Blood inventory management method and system

Abstract

The invention provides a blood inventory management method and system, and belongs to the field of data processing, and the method comprises the steps: obtaining the actual use amount of each blood product in each week in a plurality of years before the current time of a hospital, obtaining an increment coefficient sequence of the season of the current time and the same season as the season of the current time in a plurality of years before the current time, and obtaining a predicted inventory value of the week of the current time by combining the minimum inventory value of each blood product at the current time; and combining the number and the collection time of each blood product in the blood bank of the hospital at the current time and the storage life of each blood product to obtain the optimal stock value of each blood product in the week where the current time is located. The invention aims to solve the problem that the actual stock amount and the actual demand amount are different when the blood stock is managed through an EOQ model due to the dynamic change of the hospital blood use.

Description

Technical Field

[0001] This invention belongs to the field of data processing, and specifically relates to a blood inventory management method and system. Background Technology

[0003] Currently, when managing blood inventory using the EOQ model, there are drawbacks. The EOQ model aims to minimize total inventory costs under stable demand conditions, while blood demand is dynamic and has time-sensitive characteristics. This can lead to a significant discrepancy between the predicted and actual blood inventory levels under the expected regional blood supply demand, resulting in supply-demand imbalances and resource waste. Summary of the Invention

[0004] To address the problem of a significant discrepancy between actual inventory and actual demand when managing blood inventory using an EOQ model, due to the dynamic changes in blood demand and the shelf life of blood, this invention proposes a blood inventory management method and system.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] Obtain the actual usage of each blood product in the hospital for each week in the years prior to the current time, the quantity and collection time of each blood product in the hospital's blood bank at the current time, the shelf life of each blood product, and the minimum inventory value of each blood product in the hospital at the current time.

[0007] The seasons that are the same as the current season in the years preceding the current time are designated as the comparison seasons for the current time. Based on the actual usage of the same blood product in different weeks preceding the current time, the increment coefficient of each blood product in each week preceding the current time is obtained, thus obtaining the increment coefficient sequence of each blood product in the current season and its comparison season. Based on the increment coefficient sequence of each blood product in the current season and each comparison season, the reference season for the current time is obtained. Based on the increment coefficient sequence of each blood product in the current season and its reference season, the minimum inventory value of each blood product in the hospital at the current time, and the quantity of each blood product in the hospital's blood bank at the current time, the predicted inventory value for the current week is obtained.

[0008] Based on the shelf life of each blood product, the predicted inventory value of each blood product in the current week, and the quantity and collection time of each blood product in the hospital blood bank at the current time, the optimal inventory value of each blood product in the current week is obtained to assist in blood inventory management.

[0009] Furthermore, the specific steps for obtaining the actual usage of each blood product in each week of the hospital over several years prior to the current time are as follows:

[0010] Obtain the actual usage of each blood product for each week within the n years prior to the current time from the hospital's back-end system; where n is the preset collection duration.

[0011] Furthermore, the specific calculation formula for the incremental coefficient of each blood product in each week prior to the current time is as follows:

[0012]

[0013] In the formula, Z k，w+1 D represents the increment coefficient of the k-th type of blood product in the (w+1)-th week prior to the current time. k，w+1 D represents the actual usage of the k-th type of blood product in the (w+1)-th week prior to the current time. k，w Let $t_n$ represent the actual usage of the $k$-th type of blood product in the $w$-th week prior to the current time, $|t_n$ denotes the absolute value function, and $t_n_n$ denotes the hyperbolic tangent function. The time interval between the $k$-th week prior to the current time and the current time is greater than the time interval between the $k+1$-th week prior to the current time and the current time.

[0014] Furthermore, the specific steps for obtaining the incremental coefficient sequence of each blood product in the current season and its comparative season are as follows:

[0015] The incremental coefficient of the k-th blood product in the q-th week of the current season is taken as the q-th data in the incremental coefficient sequence of the k-th blood product in the current season, thus obtaining the incremental coefficient sequence of the k-th blood product in the current season.

[0016] The incremental coefficient of the k-th blood product in the q-th week of the z-th comparison season at the current time is taken as the q-th data in the incremental coefficient sequence of the k-th blood product in the z-th comparison season at the current time, thus obtaining the incremental coefficient sequence of the k-th blood product in the z-th comparison season at the current time.

[0017] Furthermore, the specific steps for obtaining the current time reference season are as follows:

[0018] Calculate the DTW distance of the incremental coefficient sequence of the k-th blood product in the current season and its z-th comparison season;

[0019] Based on the DTW distance of the incremental coefficient sequence of the kth blood product in the current season and each of the comparison seasons, as well as the difference of the data at the same position in the incremental coefficient sequence, the similarity of the usage of the kth blood product in the current season and the zth comparison season is obtained.

[0020] The specific formula for calculating the similarity of usage of the k-th blood product between the current season and its z-th comparison season is as follows:

[0021]

[0022] In the formula, DTW represents the similarity in usage of the k-th blood product between the current season and its z-th comparison season. z，k ΔD represents the DTW distance between the current season and the incremental coefficient sequence of the k-th blood product in the z-th comparison season, N represents the number of data points in the incremental coefficient sequence of the k-th blood product in the current season, and ΔD represents the distance between the current time and the z-th comparison season. d，z，k This represents the difference between the incremental coefficient of the current season and the k-th blood product in the d-th week of the z-th comparison season, where || represents the absolute value function and exp() is an exponential function with the natural constant as the base.

[0023] The reference season corresponding to the maximum similarity of the usage of the kth type of blood product between the current season and all its reference seasons is denoted as the kth reference season of the current time.

[0024] Furthermore, the specific steps for obtaining the predicted inventory value for the current week are as follows:

[0025] The incremental coefficient of the k-th blood product in the (w+1)-th week of the current season is used as the x-coordinate of the (w+1)-th data point in the two-dimensional coordinate system.

[0026] The incremental coefficient of the k-th blood product in the (w+1)-th week of the k-th reference season at the current time is used as the ordinate of the (w+1)-th data point in the two-dimensional coordinate system.

[0027] Map the incremental coefficients of the current season and the k-th blood product in each week of its k-th reference season onto a two-dimensional coordinate system to obtain N data points in the two-dimensional coordinate system; where N is the number of data points in the incremental coefficient sequence of the k-th blood product in the current season.

[0028] The least squares method is used to fit the data points in the two-dimensional coordinate system to obtain a fitting formula;

[0029] The incremental coefficient of the k-th blood product in the (N+1)-th week of the k-th reference season at the current time is used as the ordinate and input into the fitting formula. The output is recorded as the predicted value of the incremental coefficient of the k-th blood product in the current week.

[0030] Based on the predicted value of the increment coefficient of the k-th blood product in the current week, the minimum inventory value of each blood product in the hospital at the current time, and the quantity of each blood product in the hospital's blood bank at the current time, the predicted inventory value of the k-th blood product in the current week is obtained.

[0031] Furthermore, the specific calculation steps for obtaining the predicted inventory value of the k-th type of blood product in the current week are as follows:

[0032] Based on the actual usage of the kth blood product in the previous week and the predicted value of the incremental coefficient of the kth blood product in the current week, the predicted value of the actual usage of the kth blood product in the current week is obtained.

[0033] The specific calculation formula for obtaining the predicted actual usage of the k-th type of blood product in the current week is as follows:

[0034]

[0035] In the formula, D represents the predicted actual usage of the k-th type of blood product in the current week. k This represents the actual usage of the k-th type of blood product in the week preceding the current week. This represents the predicted value of the incremental coefficient of the k-th type of blood product in the current week, where artanh() represents the inverse hyperbolic tangent function and || represents the absolute value function;

[0036] Based on the predicted actual usage of the k-th blood product in the current week, the minimum inventory of each blood product in the hospital at the current time, and the quantity of each blood product in the hospital's blood bank at the current time, the predicted inventory of the k-th blood product in the current week is obtained.

[0037] The specific formula for calculating the predicted inventory value of the k-th type of blood product in the current week is as follows:

[0038]

[0039] In the formula, S represents the predicted inventory value of the k-th type of blood product in the current week. 1，k This represents the minimum inventory value of the k-th type of blood product in the current week, where n is the current time. kThis represents the quantity of the k-th type of blood product in the hospital's blood bank at the current time.

[0040] Furthermore, the specific steps for obtaining the optimal inventory value for each blood product in the current week are as follows:

[0041] Based on the collection time of each unit of the kth type of blood product contained in the hospital's blood bank at the current time, the validity of the kth type of blood product in the hospital's blood bank at the current time can be obtained.

[0042] The specific calculation formula for obtaining the validity of the k-th blood product in the hospital's blood bank at the current time

[0043] The formula is as follows:

[0044]

[0045] In the formula, S k T represents the availability of the k-th blood product in the hospital's blood bank at the current time. k Let t represent the shelf life of the k-th type of blood product, and t represent the current time. k，g This represents the collection time of the g-th unit of the k-th type of blood product in the hospital's blood bank at the current time. k This represents the quantity of the k-th type of blood product in the hospital's blood bank at the current time.

[0046] Based on the effectiveness of the k-th blood product in the hospital's blood bank at the current time and the predicted inventory value of the k-th blood product in the current week, the optimal inventory value for the current week is obtained.

[0047] The specific formula for calculating the optimal inventory value for the current week is as follows:

[0048]

[0049] In the formula, This represents the optimal inventory value for the k-th type of blood product in the current week. S represents the predicted inventory value of the k-th type of blood product in the current week. k Let represent the availability of the k-th blood product in the hospital's blood bank at the current time, and exp() be an exponential function with the natural constant as its base.

[0050] Furthermore, the specific steps for the auxiliary blood inventory management are as follows:

[0051] Replenish the quantity of the k-th blood product in the hospital's blood bank at the current time, so that the replenished inventory value equals the optimal inventory value of the k-th blood product in the current week.

[0052] The present invention also proposes a blood inventory management system, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above method.

[0053] The blood inventory management method provided by this invention has the following beneficial effects: When predicting the optimal inventory value of a hospital in the current week, this invention first uses the total blood usage of each week as blood usage data. This solves the problem that when the blood usage data collection interval is too long, the detailed changes in blood demand are weakened, while when the blood usage data interval is too short, the calculation workload is too large, and too much attention is paid to detailed changes while ignoring overall changes. Based on the similarity of climate and external environment in the same season of different years, the method compares the weekly blood usage data collected in the current season with the current... This invention uses weekly blood consumption data collected in the same season of previous years to infer the optimal inventory value for the current week. This inference requires calculating the similarity between the weekly blood consumption data sequence for the current season and the weekly blood consumption data sequences for the same season of each previous year. In this invention, the weekly blood consumption data in the weekly blood consumption data sequence is replaced with an incremental coefficient obtained by comparing the weekly blood consumption data with the blood consumption data of the previous week. This solves the problem of inconsistencies in blood consumption data between the two sequences when directly calculating similarity using the DTW algorithm. Excessive data discrepancies can significantly impact the evaluation of overall similarity, making the DTW distance calculated using the DTW algorithm ineffective in quantifying similarity. Therefore, this paper proposes a new method to predict the optimal inventory value for the current week by selecting blood usage data from the same quarter of the year with the strongest similarity to the current season. This addresses the issue that predicting the optimal inventory value based on blood usage data from the same season of the previous year might be unreliable due to abnormal weather conditions in the previous year. After obtaining the predicted inventory value for the current season using historical data from the same season of previous years, the paper considers the time-sensitivity of blood products. It then adjusts the predicted inventory value based on the time interval between the collection time of each blood product in the hospital blood bank at the current time and the current time, thus avoiding the problem of some blood in the blood bank naturally becoming expired and causing large discrepancies between blood inventory and usage at certain times due to the lack of consideration for the time-sensitivity of blood. Attached Figure Description

[0054] To more clearly illustrate the embodiments and design schemes of the present invention, the accompanying drawings required for this embodiment will be briefly described below. The drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 This is a flowchart of a blood inventory management method according to an embodiment of the present invention. Detailed Implementation

[0056] To enable those skilled in the art to better understand and implement the technical solutions of the present invention, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and should not be construed as limiting the scope of protection of the present invention.

[0057] Example 1:

[0058] This invention provides a blood inventory management method, specifically as follows: Figure 1 As shown, it includes:

[0059] Step S001: Obtain the actual usage of each blood product in the hospital for each week in the years prior to the current time, the quantity and collection time of each blood product in the hospital's blood bank at the current time, the shelf life of each blood product, and the minimum inventory value of each blood product in the hospital at the current time.

[0060] Specifically, the system retrieves the following information from the hospital's backend system: the shelf life of each blood product, the actual usage of each blood product in each week of the previous n years, the actual usage of each blood product in each week of the current year, the quantity of each blood product in the hospital's blood bank at the current time, the collection time for each unit of each blood product, and the minimum inventory value of each blood product at the current time. In this embodiment, the preset collection duration n=5 is used as an example; other values ​​can be set in other implementations.

[0061] Step S002: Record the seasons that are the same as the current season in the years preceding the current time as the comparison season for the current time; based on the actual usage of the same blood product in different weeks preceding the current time, obtain the increment coefficient of each blood product in each week preceding the current time, and then obtain the increment coefficient sequence of each blood product in the current season and its comparison season; based on the increment coefficient sequence of each blood product in the current season and each comparison season, obtain the reference season for the current time; based on the increment coefficient sequence of each blood product in the current season and its reference season, the minimum inventory value of each blood product in the hospital at the current time, and the quantity of each blood product in the hospital's blood bank at the current time, obtain the predicted inventory value for the current week.

[0062] It should be noted that since the climate and weather conditions are relatively similar in the same season in different years, the historical data collected in the current season are compared with the historical data in the same season in other years to obtain the similarity between the current season and the same season in the previous year. Then, based on the historical data in the season of the year with strong similarity, the predicted blood consumption for the current week is obtained.

[0063] It should be further clarified that when comparing historical blood usage within the current season with historical blood usage in the same season of previous years, a one-week interval is used because most weeks consist of 5 working days and 2 rest days, and to avoid weakening the detailed characteristics of blood demand due to excessively long testing periods. That is, the total blood usage for one week is used as a single data point when collecting blood usage data.

[0064] It should be further noted that the number of weekly actual consumption data points collected in the current season differs from the number of weekly actual consumption data points collected in the same season in previous years. Therefore, the DTW algorithm is used to calculate the similarity between the current season and the same season in the year prior to the current time.

[0065] It's important to further clarify that when using the DTW algorithm to calculate similarity, directly calculating the DTW distance based on weekly actual usage can lead to issues. The actual usage data for some weeks within the current season differs significantly from that of some weeks within the same season in the previous year. This means that the differences in actual usage for some weeks within the same season across different years may have an excessive impact on the overall DTW distance, making the obtained DTW distance inaccurate in quantifying the similarity of blood usage between the current season and the same season in the previous year. Therefore, when calculating similarity using the DTW algorithm, the actual usage for each week is compared with that of the previous week to obtain an increment coefficient for each week. The DTW distance is then calculated using this increment coefficient.

[0066] It should be further explained that when calculating the similarity between the current season and the same season within the previous year using the DTW algorithm, the number of weekly actual usage data collected in the current season differs from the number collected in the same season within the previous year. This may lead to the calculation of the DTW distance comparing the incremental coefficient of the i-th week collected in the current season with the incremental coefficients of non-i-th weeks within the same season within the previous year. Therefore, after obtaining the DTW distance, the final similarity is obtained by comparing the incremental coefficient of the i-th week collected in the current season with the incremental coefficient of the i-th week within the same season within the previous year. Based on the actual usage in the same season over historical years, the predicted blood usage for the current week is obtained.

[0067] It should be further explained that since hospitals set a minimum inventory level, the predicted inventory level for the current week is obtained based on the predicted blood usage and safety stock level for the current week.

[0068] Specifically, the formula for calculating the incremental coefficient of each blood product in each week prior to the current time is as follows:

[0069]

[0070] In the formula, Z k，w+1 D represents the increment coefficient of the k-th type of blood product in the (w+1)-th week prior to the current time. k，w+1 D represents the actual usage of the k-th type of blood product in the (w+1)-th week prior to the current time. k，w This represents the actual usage of the k-th type of blood product in the w-th week prior to the current time, where || represents the absolute value function, and tanh() represents the hyperbolic tangent function. In this embodiment, it is used to let Z... k，w+1The value is between -1 and 1. Specifically, the time interval between the k-th week prior to the current time and the current time is greater than the time interval between the (k+1)-th week prior to the current time and the current time.

[0071] It should be noted that if you go directly through When calculating the increment coefficient of the k-th blood product in the (w+1)-th week prior to the current time, we may encounter problems due to D k，w The value is small, thus making The problem is that the value is large, therefore... This is to address the problem that the incremental coefficient of a small number of blood products is too large because the actual usage of the k-th blood product is relatively low in some weeks before the current time.

[0072] This gives us the increment coefficient for each blood product in each week prior to the current time.

[0073] Furthermore, the seasons within the n years preceding the current time that are the same as the current time are designated as the comparison seasons for the current time. Based on the increment coefficient of the k-th blood product in each week of the current time's season, a sequence of increment coefficients for the k-th blood product within the current time's season is obtained. Based on the increment coefficient of the k-th blood product in each week of the z-th comparison season, a sequence of increment coefficients for the k-th blood product within the z-th comparison season is obtained. The number of data points in the increment coefficient sequence for the k-th blood product within the z-th comparison season is greater than the number of data points in the increment coefficient sequence for the k-th blood product within the previous season.

[0074] Furthermore, the DTW algorithm is used to calculate the DTW distance between the incremental coefficient sequence of the current season and the k-th blood product in its z-th comparison season. The use of the DTW algorithm to calculate the DTW distance between two sequences is a well-known existing technique and will not be elaborated upon in this embodiment.

[0075] Furthermore, the specific calculation formula for obtaining the similarity of usage of the k-th blood product between the current season and its z-th comparison season is as follows:

[0076]

[0077] In the formula, DTW represents the similarity in usage of the k-th blood product between the current season and its z-th comparison season. z，k ΔD represents the DTW distance between the current season and the incremental coefficient sequence of the k-th blood product in the z-th comparison season, where N represents the number of data points in the incremental coefficient sequence of the current season. d,z,kThis represents the difference between the incremental coefficient of the current season and the k-th blood product in the d-th week of the z-th comparison season. || represents the absolute value function, and exp() is an exponential function with the natural constant as the base. In this embodiment, it is used to represent the inverse proportional relationship.

[0078] It should be noted that DTW z,k The smaller the value, the stronger the reference value of the weekly increment coefficient of the k-th blood product in the current comparative season, and the stronger the similarity of usage. It is used to reflect the difference in the incremental coefficient between the z-th comparison season at the current time and the same week within the current season. The larger the value, the greater the difference in blood usage between the z-th comparison season at the current time and the current season, that is, the stronger the similarity in usage.

[0079] Furthermore, the reference season corresponding to the maximum similarity of the usage of the kth type of blood product between the current season and all its reference seasons is denoted as the kth reference season of the current time.

[0080] Furthermore, a two-dimensional coordinate system is constructed, with the horizontal axis representing the incremental coefficient of the k-th blood product within the current season and the vertical axis representing the incremental coefficient of the k-th blood product within the current reference season.

[0081] Furthermore, the increment coefficient of the k-th blood product in the (w+1)-th week of the current season is used as the x-coordinate of the (w+1)-th data point in the two-dimensional coordinate system. The increment coefficient of the k-th blood product in the (w+1)-th week of the k-th reference season is used as the y-coordinate of the (w+1)-th data point in the two-dimensional coordinate system. Thus, the increment coefficients of the k-th blood product in each week of the current season and the k-th reference season are mapped to the two-dimensional coordinate system, resulting in N data points in the two-dimensional coordinate system.

[0082] Furthermore, the least squares method is used to fit the data points in the two-dimensional coordinate system to obtain a fitting formula. The increment coefficient of the k-th blood product in the (N+1)-th week of the k-th reference season at the current time is used as the ordinate and input into the fitting formula. The output is recorded as the predicted value of the increment coefficient of the k-th blood product in the current week. The fitting formula obtained by fitting the data is an existing and well-known technique, and will not be described in detail in this embodiment.

[0083] Furthermore, the formula for calculating the predicted actual usage of the k-th blood product in the current week is as follows:

[0084]

[0085] In the formula, D represents the predicted actual usage of the k-th type of blood product in the current week. k This represents the actual usage of the k-th type of blood product in the week preceding the current week. This represents the predicted value of the increment coefficient of the k-th type of blood product in the current week. artanh() represents the inverse hyperbolic tangent function, and || represents the absolute value function.

[0086] Furthermore, the specific formula for calculating the predicted inventory value for the current week is as follows:

[0087]

[0088] In the formula, This represents the predicted inventory value of the k-th blood product in the current week. S represents the predicted actual usage of the k-th type of blood product in the current week. 1,k This represents the minimum inventory value of the k-th type of blood product in the current week, where n is the current time. k This represents the quantity of the k-th type of blood product in the hospital's blood bank at the current time.

[0089] This gives us the predicted inventory value for each blood product for the current week.

[0090] Step S003: Based on the shelf life of each blood product, the predicted inventory value of each blood product in the current week, and the quantity and collection time of each blood product in the hospital blood bank at the current time, obtain the optimal inventory value of each blood product in the current week to assist in blood inventory management.

[0091] It should be noted that blood products have expiration dates, causing the amount of blood products in hospital blood banks to decrease automatically over time. Therefore, when replenishing blood in hospital blood banks, the expiration dates of the blood products currently in the bank must be considered. Thus, based on the expiration dates of the blood products currently in the hospital blood bank, the predicted inventory value for each type of blood product for the current week is adjusted to determine the optimal inventory value for each type of blood product for the current week.

[0092] Specifically, based on the collection time of each unit of the kth blood product contained in the hospital's blood bank at the current time, the specific calculation formula for the effectiveness of the kth blood product in the hospital's blood bank at the current time is as follows:

[0093]

[0094] In the formula, S k T represents the availability of the k-th blood product in the hospital's blood bank at the current time.k Let t represent the shelf life of the k-th type of blood product, and t represent the current time. k,g This represents the collection time of the g-th unit of the k-th type of blood product in the hospital's blood bank at the current time. k This represents the quantity of the k-th type of blood product in the hospital's blood bank at the current time.

[0095] It should be noted that tt k,g The larger the value, the better. The smaller the value, the longer the interval between the collection time of the k-th blood product in the hospital's blood bank and the current time. In other words, the greater the possibility that the k-th blood product in the hospital's blood bank will become invalid at the current time, and a large adjustment is needed to the predicted inventory value of the k-th blood product in the current week.

[0096] Furthermore, the specific formula for calculating the optimal inventory value for the current week is as follows:

[0097]

[0098] In the formula, This represents the optimal inventory value for the k-th type of blood product in the current week. S represents the predicted inventory value of the k-th type of blood product in the current week. k This represents the validity of the k-th blood product in the hospital's blood bank at the current time. exp() is an exponential function with the natural constant as its base, which is used in this embodiment for inverse proportional processing.

[0099] It should be noted that S k The larger the value, the smaller the quantity of the k-th type of blood product that will expire in the hospital's blood bank at the current time. Therefore, for To achieve a smaller growth; S k The smaller the value, the larger the quantity of the k-th type of blood product that will expire in the hospital's blood bank at the current time. Therefore, for To achieve significant growth.

[0100] Furthermore, the quantity of the k-th blood product in the hospital's blood bank at the current time is replenished so that the replenished inventory value equals the optimal inventory value of the k-th blood product for the current week.

[0101] This concludes the embodiment.

[0102] Another embodiment of the present invention provides a blood inventory management system, which includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the above-described method steps S001 to S003.

[0103] 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, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for managing blood inventory, characterized in that, include: Obtain the actual usage of each blood product in the hospital for each week in the years prior to the current time, the quantity and collection time of each blood product in the hospital's blood bank at the current time, the shelf life of each blood product, and the minimum inventory value of each blood product in the hospital at the current time. The seasons that are the same as the current season in the years preceding the current time are designated as the comparison seasons for the current time. Based on the actual usage of the same blood product in different weeks preceding the current time, the increment coefficient of each blood product in each week preceding the current time is obtained, thus obtaining the increment coefficient sequence of each blood product in the current season and its comparison season. Based on the increment coefficient sequence of each blood product in the current season and each comparison season, the reference season for the current time is obtained. Based on the increment coefficient sequence of each blood product in the current season and its reference season, the minimum inventory value of each blood product in the hospital at the current time, and the quantity of each blood product in the hospital's blood bank at the current time, the predicted inventory value for the current week is obtained. Based on the shelf life of each blood product, the predicted inventory value of each blood product in the current week, and the quantity and collection time of each blood product in the hospital blood bank at the current time, the optimal inventory value of each blood product in the current week is obtained to assist in blood inventory management.

2. The blood inventory management method according to claim 1, characterized in that, The specific steps for obtaining the actual usage of each blood product in the hospital for each week over several years prior to the current time are as follows: Obtain the actual usage of each blood product for each week within the n years prior to the current time from the hospital's back-end system; where n is the preset collection duration.

3. The blood inventory management method according to claim 1, characterized in that, The specific calculation formula for the incremental coefficient of each blood product in each week prior to the current time is as follows: In the formula, Z k，w+1 D represents the increment coefficient of the k-th type of blood product in the (w+1)-th week prior to the current time. k，w+1 D represents the actual usage of the k-th type of blood product in the (w+1)-th week prior to the current time. k，w This represents the actual usage of the k-th type of blood product in the w-th week prior to the current time, where || represents the absolute value function and tanh() represents the hyperbolic tangent function; the time interval between the k-th week prior to the current time and the current time is greater than the time interval between the (k+1)-th week prior to the current time and the current time.

4. The blood inventory management method according to claim 1, characterized in that, The specific steps for obtaining the incremental coefficient sequence of each blood product in the current season and its comparative season are as follows: The incremental coefficient of the k-th blood product in the q-th week of the current season is taken as the q-th data in the incremental coefficient sequence of the k-th blood product in the current season, thus obtaining the incremental coefficient sequence of the k-th blood product in the current season. The incremental coefficient of the k-th blood product in the q-th week of the z-th comparison season at the current time is taken as the q-th data in the incremental coefficient sequence of the k-th blood product in the z-th comparison season at the current time, thus obtaining the incremental coefficient sequence of the k-th blood product in the z-th comparison season at the current time.

5. The blood inventory management method according to claim 1, characterized in that, The specific steps to obtain the current time reference season are as follows: Calculate the DTW distance of the incremental coefficient sequence of the k-th blood product in the current season and its z-th comparison season; Based on the DTW distance of the incremental coefficient sequence of the kth blood product in the current season and each of the comparison seasons, as well as the difference of the data at the same position in the incremental coefficient sequence, the similarity of the usage of the kth blood product in the current season and the zth comparison season is obtained. The specific formula for calculating the similarity of usage of the k-th blood product between the current season and its z-th comparison season is as follows: In the formula, DTW represents the similarity in usage of the k-th blood product between the current season and its z-th comparison season. z，k ΔD represents the DTW distance between the current season and the incremental coefficient sequence of the k-th blood product in the z-th comparison season, N represents the number of data points in the incremental coefficient sequence of the k-th blood product in the current season, and ΔD represents the distance between the current time and the z-th comparison season. d，z，k This represents the difference between the incremental coefficient of the current season and the k-th blood product in the d-th week of the z-th comparison season; || represents the absolute value function; and exp() is an exponential function with the natural constant as the base. The reference season corresponding to the maximum similarity of the usage of the kth type of blood product between the current season and all its reference seasons is denoted as the kth reference season of the current time.

6. A blood inventory management method according to claim 1, characterized in that, The specific steps to obtain the predicted inventory value for the current week are as follows: The incremental coefficient of the k-th blood product in the (w+1)-th week of the current season is used as the x-coordinate of the (w+1)-th data point in the two-dimensional coordinate system. The incremental coefficient of the k-th blood product in the (w+1)-th week of the k-th reference season at the current time is used as the ordinate of the (w+1)-th data point in the two-dimensional coordinate system. Map the incremental coefficients of the current season and the k-th blood product in each week of the k-th reference season to a two-dimensional coordinate system to obtain N data points in the two-dimensional coordinate system; where N is the number of data points in the incremental coefficient sequence of the k-th blood product in the current season. The least squares method is used to fit the data points in the two-dimensional coordinate system to obtain a fitting formula; The incremental coefficient of the k-th blood product in the (N+1)-th week of the k-th reference season at the current time is used as the ordinate and input into the fitting formula. The output is recorded as the predicted value of the incremental coefficient of the k-th blood product in the current week. Based on the predicted value of the increment coefficient of the k-th blood product in the current week, the minimum inventory value of each blood product in the hospital at the current time, and the quantity of each blood product in the hospital's blood bank at the current time, the predicted inventory value of the k-th blood product in the current week is obtained.

7. A blood inventory management method according to claim 6, characterized in that, The specific calculation steps for obtaining the predicted inventory value of the k-th type of blood product in the current week are as follows: Based on the actual usage of the kth blood product in the previous week and the predicted value of the incremental coefficient of the kth blood product in the current week, the predicted value of the actual usage of the kth blood product in the current week is obtained. The specific calculation formula for obtaining the predicted actual usage of the k-th type of blood product in the current week is as follows: In the formula, D represents the predicted actual usage of the k-th type of blood product in the current week. k This represents the actual usage of the k-th type of blood product in the week preceding the current week. This represents the predicted value of the incremental coefficient of the k-th type of blood product in the current week. artanh() represents the inverse hyperbolic tangent function, and || represents the absolute value function. Based on the predicted actual usage of the k-th blood product in the current week, the minimum inventory of each blood product in the hospital at the current time, and the quantity of each blood product in the hospital's blood bank at the current time, the predicted inventory of the k-th blood product in the current week is obtained. The specific formula for calculating the predicted inventory value of the k-th type of blood product in the current week is as follows: In the formula, S represents the predicted inventory value of the k-th type of blood product in the current week. 1，k This represents the minimum inventory value of the k-th type of blood product in the current week, where n is the current time. k This represents the quantity of the k-th type of blood product in the hospital's blood bank at the current time.

8. A blood inventory management method according to claim 1, characterized in that, The specific steps for obtaining the optimal inventory value for each type of blood product in the current week are as follows: Based on the collection time of each unit of the kth type of blood product contained in the hospital's blood bank at the current time, the validity of the kth type of blood product in the hospital's blood bank at the current time can be obtained. The specific formula for calculating the validity of the k-th blood product in the hospital's blood bank at the current time is as follows: In the formula, S k T represents the availability of the k-th blood product in the hospital's blood bank at the current time. k Let t represent the shelf life of the k-th type of blood product, and t represent the current time. k，g This represents the collection time of the g-th unit of the k-th type of blood product in the hospital's blood bank at the current time. k This represents the quantity of the k-th type of blood product in the hospital's blood bank at the current time. Based on the availability of the k-th blood product in the hospital's blood bank at the current time and the predicted inventory value of the k-th blood product in the current week, the optimal inventory value for the current week is obtained. The specific formula for calculating the optimal inventory value for the current week is as follows: In the formula, This represents the optimal inventory value for the k-th type of blood product in the current week. S represents the predicted inventory value of the k-th type of blood product in the current week. k This represents the availability of the k-th blood product in the hospital's blood bank at the current time, and exp() is an exponential function with the natural constant as its base.

9. A blood inventory management method according to claim 1, characterized in that, The specific steps for assisting in blood inventory management are as follows: Replenish the quantity of the k-th blood product in the hospital's blood bank at the current time, so that the replenished inventory value equals the optimal inventory value of the k-th blood product in the current week.

10. A blood inventory management system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the blood inventory management method as described in any one of claims 1-9.

Images