicines within a preset time period, and determine the number of refrigerated spaces that can be released within the preset time period based on the expected sales volume.

[0014] Based on the data of refrigerated medicines in transit for each store, determine the number of additional cold storage spaces required for the refrigerated medicines expected to arrive within a preset time.

[0015] Based on the number of available cold storage spaces and the number of newly occupied cold storage spaces, determine the future occupancy changes of cold storage resources in each store within a preset time period;

[0016] By integrating future occupancy change information with the current cooling space utilization rate, the cooling space shortage trend value of each store within a preset time period can be obtained.

[0017] As a further limitation of the technical solution of this invention embodiment, the cold storage space occupancy value of each drug is calculated based on the drug status, the number of cold storage space occupancy units, the predicted occupancy duration, and the cold storage space shortage trend value. The number of cold storage space occupancy units is determined based on the preset storage space occupancy parameters corresponding to the drug. The step of predicting the occupancy duration based on the drug status from historical sales data or store drug processing record data includes:

[0018] Based on the pre-defined correspondence between drug status and status weight coefficient, determine the status weight coefficient corresponding to each drug.

[0019] Based on the preset storage space parameters corresponding to each drug, determine the number of cold storage units occupied by each drug.

[0020] Based on the status of the medicine, select the corresponding data from historical sales data or store medicine handling records, predict the occupancy duration of each medicine, and calculate the basic occupancy based on the number of cold storage units occupied and the predicted occupancy duration.

[0021] The cold space shortage correction coefficient is determined based on the cold space shortage trend value;

[0022] The value of cold space occupancy for each drug is obtained by combining the basic occupancy amount, the state weight coefficient, and the cold space tension correction coefficient.

[0023] As a further limitation of the technical solution of this invention, the step of generating a cold storage space release priority sequence based on the cold storage space occupancy value corresponding to each medicine, and when the cold storage space shortage trend value exceeds a preset threshold, performing cold storage space resource scheduling according to the cold storage space release priority sequence to adjust the distribution or processing order of medicines among stores includes:

[0024] Based on the value of each medicine's corresponding cold storage space occupancy, the refrigerated medicines in the target store are sorted to generate a cold storage space release priority sequence.

[0025] According to the cold space release priority sequence, drugs to be processed are selected sequentially starting from drugs with higher priority, until the number of cold spaces released reaches the target release number or the cold space tension trend value drops below the preset threshold, thus obtaining a set of drugs to be processed.

[0026] When the cold space shortage trend value of the target store is detected to exceed a preset threshold, the cold space resource scheduling process of the target store is triggered.

[0027] Based on the status of each drug in the set of drugs to be processed, the corresponding scheduling method is determined, wherein the scheduling method includes at least one of cross-store transfer, priority verification and disposal, and adjustment of the order of entry into the warehouse;

[0028] When the scheduling method is cross-store transfer, the target receiving store is determined based on the cold storage capacity information and current cold storage utilization rate of other stores, and the corresponding medicines are transferred to the target receiving store; when the scheduling method is priority verification and disposal, the verification or disposal process is initiated first for medicines in the status of being verified or in the isolation status; when the scheduling method is adjustment of the warehousing order, the warehousing order of medicines in the status of being inspected is postponed or rearranged.

[0029] After completing the allocation of cooling space resources, update the current occupancy status and utilization rate of each store's cooling space.

[0030] A smart chain store AI-driven resource collaborative scheduling system, the system comprising:

[0031] The data acquisition module is used to acquire information on the cold storage capacity of each store's refrigeration equipment and the current cold storage occupancy data. Based on the current cold storage occupancy data, it calculates the current cold storage utilization rate and acquires historical sales data, in-transit refrigerated medicine data, and store medicine handling record data for each store.

[0032] The trend prediction module is used to predict the trend of cold storage space occupancy in each store within a preset time period based on historical sales data and data on refrigerated medicines in transit, and to calculate the cold storage space shortage trend value of each store within the preset time period in combination with the current cold storage space utilization rate.

[0033] The status classification module is used to classify the status of refrigerated medicines in the store. The status includes normal status, pending inspection status, pending verification status, and isolation status.

[0034] The value calculation module is used to calculate the cold space occupancy value of each drug based on the drug status, the number of cold space occupancy units, the predicted occupancy duration, and the cold space shortage trend value. The number of cold space occupancy units is determined based on the preset storage occupancy parameters of the drug. The occupancy duration is predicted from historical sales data or store drug processing record data based on the drug status.

[0035] The scheduling and execution module is used to generate a cold space release priority sequence based on the cold space occupancy value of each drug. When the cold space shortage trend value exceeds the preset threshold, the cold space resource scheduling is executed according to the cold space release priority sequence to adjust the distribution or processing order of drugs among stores.

[0036] As a further limitation of the technical solution of this embodiment of the invention, the trend prediction module specifically includes:

[0037] The sales forecasting unit is used to predict the expected sales volume of various refrigerated medicines within a preset time period based on the historical sales data of each store, and to determine the number of refrigerated spaces that can be released within the preset time period based on the expected sales volume.

[0038] The in-transit calculation unit is used to determine the number of new cold storage spaces to be occupied for refrigerated medicines expected to arrive within a preset time, based on the in-transit refrigerated medicine data of each store.

[0039] The change determination unit is used to determine the future occupancy change information of each store's cold space resources within a preset time period based on the number of available cold space units and the number of newly occupied cold space units.

[0040] The trend calculation unit is used to integrate future occupancy change information with the current cold space utilization rate to calculate the cold space shortage trend value of each store within a preset time.

[0041] As a further limitation of the technical solution of this embodiment of the invention, the value calculation module specifically includes:

[0042] The weight determination unit is used to determine the state weight coefficient corresponding to each drug based on the preset correspondence between drug state and state weight coefficient.

[0043] The space determination unit is used to determine the number of cold storage space occupancy units corresponding to each drug based on the preset storage space occupancy parameters corresponding to the drug.

[0044] The time-occupancy prediction unit is used to select corresponding data from historical sales data or store drug processing records based on the drug status, predict the occupancy duration of each drug, and calculate the basic occupancy amount based on the number of cold space occupancy units and the predicted occupancy duration.

[0045] The correction calculation unit is used to determine the cold space tension correction coefficient based on the cold space tension trend value;

[0046] The value calculation unit is used to combine the basic occupancy, state weight coefficient, and cold space tension correction coefficient to calculate the cold space occupancy value corresponding to each drug.

[0047] As a further limitation of the technical solution of this embodiment of the invention, the scheduling execution module specifically includes:

[0048] The sorting generation unit is used to sort the refrigerated medicines in the target store according to the cold storage space occupancy value of each medicine, and generate a cold storage space release priority sequence.

[0049] The set selection unit is used to select drugs to be processed sequentially from drugs with higher priority according to the cold position release priority sequence, until the number of cold positions released reaches the target release number or the cold position tension trend value drops below the preset threshold, thus obtaining a set of drugs to be processed.

[0050] The scheduling triggering unit is used to trigger the cold space resource scheduling process of the target store when the cold space tension trend value of the target store is detected to exceed a preset threshold.

[0051] The strategy determination unit is used to determine the corresponding scheduling method based on the drug status of each drug in the set of drugs to be processed, wherein the scheduling method includes at least one of cross-store transfer, priority verification and disposal, and adjustment of the order of entry into the warehouse;

[0052] The strategy execution unit is used to determine the target receiving store based on the cold storage capacity information and current cold storage utilization rate of other stores when the scheduling method is cross-store transfer, and to transfer the corresponding medicines to the target receiving store; when the scheduling method is priority verification and disposal, the verification or disposal process is initiated first for medicines in the status of pending verification or isolation; when the scheduling method is warehousing order adjustment, the warehousing order of medicines in the status of pending inspection is delayed or rearranged.

[0053] The status update unit is used to update the current occupancy status and utilization rate of each store after the cold space resource scheduling is completed.

[0054] Compared with existing technologies, this invention introduces cold storage space shortage trend values ​​and cold storage space occupancy value values ​​to quantitatively model and dynamically evaluate cold storage space resources for refrigerated medicines in chain pharmacies, realizing a transformation from traditional static inventory management to future-oriented, prediction-driven resource scheduling. By integrating historical sales data, in-transit refrigerated medicine data, and store medicine handling records, it can accurately reflect the future changing trends of cold storage space resources and, combined with differences in medicine status, finely differentiate cold storage space occupancy, thereby improving the rationality and foresight of cold storage space resource allocation. Simultaneously, this invention achieves cross-store collaborative scheduling and multi-strategy processing based on priority sequences, effectively alleviating cold storage space shortages and reducing the risk of resource congestion caused by cold chain anomalies or concentrated arrivals. This solution is applicable to chain pharmacies, pharmaceutical retail, and cold chain management scenarios, and has good prospects for widespread application. Attached Figure Description

[0055] Figure 1 A flowchart of the method provided in the embodiments of the present invention;

[0056] Figure 2 This is a flowchart illustrating the calculation of the cold space shortage trend value in the method provided in this embodiment of the invention;

[0057] Figure 3 This is a flowchart illustrating the calculation of the cold storage space occupancy value in the method provided in this embodiment of the invention;

[0058] Figure 4 This is a flowchart illustrating the process of determining and executing a scheduling method in the embodiment of the present invention.

[0059] Figure 5 Application architecture diagram of the system provided in the embodiments of the present invention;

[0060] Figure 6 This is a structural block diagram of the trend prediction module in the system provided in the embodiments of the present invention;

[0061] Figure 7 This is a structural block diagram of the value calculation module in the system provided in the embodiments of the present invention;

[0062] Figure 8 This is a structural block diagram of the scheduling and execution module in the system provided in the embodiment of the present invention. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0064] Figure 1 A flowchart of the method provided by an embodiment of the present invention is shown.

[0065] Specifically, an AI-driven resource collaborative scheduling method for smart chain stores includes the following steps:

[0066] Step S100: Obtain the cold space capacity information and current cold space occupancy data of the refrigeration equipment in each store; calculate the current cold space utilization rate based on the current cold space occupancy data; and obtain the historical sales data, in-transit refrigerated medicine data, and store medicine processing record data of each store.

[0067] In this embodiment of the invention, the invention is applied to the management and resource scheduling of refrigerated medicines in the context of chain pharmacies, specifically involving the intelligent collaborative scheduling of cold storage space resources in store refrigeration equipment. With the development of large-scale operations in chain pharmacies, the proportion of refrigerated medicines (such as biological agents, insulin drugs, and some special preparations requiring low-temperature storage) in each store is gradually increasing. However, the capacity of refrigeration equipment has significant physical constraints, making cold storage space resources a key resource affecting the storage, turnover, and fulfillment capabilities of medicines. The "AI-driven resource collaborative scheduling method for smart chain stores" proposed in this invention is specifically designed for this type of scenario. By introducing data-driven and predictive analysis mechanisms, it achieves dynamic optimization of cold storage space resources across multiple stores.

[0068] Specifically, the "AI-driven" approach in this invention does not simply refer to a specific algorithm model. Rather, it refers to the process of modeling, analyzing, and predicting multi-source data, including historical sales data, in-transit refrigerated drug data, and store drug handling records, to obtain key indicators reflecting future trends in cold storage resources (such as cold storage shortage trend values), and then using these indicators to drive subsequent resource scheduling decisions. In this way, the traditional cold chain management method based on experience or static rules is transformed into an intelligent scheduling method based on data prediction and dynamic optimization, thereby improving the overall resource utilization efficiency of chain pharmacies.

[0069] Furthermore, the core research point of this invention lies in the fact that, in existing technologies, refrigerated medicine management typically focuses on temperature monitoring, inventory management, and storage optimization within a single store, while rarely considering systematic modeling and scheduling from the perspective of "cold storage space resources." Especially when cold chain anomalies occur (such as equipment failure, temperature exceeding limits, etc.) or business fluctuations occur (such as concentrated arrivals, sales peaks, etc.), a large number of medicines may simultaneously enter a state of pending verification, pending inspection, or isolation. Although these medicines are temporarily unsaleable, they still continuously occupy cold storage space resources, leading to a large-scale occupation or even shortage of cold storage space resources in a short period. Existing technologies typically do not differentiate the cold storage space occupancy characteristics of medicines in different states, nor do they consider the release and new occupancy of cold storage space in the future, thus lacking an effective resource scheduling mechanism. This invention solves the above problems by introducing indicators such as cold storage space utilization rate, future occupancy trends, and cold storage space shortage trends to establish a future-oriented cold storage space resource prediction and scheduling model.

[0070] In this step, the first step is to obtain the cold storage capacity information of the refrigeration equipment in each store. The cold storage capacity information is used to characterize the maximum storage capacity that the corresponding refrigeration equipment can provide, and can be expressed in the form of the number of cold storage units, the number of standard storage units, or the equivalent storage volume. This information is usually obtained from the equipment configuration parameters or the equipment ledger data pre-set in the store system.

[0071] Simultaneously, the current cold storage space occupancy data is obtained. This data represents the number of cold storage spaces occupied by medicines in the refrigeration equipment of each store at the current moment. It can be obtained by statistically analyzing the storage space occupancy of refrigerated medicines in the store's inventory system. For example, based on the preset storage space occupancy parameters corresponding to the medicines, the occupancy status of each medicine can be converted into a unified cold storage space unit for aggregation.

[0072] After obtaining the above data, the current cooling space utilization rate is calculated based on the current occupancy data. Specifically, the current cooling space utilization rate can be obtained by comparing the current number of occupied cooling spaces with the cooling space capacity information, reflecting the current utilization level of cooling space resources in the store. For example, a high cooling space utilization rate indicates that the store's cooling space resources are becoming scarce; a low utilization rate indicates that there is still some redundant cooling space. This indicator is subsequently used to integrate with future occupancy trends to determine the scarcity of cooling space resources.

[0073] In addition, historical sales data from each store is acquired. This historical sales data reflects the sales performance of various refrigerated medicines over a specific historical period, including information such as sales volume, sales frequency, and sales time distribution. By analyzing this data, the sales trends of various medicines in the future can be predicted, thereby estimating the corresponding cold storage release.

[0074] Simultaneously, data on refrigerated medicines in transit is acquired. This data represents information on refrigerated medicines that have been delivered from upstream but have not yet been stored at the store, including estimated arrival time, type of medicine, and quantity. This data is used to predict the occupancy of new cold storage spaces in the near future.

[0075] Furthermore, data on drug processing records in stores is also acquired. This data reflects the processing of drugs within the store, including information such as warehousing records, duration of pending inspection records, records of pending verification or isolation treatment, and completion times. This type of data allows for analysis of the duration characteristics of drugs in different states within the cold storage area, providing a basis for predicting subsequent occupancy durations.

[0076] Furthermore, the AI-driven resource collaborative scheduling method for smart chain stores also includes the following steps:

[0077] Step S200: Based on historical sales data and data on refrigerated medicines in transit, predict the trend of cold storage space occupancy in each store within a preset time period, and calculate the cold storage space shortage trend value of each store within the preset time period in combination with the current cold storage space utilization rate.

[0078] Specifically, Figure 2 A flowchart for calculating the cold spot tension trend value is shown.

[0079] The process of predicting the occupancy trend of refrigerated storage space in each store within a preset time period, based on historical sales data and data on refrigerated medicines in transit, and calculating the refrigeration space shortage trend value for each store within the preset time period based on the current refrigeration space utilization rate, specifically includes the following steps:

[0080] Step S201: Based on the historical sales data of each store, predict the expected sales volume of various refrigerated medicines within a preset time period, and determine the number of refrigerated spaces that can be released within the preset time period based on the expected sales volume.

[0081] Step S202: Based on the data of refrigerated medicines in transit for each store, determine the number of new cold storage spaces to be occupied for the refrigerated medicines expected to arrive within a preset time.

[0082] Step S203: Based on the number of available cold storage spaces and the number of newly occupied cold storage spaces, determine the future occupancy change information of cold storage space resources in each store within a preset time period;

[0083] Step S204: The future occupancy change information is combined with the current cold space utilization rate to calculate the cold space shortage trend value of each store within a preset time.

[0084] In this embodiment of the invention, the changes in cold storage space resources of each store within a preset time period are predicted and modeled, and a cold storage space tension trend value that can reflect the degree of tension of cold storage space is obtained, thereby providing a basis for subsequent cold storage space resource scheduling.

[0085] Specifically, historical sales data can be statistically analyzed. For example, the average sales rate can be calculated by drug category and time window (e.g., daily or weekly), or a weighted forecast can be made by combining recent sales trends to obtain the expected sales volume of various refrigerated drugs within a preset time period. After obtaining the expected sales volume, the expected sales volume can be converted into the corresponding number of refrigeration space units to be released, based on the number of refrigeration space units occupied by each type of drug. That is, the more drugs expected to be sold, the greater the number of refrigeration space units to be released. For example, if 10 boxes of a certain type of drug are expected to be sold within a preset time period, and each box occupies 1 refrigeration space unit, then 10 refrigeration space units can be released.

[0086] Specifically, based on the estimated arrival time of refrigerated medicines in transit, medicines that will arrive at the store within a preset time can be selected. Then, combined with the number of cold storage units occupied by each medicine, the number of cold storage units required after the medicine is put into storage can be calculated. For example, if a batch of medicines in transit is expected to arrive in 20 boxes within a preset time, and each box occupies 1 cold storage unit, then the corresponding additional cold storage units will be 20.

[0087] Specifically, the net change in cold storage space resources can be obtained by comparing or calculating the difference between the newly added occupied cold storage spaces and the number of available cold storage spaces. For example, if the newly occupied space is 20 units and the available space is 10 units, the net change is an increase of 10 cold storage spaces, indicating that the future occupancy of cold storage spaces will increase; conversely, if the available space is greater than the newly occupied space, it indicates that the occupancy of cold storage spaces will decrease.

[0088] Specifically, the current utilization rate of cooling spaces can be used as the baseline for the current situation, and information on future occupancy changes can be used as a trend adjustment factor. The cooling space shortage trend value can be obtained through weighted calculation or function mapping. For example, when the current utilization rate of cooling spaces is already high and future occupancy is still on an increasing trend, the calculated cooling space shortage trend value will be significantly higher, indicating that cooling space resources are becoming scarce; while when the current utilization rate is low or future occupancy is on a decreasing trend, the cooling space shortage trend value will be relatively low.

[0089] Through the above steps, a comprehensive assessment of the "current status and future changes" of cold storage space resources can be achieved, thereby more accurately reflecting the urgency of cold storage space resources in stores within a preset time period, and providing support for subsequent priority ranking and scheduling based on the value of cold storage space occupancy.

[0090] Furthermore, the AI-driven resource collaborative scheduling method for smart chain stores also includes the following steps:

[0091] Step S300: Classify the status of refrigerated medicines in the store, including normal status, pending inspection status, pending verification status, and isolation status.

[0092] In this embodiment of the invention, the refrigerated medicines in the store are classified into different states. The purpose of this classification is to distinguish the schedulability and processing constraints of different medicines during the occupation of refrigerated space resources, thereby providing a basis for the subsequent calculation of the value of refrigerated space occupation and the scheduling of refrigerated space resources. Specifically, medicines in different states have significant differences in terms of whether they are movable, whether they can be prioritized for processing, and the time they occupy refrigerated space. Without state classification, it is impossible to carry out refined management and optimized scheduling of refrigerated space resources.

[0093] In practical applications, refrigerated medicines in stores can be categorized into four states based on their current business status: normal, pending inspection, pending verification, and isolated. Medicines in the normal state refer to those that have completed inspection and are ready for sale. These medicines have high flexibility in terms of refrigeration space allocation; for example, when refrigeration resources are scarce, they can be released through sales or inter-store transfers. Medicines in the pending inspection state are those that have arrived but have not yet completed inspection. According to relevant regulations, these medicines typically need to be temporarily stored under refrigeration and should not be moved arbitrarily; their refrigeration space allocation is subject to certain rigid constraints. Medicines in the pending verification state are those that have entered the verification process due to abnormal temperatures, record discrepancies, or other quality concerns. These medicines cannot be sold or circulated arbitrarily before verification is completed, but they still require refrigeration space. Medicines in the isolated state are those that have been determined to pose a quality risk and need to be stored separately. These medicines typically need to be refrigerated in an isolated area, occupying refrigeration space but not participating in normal circulation.

[0094] For example, in a store, if some refrigerated medicines enter a pending inspection state due to a brief temperature anomaly in the freezer, these medicines need to continue occupying refrigeration space and are difficult to release in the short term. Meanwhile, medicines in normal condition can release refrigeration space resources by prioritizing their sale or allocating them to other stores. For newly arrived medicines awaiting inspection, their warehousing may need to be delayed or their warehousing order adjusted. This status classification clarifies the processing priority and operational space for different medicines in refrigeration space resource allocation, thus providing support for subsequent ranking and scheduling decisions based on the value of refrigeration space occupancy.

[0095] Furthermore, the AI-driven resource collaborative scheduling method for smart chain stores also includes the following steps:

[0096] Step S400: Based on the drug status, the number of cold storage units occupied, the predicted occupancy duration, and the cold storage shortage trend value, calculate the cold storage occupancy value corresponding to each drug. The number of cold storage units occupied is determined based on the preset storage occupancy parameters corresponding to the drug. The occupancy duration is predicted from historical sales data or store drug processing record data based on the drug status.

[0097] Specifically, Figure 3 A flowchart for calculating the value of a cold storage space is shown.

[0098] The process involves calculating the cold storage space occupancy value for each drug based on its status, the number of cold storage space occupancy units, the predicted occupancy duration, and the cold storage space shortage trend. The number of cold storage space occupancy units is determined based on preset storage space occupancy parameters for the drug. The occupancy duration is predicted from historical sales data or store drug processing records based on the drug's status, and specifically includes the following steps:

[0099] Step S401: Determine the state weight coefficient corresponding to each drug based on the preset correspondence between drug state and state weight coefficient.

[0100] Step S402: Based on the preset storage space parameters corresponding to the medicines, determine the number of cold storage space units occupied by each medicine.

[0101] Step S403: Based on the drug status, select corresponding data from historical sales data or store drug processing record data, predict the occupancy duration for each drug, and calculate the basic occupancy amount based on the number of cold space occupancy units and the predicted occupancy duration.

[0102] Step S404: Determine the cold space tension correction coefficient based on the cold space tension trend value;

[0103] Step S405: Combine the basic occupancy amount, state weight coefficient, and cold space tension correction coefficient to calculate the cold space occupancy value corresponding to each drug.

[0104] In this embodiment of the invention, the "occupancy value" of different drugs during the cold storage resource occupancy process is quantitatively evaluated, thereby providing a basis for prioritizing the release of cold storage spaces. The cold storage space occupancy value comprehensively considers the drug status, occupancy scale, occupancy time, and overall cold storage space tension, so that scheduling decisions are not only based on the current occupancy situation but also reflect future impacts.

[0105] Specifically, a mapping relationship between states and weights can be pre-set in the system. For example, the state of isolation has a higher weight coefficient, followed by the state of pending verification, then the state of pending inspection, and the normal state has a relatively lower weight coefficient. This method allows drugs that occupy cold slots but have limited processing or higher priority to have a greater impact in the calculation. For example, for two drugs that also occupy cold slots, if one is in an isolated state, its state weight coefficient can be set higher than that of the normal state, thus reflecting its priority processing requirement in subsequent calculations.

[0106] Specifically, the system can pre-configure corresponding storage space parameters for different drugs, such as converting drugs into a uniform number of cold storage units according to packaging specifications, volume, or storage method. For example, small-sized drugs may correspond to 1 cold storage unit, while large-sized or specially packaged drugs may correspond to 2 or more cold storage units, thereby achieving uniform quantification of cold storage space occupancy for different drugs.

[0107] Specifically, for drugs in normal condition, the time required for them to go from their current inventory status to being sold and released from the cold storage can be predicted based on historical sales data (such as average sales rate). For drugs awaiting inspection, verification, or quarantine, the duration of their occupation of the cold storage space can be predicted based on store drug processing record data (such as historical verification duration, quarantine processing cycle, etc.). After obtaining the occupation duration, it is combined with the number of units occupied in the cold storage space, for example, by multiplication, to obtain the basic occupation amount, which is used to characterize the degree of occupation of cold storage space resources by the drug within a certain period of time.

[0108] Specifically, a corresponding correction coefficient can be set according to the magnitude of the cold space tension trend value. For example, when the cold space tension trend value is high, the correction coefficient is increased to amplify the impact of each drug's occupation on the overall scheduling; when the cold space tension trend value is low, the correction coefficient is relatively small to make the scheduling smoother, thereby realizing the dynamic adjustment of the scheduling strategy under different tension levels.

[0109] Specifically, the above factors can be integrated through weighted summation or multiplication. For example, the basic occupancy rate can be multiplied by the state weight coefficient and the cold space tension correction coefficient to obtain the final cold space occupancy value. The larger this value, the greater the impact of the corresponding drug on the occupancy of cold space resources in the current and future period, and it should be given priority in subsequent scheduling. In this way, a comprehensive assessment of the cold space occupancy of different drugs can be achieved, making scheduling decisions more scientific and reasonable.

[0110] Furthermore, the AI-driven resource collaborative scheduling method for smart chain stores also includes the following steps:

[0111] Step S500: Generate a cold storage release priority sequence based on the cold storage occupancy value of each drug. When the cold storage shortage trend value exceeds a preset threshold, perform cold storage resource scheduling according to the cold storage release priority sequence to adjust the distribution or processing order of drugs among stores.

[0112] Specifically, Figure 4 A flowchart is shown to determine the scheduling method and execute the scheduling.

[0113] The process involves generating a cold storage space release priority sequence based on the cold storage space occupancy value of each drug. When the cold storage space shortage trend value exceeds a preset threshold, cold storage space resource scheduling is executed according to the cold storage space release priority sequence to adjust the distribution or processing order of drugs among various stores. This specifically includes the following steps:

[0114] Step S501: Based on the cold storage space occupancy value of each medicine, sort the refrigerated medicines in the target store and generate a cold storage space release priority sequence.

[0115] Step S502: According to the cold position release priority sequence, select the drugs to be processed sequentially starting from the drugs with higher priority, until the number of cold positions released reaches the target release number or the cold position tension trend value drops below the preset threshold, and obtain the set of drugs to be processed.

[0116] Step S503: When the cold space shortage trend value of the target store is detected to exceed the preset threshold, the cold space resource scheduling process of the target store is triggered.

[0117] Step S504: Determine the corresponding scheduling method based on the drug status of each drug in the set of drugs to be processed, wherein the scheduling method includes at least one of cross-store transfer, priority verification and disposal, and adjustment of the order of entry into the warehouse;

[0118] Step S505: When the scheduling method is cross-store transfer, the target receiving store is determined based on the cold storage capacity information and current cold storage utilization rate of other stores, and the corresponding medicines are transferred to the target receiving store; when the scheduling method is priority verification and disposal, the verification or disposal process is initiated first for medicines in the verification or isolation status; when the scheduling method is warehouse entry order adjustment, the warehouse entry order of medicines in the inspection status is postponed or rearranged.

[0119] Step S506: After completing the cold storage resource scheduling, update the current cold storage occupancy status and current cold storage utilization rate of each store.

[0120] In this embodiment of the invention, when the cold storage shortage trend value exceeds a preset threshold, based on the cold storage occupancy value calculated above, the refrigerated medicines in the store are systematically screened and corresponding scheduling operations are performed, thereby realizing the dynamic release and optimized allocation of cold storage resources.

[0121] Specifically, the cold storage space occupancy value corresponding to each drug can be used as the sorting criterion, arranged in descending order to form a priority sequence. The higher the cold storage space occupancy value, the greater the impact of the drug on the occupation of cold storage space resources in the current and preset time period, and it should be included in the scheduling scope first. For example, if a certain isolated drug has a long occupation time and a high trend of cold storage space shortage, its corresponding cold storage space occupancy value is large, so it will be ranked at the front of the sequence.

[0122] In step S502, according to the cold storage release priority sequence, drugs to be processed are selected sequentially, starting with drugs of higher priority, to gradually build a set of drugs to be processed. During the selection process, the number of cold storage units to be released or the cold storage tension trend value can be used as a stopping condition. That is, when the cumulative number of cold storage units that can be released reaches the target release quantity, or when the estimated cold storage tension trend value drops below a preset threshold after processing, the selection stops. This method avoids over-scheduling. For example, when the system determines that only 10 cold storage units need to be released to alleviate the tension, only a few drugs in the top priority sequence are selected, ensuring that their corresponding cold storage release amounts reach the target.

[0123] In step S503, when the cold space shortage trend value of the target store is detected to exceed a preset threshold, the cold space resource scheduling process is triggered. This triggering process can be completed automatically by the system, for example, by periodically calculating or monitoring the cold space shortage trend value in real time, and entering the scheduling stage once the threshold is exceeded.

[0124] In steps S504 and S505, the corresponding scheduling method is determined and executed based on the status of each drug in the set of drugs to be processed. For example, for drugs in normal status, cross-store transfer can be prioritized to transfer them to other stores with lower cold storage utilization rates; for drugs awaiting verification or in isolation status, the verification or disposal process can be prioritized to shorten their occupation time; for drugs awaiting inspection status, their entry into the warehouse can be delayed or the order of entry into the warehouse can be adjusted to avoid them occupying scarce cold storage resources at the current moment.

[0125] After completing the above scheduling operations, update the current occupancy status and utilization rate of each store to reflect the latest resource situation after scheduling and to provide a basis for calculating the next round of occupancy shortage trend value.

[0126] In the above process, the role of AI is mainly reflected in two aspects: First, by calculating the value of cold storage occupancy, multi-dimensional factors (such as drug status, occupancy time, and cold storage sufficiency) are integrated into a unified indicator, making the ranking more comprehensive and forward-looking. Second, when selecting the set of drugs to be processed, the system can dynamically evaluate the impact of different combinations on the cold storage sufficiency trend value based on a predictive model, thereby selecting a better release plan. For example, among multiple optional drug combinations, the system can prioritize the combination that can reduce the cold storage sufficiency trend value below the threshold with the minimum scheduling cost, thereby improving the overall scheduling efficiency.

[0127] Furthermore, Figure 5 An application architecture diagram of the system provided in an embodiment of the present invention is shown.

[0128] In another preferred embodiment of the present invention, an AI-driven resource collaborative scheduling system for smart chain stores includes:

[0129] The data acquisition module 100 is used to acquire the cold space capacity information and current cold space occupancy data of the refrigeration equipment in each store, calculate the current cold space utilization rate based on the current cold space occupancy data, and acquire the historical sales data, in-transit refrigerated medicine data and store medicine processing record data of each store.

[0130] Furthermore, the AI-driven resource collaborative scheduling system for smart chain stores also includes:

[0131] The trend prediction module 200 is used to predict the trend of cold storage space occupancy in each store within a preset time period based on historical sales data and data on refrigerated medicines in transit, and to calculate the cold storage space shortage trend value of each store within the preset time period in combination with the current cold storage space utilization rate.

[0132] Specifically, Figure 6 A structural block diagram of the trend prediction module 200 in the system provided in an embodiment of the present invention is shown.

[0133] In a preferred embodiment provided by the present invention, the trend prediction module 200 specifically includes:

[0134] The sales forecasting unit 201 is used to forecast the expected sales volume of various refrigerated medicines within a preset time period based on the historical sales data of each store, and to determine the number of refrigerated spaces that can be released within the preset time period based on the expected sales volume.

[0135] The in-transit calculation unit 202 is used to determine the number of new cold storage spaces to be occupied for refrigerated medicines expected to arrive within a preset time based on the in-transit refrigerated medicine data of each store.

[0136] The change determination unit 203 is used to determine the future occupancy change information of the cold space resources of each store within a preset time based on the number of available cold spaces and the number of newly occupied cold spaces.

[0137] The trend calculation unit 204 is used to integrate future occupancy change information with the current cold space utilization rate to calculate the cold space shortage trend value of each store within a preset time.

[0138] Furthermore, the AI-driven resource collaborative scheduling system for smart chain stores also includes:

[0139] The status classification module 300 is used to classify the status of refrigerated medicines in the store, including normal status, pending inspection status, pending verification status, and isolation status.

[0140] Furthermore, the AI-driven resource collaborative scheduling system for smart chain stores also includes:

[0141] The value calculation module 400 is used to calculate the cold space occupancy value of each drug based on the drug status, the number of cold space occupancy units, the predicted occupancy duration, and the cold space shortage trend value. The number of cold space occupancy units is determined based on the preset storage occupancy parameters of the drug. The occupancy duration is predicted from historical sales data or store drug processing record data based on the drug status.

[0142] Specifically, Figure 7 A structural block diagram of the value calculation module 400 in the system provided by an embodiment of the present invention is shown.

[0143] In a preferred embodiment provided by the present invention, the value calculation module 400 specifically includes:

[0144] The weight determination unit 401 is used to determine the state weight coefficient corresponding to each drug based on the preset correspondence between drug state and state weight coefficient.

[0145] The space determination unit 402 is used to determine the number of cold space occupancy units corresponding to each drug based on the preset storage space occupancy parameters corresponding to the drug.

[0146] The time-occupancy prediction unit 403 is used to select corresponding data from historical sales data or store drug processing record data according to the drug status, predict the occupancy duration of each drug, and calculate the basic occupancy amount based on the number of cold space occupancy units and the predicted occupancy duration.

[0147] The correction calculation unit 404 is used to determine the cold space tension correction coefficient based on the cold space tension trend value;

[0148] The value calculation unit 405 is used to combine the basic occupancy, state weight coefficient and cold space tension correction coefficient to calculate the cold space occupancy value corresponding to each drug.

[0149] Furthermore, the AI-driven resource collaborative scheduling system for smart chain stores also includes:

[0150] The scheduling execution module 500 is used to generate a cold space release priority sequence based on the cold space occupancy value of each drug. When the cold space tension trend value exceeds the preset threshold, the cold space resource scheduling is executed according to the cold space release priority sequence to adjust the distribution or processing order of drugs among stores.

[0151] Specifically, Figure 8 A structural block diagram of the scheduling execution module 500 in the system provided by an embodiment of the present invention is shown.

[0152] In a preferred embodiment provided by the present invention, the scheduling execution module 500 specifically includes:

[0153] The sorting generation unit 501 is used to sort the refrigerated medicines in the target store according to the cold storage space occupancy value of each medicine, and generate a cold storage space release priority sequence.

[0154] The set selection unit 502 is used to select drugs to be processed sequentially from drugs with higher priority according to the cold position release priority sequence, until the number of cold positions released reaches the target release number or the cold position tension trend value drops below the preset threshold, thus obtaining a set of drugs to be processed.

[0155] The scheduling triggering unit 503 is used to trigger the cold space resource scheduling process of the target store when the cold space tension trend value of the target store is detected to exceed a preset threshold.

[0156] The strategy determination unit 504 is used to determine the corresponding scheduling method based on the drug status of each drug in the set of drugs to be processed, wherein the scheduling method includes at least one of cross-store transfer, priority verification and disposal, and adjustment of the order of entry into the warehouse;

[0157] The strategy execution unit 505 is used to determine the target receiving store based on the cold storage capacity information and current cold storage utilization rate of other stores when the scheduling method is cross-store transfer, and to transfer the corresponding medicines to the target receiving store; when the scheduling method is priority verification and disposal, the verification or disposal process is initiated first for medicines in the status of being verified or in the isolation status; when the scheduling method is warehousing order adjustment, the warehousing order of medicines in the status of being inspected is delayed or rearranged.

[0158] The status update unit 506 is used to update the current occupancy status and current utilization rate of each store after the cold space resource scheduling is completed.

[0159] It should be understood that although the steps in the flowcharts of the various embodiments of the present invention are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the various embodiments may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the sub-steps or stages of other steps.

[0160] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0161] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0162] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

[0163] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A resource collaborative scheduling method driven by AI for smart chain stores, characterized in that, The method includes: Obtain information on the cold storage capacity of each store's refrigeration equipment and the current cold storage occupancy data. Calculate the current cold storage utilization rate based on the current cold storage occupancy data. Obtain historical sales data, in-transit refrigerated medicine data, and store medicine handling record data for each store. Based on historical sales data and data on refrigerated medicines in transit, the trend of cold storage space occupancy in each store within a preset time period is predicted, and the cold storage space shortage trend value of each store within the preset time period is calculated in combination with the current cold storage space utilization rate. The refrigerated medicines in the store are classified into four states: normal state, pending inspection state, pending verification state, and quarantine state. Based on the drug status, the number of cold storage units occupied, the predicted duration of occupancy, and the cold storage shortage trend value, the cold storage occupancy value corresponding to each drug is calculated. The number of cold storage units occupied is determined based on the preset storage occupancy parameters corresponding to the drug. The occupancy duration is predicted from historical sales data or store drug processing records based on the drug status. Based on the cold storage space occupancy value of each drug, a cold storage space release priority sequence is generated. When the cold storage space shortage trend value exceeds the preset threshold, cold storage space resource scheduling is performed according to the cold storage space release priority sequence to adjust the distribution or processing order of drugs among stores.

2. The AI-driven resource collaborative scheduling method for smart chain stores according to claim 1, characterized in that, Based on historical sales data and data on refrigerated medicines in transit, the steps to predict the changing trend of refrigeration space occupancy in each store within a preset time period, and to calculate the refrigeration space shortage trend value for each store within the preset time period based on the current refrigeration space utilization rate, include: Based on the historical sales data of each store, predict the expected sales volume of various refrigerated medicines within a preset time period, and determine the number of refrigerated spaces that can be released within the preset time period based on the expected sales volume. Based on the data of refrigerated medicines in transit for each store, determine the number of additional cold storage spaces required for the refrigerated medicines expected to arrive within a preset time. Based on the number of available cooling spaces and the number of newly occupied cooling spaces, determine the future occupancy changes of cooling space resources in each store within a preset time period; By integrating future occupancy change information with the current cooling space utilization rate, the cooling space shortage trend value of each store within a preset time period can be obtained.

3. The AI-driven resource collaborative scheduling method for smart chain stores according to claim 1, characterized in that, Based on the drug status, the number of cold storage units occupied, the predicted duration of occupancy, and the cold storage shortage trend value, the cold storage occupancy value corresponding to each drug is calculated. The number of cold storage units occupied is determined based on preset storage occupancy parameters corresponding to the drug. The step of predicting the occupancy duration based on the drug status from historical sales data or store drug processing records includes: Based on the pre-defined correspondence between drug status and status weight coefficient, determine the status weight coefficient corresponding to each drug. Based on the preset storage space parameters corresponding to each drug, determine the number of cold storage units occupied by each drug. Based on the status of the medicine, select the corresponding data from historical sales data or store medicine handling records, predict the occupancy duration of each medicine, and calculate the basic occupancy based on the number of cold storage units occupied and the predicted occupancy duration. The cold space shortage correction coefficient is determined based on the cold space shortage trend value; The value of cold space occupancy for each drug is obtained by combining the basic occupancy amount, the state weight coefficient, and the cold space tension correction coefficient.

4. The AI-driven resource collaborative scheduling method for smart chain stores according to claim 1, characterized in that, Based on the occupancy value of each drug's corresponding cold storage space, a cold storage space release priority sequence is generated. When the cold storage space shortage trend value exceeds a preset threshold, cold storage space resource scheduling is performed according to the cold storage space release priority sequence to adjust the distribution or processing order of drugs among various stores. The steps include: Based on the value of each medicine's corresponding cold storage space occupancy, the refrigerated medicines in the target store are sorted to generate a cold storage space release priority sequence. According to the cold space release priority sequence, drugs to be processed are selected sequentially starting from drugs with higher priority, until the number of cold spaces released reaches the target release number or the cold space tension trend value drops below the preset threshold, thus obtaining a set of drugs to be processed. When the cold space shortage trend value of the target store is detected to exceed a preset threshold, the cold space resource scheduling process of the target store is triggered. Based on the status of each drug in the set of drugs to be processed, the corresponding scheduling method is determined, wherein the scheduling method includes at least one of cross-store transfer, priority verification and disposal, and adjustment of the order of entry into the warehouse; When the scheduling method is cross-store transfer, the target receiving store is determined based on the cold storage capacity information and current cold storage utilization rate of other stores, and the corresponding medicines are transferred to the target receiving store; when the scheduling method is priority verification and disposal, the verification or disposal process is initiated first for medicines in the status of being verified or in the isolation status; when the scheduling method is adjustment of the warehousing order, the warehousing order of medicines in the status of being inspected is postponed or rearranged. After completing the allocation of cooling space resources, update the current occupancy status and utilization rate of each store's cooling space.

5. A smart chain store AI-driven resource collaborative scheduling system, characterized in that, The system includes: The data acquisition module is used to acquire information on the cold storage capacity of each store's refrigeration equipment and the current cold storage occupancy data. Based on the current cold storage occupancy data, it calculates the current cold storage utilization rate and acquires historical sales data, in-transit refrigerated medicine data, and store medicine handling record data for each store. The trend prediction module is used to predict the trend of cold storage space occupancy in each store within a preset time period based on historical sales data and data on refrigerated medicines in transit, and to calculate the cold storage space shortage trend value of each store within the preset time period in combination with the current cold storage space utilization rate. The status classification module is used to classify the status of refrigerated medicines in the store. The status includes normal status, pending inspection status, pending verification status, and isolation status. The value calculation module is used to calculate the cold space occupancy value of each drug based on the drug status, the number of cold space occupancy units, the predicted occupancy duration, and the cold space shortage trend value. The number of cold space occupancy units is determined based on the preset storage occupancy parameters of the drug. The occupancy duration is predicted from historical sales data or store drug processing record data based on the drug status. The scheduling and execution module is used to generate a cold space release priority sequence based on the cold space occupancy value of each drug. When the cold space shortage trend value exceeds the preset threshold, the cold space resource scheduling is executed according to the cold space release priority sequence to adjust the distribution or processing order of drugs among stores.

6. The AI-driven resource collaborative scheduling system for smart chain stores according to claim 5, characterized in that, The trend prediction module specifically includes: The sales forecasting unit is used to predict the expected sales volume of various refrigerated medicines within a preset time period based on the historical sales data of each store, and to determine the number of refrigerated spaces that can be released within the preset time period based on the expected sales volume. The in-transit calculation unit is used to determine the number of new cold storage spaces to be occupied for refrigerated medicines expected to arrive within a preset time, based on the in-transit refrigerated medicine data of each store. The change determination unit is used to determine the future occupancy change information of each store's cold space resources within a preset time period based on the number of available cold space units and the number of newly occupied cold space units. The trend calculation unit is used to integrate future occupancy change information with the current cold space utilization rate to calculate the cold space shortage trend value of each store within a preset time.

7. The AI-driven resource collaborative scheduling system for smart chain stores according to claim 5, characterized in that, The value calculation module specifically includes: The weight determination unit is used to determine the state weight coefficient corresponding to each drug based on the preset correspondence between drug state and state weight coefficient. The space determination unit is used to determine the number of cold storage space occupancy units corresponding to each drug based on the preset storage space occupancy parameters corresponding to the drug. The time-occupancy prediction unit is used to select corresponding data from historical sales data or store drug processing records based on the drug status, predict the occupancy duration of each drug, and calculate the basic occupancy amount based on the number of cold space occupancy units and the predicted occupancy duration. The correction calculation unit is used to determine the cold space tension correction coefficient based on the cold space tension trend value. The value calculation unit is used to combine the basic occupancy, state weight coefficient, and cold space tension correction coefficient to calculate the cold space occupancy value corresponding to each drug.

8. The AI-driven resource collaborative scheduling system for smart chain stores according to claim 5, characterized in that, The scheduling execution module specifically includes: The sorting generation unit is used to sort the refrigerated medicines in the target store according to the cold storage space occupancy value of each medicine, and generate a cold storage space release priority sequence. The set selection unit is used to select drugs to be processed sequentially from drugs with higher priority according to the cold position release priority sequence, until the number of cold positions released reaches the target release number or the cold position tension trend value drops below the preset threshold, thus obtaining a set of drugs to be processed. The scheduling triggering unit is used to trigger the cold space resource scheduling process of the target store when the cold space tension trend value of the target store is detected to exceed a preset threshold. The strategy determination unit is used to determine the corresponding scheduling method based on the drug status of each drug in the set of drugs to be processed, wherein the scheduling method includes at least one of cross-store transfer, priority verification and disposal, and adjustment of the order of entry into the warehouse; The strategy execution unit is used to determine the target receiving store based on the cold storage capacity information and current cold storage utilization rate of other stores when the scheduling method is cross-store transfer, and to transfer the corresponding medicines to the target receiving store; when the scheduling method is priority verification and disposal, the verification or disposal process is initiated first for medicines in the status of pending verification or isolation; when the scheduling method is warehousing order adjustment, the warehousing order of medicines in the status of pending inspection is delayed or rearranged. The status update unit is used to update the current occupancy status and utilization rate of each store after the cold storage resource scheduling is completed.

Images