Slurry station resource sharing system deployed based on SaaS platform

Through the plasma station resource sharing system based on the SaaS platform, the dual-exponential smoothing method is used to predict plasma resource trends and support assessment, and the plasma resource allocation is optimized, which solves the problems of low resource utilization and uneven allocation in plasma station resource sharing, and realizes the More efficient resource management.

CN118942654APending Publication Date: 2024-11-12SHENZHEN QIAOLANGCHENG TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410960998.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-17
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

There are problems of insufficient or excess plasma resources in the plasma station resource sharing system, resulting in low resource utilization, unbalanced allocation, unable to meet patient needs, and unpredictable periods of high or low plasma demand.

Method used

The plasma station resource sharing system deployed based on the SaaS platform includes analysis and resource allocation units, calculation and judgment units, and optimization allocation units. It predicts plasma resource trends through dual-exponential smoothing method, optimizes plasma resource allocation, and uses support and confidence to evaluate the improvement. Make targeted allocations.

Benefits of technology

The utilization efficiency of plasma resources is improved, and resource allocation is predicted to increase in the period of high plasma demand and reduce resource investment in the period of low demand, achieving a more balanced and efficient allocation of resources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942654A_ABST
    Figure CN118942654A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of resource sharing, in particular to a slurry station resource sharing system deployed based on an SaaS platform. The system comprises an analysis and resource allocation unit, a calculation and judgment unit and an optimal allocation unit. The high-low judgment module predicts a shared plasma resource value at a future time point according to a calculated corresponding time point smooth value and a calculated shared plasma resource quantity trend value, and judges by using the predicted shared plasma resource value at the future time point and a set standard shared plasma resource range value; whether the plasma high-demand period and the plasma low-demand period exist in the shared resources at the future time point or not is judged, the plasma high-demand period can be predicted by predicting the shared plasma resource value at the future time point, the optimized allocation of the shared plasma resources is increased to meet the requirements of patients, and when the plasma low-demand period is predicted, the optimal allocation of the shared plasma resources is increased. Therefore, the input of shared plasma resources can be reduced, and the utilization efficiency of the shared plasma resources is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of resource sharing, and in particular to a pulp station resource sharing system deployed based on a SaaS platform. Background Art

[0002] Plasma station resource sharing refers to the sharing of resources, information and services between different plasma stations through the Internet and software service SaaS platform, which can improve the efficiency and resource utilization of plasma stations and ensure that plasma collection and process management are more efficient and safe. Due to the frequent problems of insufficient or excessive shared plasma resources, when a plasma station has a high plasma demand period at a certain point in time, more shared plasma resources are needed. Since shared plasma resources cannot be increased or allocated quickly, the shared plasma resources of the plasma station are tight and cannot meet the needs of all patients. When a plasma station has a low plasma demand period at a certain point in time, shared plasma resources cannot be fully utilized, resulting in idle and wasted shared plasma resources, reducing the utilization rate of shared plasma resources, and there will be a certain degree of correlation between different shared plasma resources and patients. However, the plasma station does not optimize the allocation of shared plasma resources in a targeted manner, resulting in an unbalanced allocation of shared plasma resources and reduced efficiency of shared plasma resource allocation. In order to avoid the reduction of shared plasma resource utilization due to high and low plasma demand periods at a certain point in time, we provide a plasma station resource sharing system deployed based on the SaaS platform. Summary of the invention

[0003] The purpose of the present invention is to provide a pulp station resource sharing system deployed based on a SaaS platform to solve the problems raised in the above-mentioned background technology.

[0004] To achieve the above-mentioned purpose, the present invention provides a pulp station resource sharing system deployed based on a SaaS platform, including an analysis and resource allocation unit, a calculation and judgment unit, and an optimization allocation unit;

[0005] The analysis and resource allocation unit uses the SaaS platform to obtain patient-related plasma demands and related sharable plasma resources, and analyzes patient plasma demands and shared plasma resource rules, and then matches and allocates common conditions according to the analyzed patient plasma demands and the analyzed shared plasma resource rules, and records the time point corresponding to the amount of allocated shared plasma resources;

[0006] The calculation and judgment unit is used to receive the number of shared plasma resources allocated in the analysis and resource allocation unit, calculate the smoothed value of the corresponding time point at the corresponding time point, and then predict whether there will be a high plasma demand period and a low plasma demand period at a future time point based on the calculated smoothed value of the corresponding time point;

[0007] The calculation and judgment unit includes a data calculation module and a high and low judgment module;

[0008] The data calculation module is used to receive the historical shared plasma resource quantity data obtained in the data analysis module and the shared plasma resource quantity data allocated in the matching allocation module, and the corresponding time point, and use the double exponential smoothing method to calculate the smoothing value of the corresponding time point according to the obtained historical shared plasma resource quantity data, the corresponding time point and the allocated shared plasma resource quantity data, and then calculate the trend value of the plasma station shared plasma resource quantity according to the calculated smoothing value of the corresponding time point;

[0009] The implementation steps of using double exponential smoothing method to analyze the changing trend of the number of shared resources are as follows:

[0010] Step 1: Collect and obtain historical shared plasma resource quantity data LS sl , Allocated shared plasma resource quantity data FP sl and the corresponding time point t, and based on the historical shared plasma resource quantity data LS sl and the amount of shared plasma resources allocated FP sl Set the standard smoothing parameters a and b;

[0011] Step 2: Get the smoothed value S of the previous time point (t-1) from the data repository t-1 and trend value T t-1 , and using the smoothing parameter a, the corresponding time point t, and the allocated shared plasma resource quantity data FP sl , the smoothing value S at the previous time point t-1 and trend value T t-1 Calculate the smoothing value at the corresponding time point t to obtain the calculated smoothing value S at the corresponding time point t , the specific algorithm formula is:

[0012] S t =(a×FP sl )+(1-a)×(S t-1 +T t-1 );

[0013] Among them, the value range of the smoothing parameter a is (0,1);

[0014] Step 3: Use the calculated smoothing value S at the corresponding time point t , the smoothing value S at the previous time point t-1 and trend value T t-1 , smoothing parameter b is used to calculate the trend value of the number of shared plasma resources in the plasma station, and the calculated trend value of the number of shared plasma resources T is obtained. t , the specific algorithm formula is:

[0015] Tt =b×(S t -S t-1 )+(1-b)×T t-1 ;

[0016] Among them, the value range of the smoothing parameter b is (0,1);

[0017] The optimization allocation unit is used to receive commands with different common conditions matched in the analysis and resource allocation unit or plasma high demand period commands or plasma low demand period commands in the calculation and judgment unit. The optimization allocation unit obtains the analyzed patient plasma demand and the analyzed shared plasma resource rules from the analysis and resource allocation unit and evaluates the degree of improvement, and then uses the evaluated degree of improvement and the set standard degree of improvement to judge the correlation and optimize the allocation of shared plasma resources.

[0018] As a further improvement of the technical solution, the analysis and resource allocation unit includes a data analysis module and a matching allocation module;

[0019] The data analysis module obtains patient-related plasma demand through the SaaS platform, and analyzes the patient's plasma demand based on the obtained patient-related plasma demand data, then obtains relevant sharable plasma resources from the plasma station, and analyzes the shared plasma resource rules based on the obtained relevant sharable plasma resources;

[0020] The matching allocation module is used to receive the patient plasma demand data and the analyzed shared plasma resource rule data analyzed in the data analysis module, and deploy the analyzed patient plasma demand data to the plasma station through the SaaS platform, and then match common conditions based on the analyzed patient plasma demand data and the analyzed shared plasma resource rule data.

[0021] As a further improvement of the technical solution, the matching of common conditions in the matching allocation module:

[0022] The patient plasma demand data XQ analyzed includes the requested plasma storage time QQ sc , Coverage of requested locations QQ dd The analyzed shared plasma resource rule data GZ includes the storage time GX of shared plasma sc , the coverage of shared locations GX dd , the analyzed patient plasma demand data XQ and the analyzed shared plasma resource rule data GZ have common conditions of duration sc and location dd, and the duration sc and location dd are used as the matching common conditions PP gx , when the plasma duration sc and location dd required by the patient are not within the duration sc and location dd of the shared plasma resource, then the commonality condition PP gxNo match, when the plasma duration sc and location dd required by the patient are within the duration sc and location dd of the shared plasma resource, then the commonality condition PP gx Match.

[0023] As a further improvement of the technical solution, the specific matching conditions in the matching allocation module include:

[0024] Case ①: When the analyzed patient plasma demand data matches the analyzed shared plasma resource rule data in the same common conditions, the shared resources of the plasma station are screened according to the matched common conditions, and the shared resources of the plasma station are allocated to the patient through the SaaS platform. The time point corresponding to the allocated shared plasma resource quantity data is recorded, and the allocated shared plasma resource quantity data and the corresponding time point are transmitted to the calculation and judgment unit;

[0025] Case ②: When the common conditions matched by the analyzed patient plasma demand data and the analyzed shared plasma resource rule data are different, the command data with different matching common conditions are transmitted to the optimization allocation unit.

[0026] As a further improvement of the present technical solution, the high and low judgment module is used to receive the smoothed value of the corresponding time point and the calculated trend value of the shared plasma resource quantity calculated in the data calculation module, and use the prediction algorithm to predict the shared plasma resource value at the future time point based on the calculated smoothed value of the corresponding time point and the calculated trend value of the shared plasma resource quantity, and then use the predicted shared plasma resource value at the future time point and the set standard shared plasma resource range value to judge whether the shared plasma resource situation of the plasma station will have a period of high plasma demand and a period of low plasma demand in the future time point.

[0027] As a further improvement of the technical solution, the implementation principle of using the prediction algorithm in the high and low judgment module to predict the shared resource value in the future time period is:

[0028] First, collect the calculated smoothing values ​​S at the corresponding time points t and the calculated trend value of the number of shared plasma resources T t And calculate the shared plasma resource value at the future time point, and obtain the calculated shared resource value hat at the future time point y , calculate the shared resource value hat at the future time point y That is, the predicted shared plasma resource value at a future time point. The specific algorithm formula is:

[0029] hat y =S t +(h×T t );

[0030] Here, h refers to a future time point in hours.

[0031] As a further improvement of the technical solution, the specific judgment situations in the high and low judgment module include:

[0032] Case 1: When the predicted shared plasma resource value at a future time point is greater than the set standard shared plasma resource range value, it indicates that there is a high plasma demand period at the predicted future time point. The high plasma demand period will cause a rapid increase in the patient's demand for shared plasma resources, and a high plasma demand period command will be transmitted to the optimization allocation unit;

[0033] Case 2: When the predicted shared plasma resource value at a future time point is less than the set standard shared plasma resource range value, it indicates that there is a period of low plasma demand at the predicted future time point. The low plasma demand period will result in the plasma station shared plasma resources being unable to be fully utilized, and a command for the existence of a low plasma demand period will be transmitted to the optimization allocation unit;

[0034] Case 3: When the predicted shared plasma resource value at a future time point is within the set standard shared plasma resource range, it means that there will be no period of high plasma demand or low plasma demand at the future time point.

[0035] As a further improvement of the technical solution, the optimization allocation unit includes an item set generation module, a frequency statistics module and an evaluation allocation module;

[0036] The generating item set module is used to receive command data with different common conditions matched in the matching allocation module or plasma high demand period command or plasma low demand period command in the high and low judgment module, the generating item set module obtains the analyzed patient plasma demand data and the analyzed shared plasma resource rule data from the data analysis module and integrates them into a data set, generates a request item set according to the requested plasma storage time and the coverage of the requested location in the analyzed patient plasma demand data, and then generates a shared item set according to the shared plasma storage time and the coverage of the shared location in the analyzed shared plasma resource rule data;

[0037] The frequency statistics module is used to receive the request item set and the shared item set in the item set generation module, and count the number of times the items in the request item set and the shared item set appear independently in the data set, and the number of times the items in the request item set and the shared item set appear simultaneously in the data set. At the same time, it is also necessary to count the total number of times all items in the request item set and all items in the shared item set appear in the data set, and then perform confidence and expenditure mining based on the number of times the items in the request item set and the shared item set appear independently, the number of times the items in the request item set and the shared item set appear simultaneously in the data set, and the total number of times they appear.

[0038] The evaluation and allocation module is used to receive the mined support and mined confidence in the frequency statistics module, and use the mined support and mined confidence to evaluate the lift, then use the evaluated lift and the set standard lift to judge the correlation, and then optimize the allocation of shared plasma resources based on the judged correlation.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] 1. In the plasma station resource sharing system deployed by the SaaS platform, the high and low judgment module predicts the shared plasma resource value at future time points based on the calculated smoothed value at the corresponding time point and the calculated trend value of the shared plasma resource quantity, and then uses the predicted shared plasma resource value at the future time point and the set standard shared plasma resource range value to judge whether there will be a period of high plasma demand and a period of low plasma demand for the shared plasma resources of the plasma station in the future. By predicting the shared plasma resource value at future time points, the period of high plasma demand can be predicted, and the shared plasma resources can be optimized to meet the needs of patients. When the period of low plasma demand is predicted, the investment in shared plasma resources can be reduced, thereby improving the utilization efficiency of shared plasma resources.

[0041] 2. In the plasma station resource sharing system deployed by the SaaS platform, the evaluation and allocation module uses the mined support and confidence to evaluate the lift, and then uses the evaluated lift and the set standard lift to judge the correlation, and then optimizes the allocation of shared plasma resources based on the judged correlation. The support and confidence provide a quantitative evaluation of the association rules. By calculating the lift, the degree of correlation between the antecedent and the consequent can be quantified more accurately, and the relationship between specific conditions and urgently needed plasma can be judged more accurately, and the shared plasma resources can be optimized and allocated in a targeted manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is an overall block diagram of the present invention;

[0043] Figure 2 It is a block diagram of the analysis and resource allocation unit of the present invention;

[0044] Figure 3 It is a block diagram of the calculation and judgment unit of the present invention;

[0045] Figure 4 This is a block diagram of the optimization allocation unit of the present invention.

[0046] The meaning of each number in the figure is:

[0047] 1. Analysis and resource allocation unit; 11. Data analysis module; 12. Matching allocation module;

[0048] 2. Calculation and judgment unit; 21. Data calculation module; 22. High and low judgment module;

[0049] 3. Optimization allocation unit; 31. Item set generation module; 32. Frequency statistics module; 33. Evaluation allocation module. DETAILED DESCRIPTION

[0050] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] Example 1

[0052] The present invention provides a pulp station resource sharing system based on SaaS platform deployment, please refer to Figure 1-Figure 4 , including an analysis and resource allocation unit 1, a calculation and judgment unit 2, and an optimization allocation unit 3;

[0053] The analysis and resource allocation unit 1 uses the SaaS platform to obtain patient-related plasma needs and related sharable plasma resources and analyze the patient's plasma needs and the shared plasma resource rules, and then matches and allocates common conditions according to the analyzed patient plasma needs and the analyzed shared plasma resource rules, and records the time points corresponding to the allocated shared plasma resource quantities; the calculation and judgment unit 2 is used to receive the shared plasma resource quantities allocated in the analysis and resource allocation unit 1, calculate the smoothed values ​​of the corresponding time points at the corresponding time points, and then predict whether there will be high plasma demand periods and low plasma demand periods at future time points based on the calculated smoothed values ​​of the corresponding time points; the optimization allocation unit 3 is used to receive commands with different common conditions matched in the analysis and resource allocation unit 1 or high plasma demand period commands or low plasma demand period commands in the calculation and judgment unit 2, and the optimization allocation unit 3 obtains the analyzed patient plasma needs and the analyzed shared plasma resource rules from the analysis and resource allocation unit 1 and evaluates the degree of improvement, and then uses the evaluated degree of improvement to judge the correlation with the set standard degree of improvement and optimizes the allocation of shared plasma resources.

[0054] The following is a refinement of the above units, see Figure 1-Figure 4 ;

[0055] The analysis and resource allocation unit 1 comprises a data analysis module 11 and a matching allocation module 12;

[0056] The data analysis module 11 obtains patient-related plasma demand through the SaaS platform, analyzes patient plasma demand based on the obtained patient-related plasma demand data, obtains relevant sharable plasma resources from the plasma station, and analyzes the shared plasma resource rules based on the obtained relevant sharable plasma resources. By analyzing the patient's plasma demand data, it is possible to more accurately understand the demand of different patients for different types of plasma, help blood service agencies better match supply and demand, and ensure that patients can obtain the required plasma resources in a timely manner. At the same time, analyzing the rules of sharable plasma resources can help blood service agencies allocate plasma resources more effectively. By identifying association rules with high promotion, the agency can give priority to allocating plasma to donor groups associated with patients who are in urgent need of plasma, thereby improving resource utilization efficiency and supply chain transparency;

[0057] The patient-related plasma demand data obtained include the requested plasma storage duration and coverage of the requested locations;

[0058] The relevant sharable plasma resources obtained include the storage duration of shared plasma, the coverage of sharing locations and the historical quantity of shared plasma resources;

[0059] The matching allocation module 12 is used to receive the patient plasma demand data and the analyzed shared plasma resource rule data analyzed in the data analysis module 11, and deploy the analyzed patient plasma demand data to the plasma station through the SaaS platform, which can better meet the personalized needs of patients, improve the utilization efficiency of plasma resources, and realize the sharing and efficient allocation of plasma resources. Then, the common conditions are matched according to the analyzed patient plasma demand data and the analyzed shared plasma resource rule data. By matching the commonality of the patient plasma resource demand and the shared plasma resource rules, the shared plasma resources suitable for the patient's needs can be determined more accurately, thereby improving the utilization efficiency of plasma resources and patient satisfaction.

[0060] Matching of common conditions in the matching allocation module 12;

[0061] Since the patient plasma demand data XQ analyzed includes the requested plasma storage time QQ sc , Coverage of requested locations QQ dd The analyzed shared plasma resource rule data GZ includes the storage time GX of shared plasma sc , the coverage of shared locations GX dd Therefore, the analyzed patient plasma demand data XQ and the analyzed shared plasma resource rule data GZ have common conditions of duration sc and location dd. The duration sc and location dd are used as the matching common conditions PP. gx , when the plasma duration sc and location dd required by the patient are not within the duration sc and location dd of the shared plasma resource, then the commonality condition PP gxNo match, when the plasma duration sc and location dd required by the patient are within the duration sc and location dd of the shared plasma resource, then the commonality condition PP gx Match;

[0062] The specific matching situations in the matching allocation module 12 include:

[0063] Case ①: When the analyzed patient plasma demand data and the analyzed shared plasma resource rule data match the same common conditions, the matched common conditions are converted into logical rules, which can be expressed in Boolean logic, and then screened according to the matched common conditions, and the shared resources of the plasma station are allocated to the patient through the SaaS platform, and the corresponding time point of the allocated shared plasma resource quantity data is recorded, and then the allocated shared plasma resource quantity data and the corresponding time point are transmitted to the calculation and judgment unit 2;

[0064] Case ②: When the common conditions matched by the analyzed patient plasma demand data and the analyzed shared plasma resource rule data are different, the command data with different matching common conditions are transmitted to the optimization allocation unit 3;

[0065] The calculation and judgment unit 2 includes a data calculation module 21 and a high and low judgment module 22;

[0066] The data calculation module 21 is used to receive the historical shared plasma resource quantity data obtained in the data analysis module 11 and the shared plasma resource quantity data allocated in the matching allocation module 12, and the corresponding time point, and use the double exponential smoothing method to calculate the smoothing value of the corresponding time point according to the historical shared plasma resource quantity data, the corresponding time point and the allocated shared plasma resource quantity data. By calculating the smoothing value, it is more suitable for trend analysis, and it can be easier to identify long-term trend changes, which is helpful for making future plans. Then, according to the calculated smoothing value of the corresponding time point, the trend value of the shared plasma resource quantity of the plasma station is calculated. By calculating the trend value of the shared resource quantity, the accuracy of the prediction can be improved, and the prediction result can be made more reliable and accurate;

[0067] The implementation steps of using the double exponential smoothing method to analyze the changing trend of the number of shared resources in the data calculation module 21 are as follows:

[0068] Step 1: Collect and obtain historical shared plasma resource quantity data LS sl , Allocated shared plasma resource quantity data FP sl and the corresponding time point t, and based on the historical shared plasma resource quantity data LS sl and the amount of shared plasma resources allocated FP sl Set the standard smoothing parameters a and b;

[0069] Step 2: Get the smoothed value S of the previous time point (t-1) from the data repository t-1 and trend value T t-1 , and using the smoothing parameter a, the corresponding time point t, and the allocated shared plasma resource quantity data FP sl , the smoothing value S at the previous time point t-1 and trend value T t-1 Calculate the smoothing value at the corresponding time point t to obtain the calculated smoothing value S at the corresponding time point t , the specific algorithm formula is:

[0070] S t =(a×FP sl )+(1-a)×(S t-1 +T t-1 );

[0071] Among them, the value range of the smoothing parameter a is (0,1). This formula is used to calculate the smoothing value at time point t, which is convenient for analyzing the subsequent trend of changes in the number of shared resources of pulp stations;

[0072] Step 3: Use the calculated smoothing value S at the corresponding time point t , the smoothing value S at the previous time point t-1 and trend value T t-1 , smoothing parameter b is used to calculate the trend value of the number of shared plasma resources in the plasma station, and the calculated trend value of the number of shared plasma resources T is obtained. t , the specific algorithm formula is:

[0073] T t =b×(S t -S t-1 )+(1-b)×T t-1 ;

[0074] Among them, the value range of the smoothing parameter b is (0,1). This formula is used to calculate the trend value T of the number of shared plasma resources. t , which is convenient for predicting the future shared resource situation;

[0075] The high and low judgment module 22 is used to receive the corresponding time point smoothing value and the calculated shared plasma resource quantity trend value calculated in the data calculation module 21, and use the prediction algorithm to predict the shared plasma resource value at the future time point according to the calculated corresponding time point smoothing value and the calculated shared plasma resource quantity trend value, and then use the predicted future time point shared plasma resource value and the set standard shared plasma resource range value to judge whether there is a high plasma demand period and a low plasma demand period in the shared plasma resource situation of the plasma station at the future time point.

[0076] The realization principle of using the prediction algorithm in the high and low judgment module 22 to predict the shared resource value in the future time period is as follows:

[0077] First, collect the calculated smoothing values ​​S at the corresponding time points t and the calculated trend value of the number of shared plasma resources T t And calculate the shared plasma resource value at the future time point, and obtain the calculated shared resource value hat at the future time point y , calculate the shared resource value hat at the future time point y That is, the predicted shared plasma resource value at a future time point. The specific algorithm formula is:

[0078] hat y =S t +(h×T t );

[0079] Among them, h refers to a future time point, in hours. This formula is used to predict the shared resource value at a future time point, so as to facilitate the subsequent accurate judgment of the shared plasma resource situation of the plasma station. There will be periods of high plasma demand and low plasma demand at future time points;

[0080] Example:

[0081] Assuming that the shared plasma resource value is predicted 1 hour later, the corresponding time point smoothing value S calculated at the current time point is t =100, the current calculated trend value of the number of shared plasma resources T t =5, the future time point h = 1 hour later, the specific algorithm formula;

[0082] hat y =100+(5×1)=105;

[0083] It indicates that the demand for shared plasma resource value 105 is predicted at the future time point h = 1 hour later;

[0084] The specific judgment situations in the high and low judgment module 22 include:

[0085] Case 1: When the predicted shared plasma resource value at a future time point is greater than the set standard shared plasma resource range value, it indicates that there is a high plasma demand period at the predicted future time point, which will cause a rapid increase in the patient's demand for shared plasma resources, and a high plasma demand period command is transmitted to the optimization allocation unit 3;

[0086] Case 2: When the predicted shared plasma resource value at a future time point is less than the set standard shared plasma resource range value, it indicates that there is a period of low plasma demand at the predicted future time point, which will result in the plasma resources shared by the plasma station being unable to be fully utilized. A command for the existence of a period of low plasma demand is transmitted to the optimization allocation unit 3;

[0087] Case 3: When the predicted shared plasma resource value at a future time point is within the set standard shared plasma resource range, it means that there will be no high plasma demand period or low plasma demand period at the future time point;

[0088] The optimization allocation unit 3 includes an item set generation module 31, a frequency statistics module 32 and an evaluation allocation module 33;

[0089] The item set generation module 31 is used to receive the command data with different common conditions matched in the matching allocation module 12 or the plasma high demand period command or the plasma low demand period command in the high and low judgment module 22. The item set generation module 31 obtains the analyzed patient plasma demand data and the analyzed shared plasma resource rule data from the data analysis module 11 and integrates them into a data set, generates a request item set according to the requested plasma storage time and the coverage of the requested location in the analyzed patient plasma demand data, and then generates a shared item set according to the shared plasma storage time and the coverage of the shared location in the analyzed shared plasma resource rule data;

[0090] The frequency counting module 32 is used to receive the request item set and the shared item set in the item set generation module 31, and count the number of times the items in the request item set and the shared item set appear independently in the data set, and the number of times the items in the request item set and the shared item set appear simultaneously in the data set. At the same time, it is also necessary to count the total number of times all the items in the request item set and all the items in the shared item set appear in the data set, and then conduct confidence and expenditure mining based on the number of times the items in the request item set and the shared item set appear independently, the number of times the items in the request item set and the shared item set appear simultaneously in the data set, and the total number of times they appear.

[0091] Steps to implement mining confidence and expenditure:

[0092] Step 1: Collect the number of independent occurrences of items in the requested item set X and the items in the shared item set Y and obtain the number of occurrences of items in the requested item set X c and the number of occurrences of items in the shared itemset Y c , collect the number of times the items in the request item set X and the items in the shared item set Y appear in the data set and obtain the number of simultaneous occurrences XY c ;

[0093] Step 2: Use the number of occurrences X c and the number of times XY appears at the same time c Calculate the confidence and obtain the calculated confidence ZX d , the calculated confidence is the mining confidence, the specific algorithm formula is:

[0094] ZX d =XY c / Xc ;

[0095] Among them, this formula is used to calculate the confidence level, which is convenient for the subsequent evaluation of the improvement level;

[0096] Step 3: Use the number of occurrences Y c and the total number of occurrences Z c Calculate the support and obtain the calculated support ZC d , the calculated support is the mined support, the specific algorithm formula is:

[0097] ZC d =Y c / Z c ;

[0098] Among them, this formula is used to calculate the support degree, which is convenient for the subsequent evaluation of the improvement degree.

[0099] The evaluation and allocation module 33 is used to receive the support and confidence mined in the frequency statistics module 32, and use the mined support and confidence to evaluate the lift, and then use the assessed lift to judge the relevance with the set standard lift, and then optimize the allocation of shared plasma resources according to the judged relevance;

[0100] The implementation principle of evaluation lift:

[0101] First collect the mined support ZC d and the mining confidence ZX d Evaluate the lift and obtain the lift TS d , the specific algorithm formula is:

[0102] TS d =ZX d / ZC d ;

[0103] Among them, this formula is used to evaluate the lift, and can provide a quantitative evaluation of the association rules through support and confidence. By calculating the lift, the degree of association between the request item level and the shared item level can be more accurately quantified, thereby optimizing the effective use of plasma resources;

[0104] The specific evaluation conditions in the evaluation allocation module 33 include:

[0105] Case 1: When the evaluation improvement is greater than the set standard improvement, it means that there is a strong correlation between the items in the request item set and the items in the shared item set, and it is more reasonable to optimize the allocation of shared plasma resources;

[0106] Case 2: When the evaluated lift is equal to the set standard lift, it means that there is no significant correlation between the items in the request item set and the items in the shared item set, and it is not recommended to optimize the allocation of shared plasma resources;

[0107] Case 2: When the evaluated lift is equal to the set standard lift, it indicates that there is a negative correlation between the items in the request item set and the items in the shared item set, and it is not recommended to allocate shared plasma resources.

[0108] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. The pulp station resource sharing system deployed on the SaaS platform is characterized by: It includes an analysis and resource allocation unit (1), a calculation and judgment unit (2), and an optimization allocation unit (3); The analysis and resource allocation unit (1) uses the SaaS platform to obtain patient-related plasma demands and related sharable plasma resources, and analyzes the patient plasma demands and the shared plasma resource rules, and then matches and allocates common conditions according to the analyzed patient plasma demands and the analyzed shared plasma resource rules, and records the time point corresponding to the amount of allocated shared plasma resources; The calculation and judgment unit (2) is used to receive the number of shared plasma resources allocated in the analysis and resource allocation unit (1), calculate the smoothed value of the corresponding time point at the corresponding time point, and then predict whether there will be a high plasma demand period and a low plasma demand period at a future time point based on the calculated smoothed value of the corresponding time point; The calculation and judgment unit (2) comprises a data calculation module (21) and a high and low judgment module (22); The data calculation module (21) is used to receive the historical shared plasma resource quantity data obtained in the data analysis module (11) and the shared plasma resource quantity data allocated in the matching allocation module (12), and the corresponding time point, and use the double exponential smoothing method to calculate the smoothing value of the corresponding time point based on the obtained historical shared plasma resource quantity data, the corresponding time point and the allocated shared plasma resource quantity data, and then calculate the trend value of the plasma station shared plasma resource quantity based on the calculated smoothing value of the corresponding time point; The implementation steps of using double exponential smoothing method to analyze the changing trend of the number of shared resources are as follows: Step 1: Collect and obtain historical shared plasma resource quantity data LS sl , Allocated shared plasma resource quantity data FP sl and the corresponding time point t, and based on the historical shared plasma resource quantity data LS sl and the amount of shared plasma resources allocated FP sl Set the standard smoothing parameters a and b; Step 2: Get the smoothed value S of the previous time point (t-1) from the data repository t-1 and trend value T t-1 , and using the smoothing parameter a, the corresponding time point t, and the allocated shared plasma resource quantity data FP sl , the smoothing value S at the previous time point t-1 and trend value T t-1 Calculate the smoothing value at the corresponding time point t to obtain the calculated smoothing value S at the corresponding time point t , the specific algorithm formula is: S t =(a×FP sl )+(1-a)×(S t-1 +T t-1 ); Among them, the value range of the smoothing parameter a is (0,1); Step 3: Use the calculated smoothing value S at the corresponding time point t , the smoothing value S at the previous time point t-1 and trend value T t-1 , smoothing parameter b is used to calculate the trend value of the number of shared plasma resources in the plasma station, and the calculated trend value of the number of shared plasma resources T is obtained. t , the specific algorithm formula is: T t =b×(S t -S t-1 )+(1-b)×T t-1 ; Among them, the value range of the smoothing parameter b is (0,1); The optimization allocation unit (3) is used to receive commands with different common conditions matched in the analysis and resource allocation unit (1) or plasma high demand period commands or plasma low demand period commands in the calculation and judgment unit (2). The optimization allocation unit (3) obtains the analyzed patient plasma demand and the analyzed shared plasma resource rules from the analysis and resource allocation unit (1) and evaluates the degree of improvement, and then uses the evaluated degree of improvement to judge the correlation with the set standard degree of improvement and optimizes the allocation of shared plasma resources.

2. The pulp station resource sharing system deployed by the SaaS platform according to claim 1 is characterized by: The analysis and resource allocation unit (1) comprises a data analysis module (11) and a matching allocation module (12); The data analysis module (11) obtains patient-related plasma demand through the SaaS platform, analyzes the patient's plasma demand based on the obtained patient-related plasma demand data, obtains relevant sharable plasma resources from the plasma station, and analyzes the shared plasma resource rules based on the obtained relevant sharable plasma resources; The matching allocation module (12) is used to receive the patient plasma demand data and the analyzed shared plasma resource rule data analyzed in the data analysis module (11), and deploy the analyzed patient plasma demand data to the plasma station through the SaaS platform, and then match the common conditions according to the analyzed patient plasma demand data and the analyzed shared plasma resource rule data.

3. The pulp station resource sharing system deployed by the SaaS platform according to claim 2 is characterized in that: The matching of common conditions in the matching allocation module (12): The patient plasma demand data XQ analyzed includes the requested plasma storage time QQ sc , Coverage of requested locations QQ dd The analyzed shared plasma resource rule data GZ includes the storage time GX of shared plasma sc , the coverage of shared locations GX dd , the analyzed patient plasma demand data XQ and the analyzed shared plasma resource rule data GZ have common conditions of duration sc and location dd, and the duration sc and location dd are used as the matching common conditions PP gx , when the plasma duration sc and location dd required by the patient are not within the duration sc and location dd of the shared plasma resource, then the commonality condition PP gx No match, when the plasma duration sc and location dd required by the patient are within the duration sc and location dd of the shared plasma resource, then the commonality condition PP gx Match.

4. The pulp station resource sharing system deployed by the SaaS platform according to claim 2 is characterized in that: The specific matching conditions in the matching allocation module (12) include: Case ①: When the analyzed patient plasma demand data and the analyzed shared plasma resource rule data match the same common conditions, the shared resources of the plasma station are screened according to the matched common conditions, and the shared resources of the plasma station are allocated to the patient through the SaaS platform. The time point corresponding to the allocated shared plasma resource quantity data is recorded, and the allocated shared plasma resource quantity data and the corresponding time point are transmitted to the calculation and judgment unit (2); Case ②: When the common conditions matched by the analyzed patient plasma demand data and the analyzed shared plasma resource rule data are different, the command data with different matching common conditions are transmitted to the optimization allocation unit (3).

5. The pulp station resource sharing system deployed by the SaaS platform according to claim 2 is characterized in that: The high and low judgment module (22) is used to receive the corresponding time point smoothing value and the calculated shared plasma resource quantity trend value calculated in the data calculation module (21), and use the prediction algorithm to predict the shared plasma resource value at a future time point based on the calculated corresponding time point smoothing value and the calculated shared plasma resource quantity trend value, and then use the predicted shared plasma resource value at the future time point and the set standard shared plasma resource range value to judge whether the shared plasma resource situation of the plasma station will have a high plasma demand period and a low plasma demand period at a future time point.

6. The pulp station resource sharing system deployed by the SaaS platform according to claim 5 is characterized by: The implementation principle of using the prediction algorithm in the high and low judgment module (22) to predict the shared resource value in the future time period is: First, collect the calculated smoothing values ​​S at the corresponding time points t and the calculated trend value of the number of shared plasma resources T t And calculate the shared plasma resource value at the future time point, and obtain the calculated shared resource value hat at the future time point y , calculate the shared resource value hat at the future time point y That is, the predicted shared plasma resource value at a future time point. The specific algorithm formula is: hat y =S t +(h×T t ); Here, h refers to a future time point in hours.

7. The pulp station resource sharing system deployed by the SaaS platform according to claim 5 is characterized in that: The specific judgment situations in the high and low judgment module (22) include: Case 1: When the predicted shared plasma resource value at a future time point is greater than the set standard shared plasma resource range value, it indicates that there is a high plasma demand period at the predicted future time point. The high plasma demand period will cause a rapid increase in the patient's demand for shared plasma resources, and a high plasma demand period command will be transmitted to the optimization allocation unit (3); Case 2: When the predicted shared plasma resource value at a future time point is less than the set standard shared plasma resource range value, it indicates that there is a period of low plasma demand at the predicted future time point. The low plasma demand period will result in the plasma station shared plasma resources being unable to be fully utilized, and a command for the existence of a low plasma demand period will be transmitted to the optimization allocation unit (3); Case 3: When the predicted shared plasma resource value at a future time point is within the set standard shared plasma resource range, it means that there will be no period of high plasma demand or low plasma demand at the future time point.

8. The pulp station resource sharing system deployed by the SaaS platform according to claim 7 is characterized in that: The optimization allocation unit (3) comprises an item set generation module (31), a frequency statistics module (32) and an evaluation allocation module (33); The generating item set module (31) is used to receive command data with different common conditions matched in the matching allocation module (12) or plasma high demand period command or plasma low demand period command in the high and low judgment module (22), the generating item set module (31) obtains the analyzed patient plasma demand data and the analyzed shared plasma resource rule data from the data analysis module (11) and integrates them into a data set, generates a request item set according to the requested plasma storage time and the coverage of the requested location in the analyzed patient plasma demand data, and then generates a shared item set according to the shared plasma storage time and the coverage of the shared location in the analyzed shared plasma resource rule data; The frequency counting module (32) is used to receive the request item set and the shared item set in the item set generation module (31), and count the number of times the items in the request item set and the shared item set appear independently in the data set, and the number of times the items in the request item set and the shared item set appear simultaneously in the data set. At the same time, it is also necessary to count the total number of times all items in the request item set and all items in the shared item set appear in the data set, and then perform confidence and expenditure mining based on the number of times the items in the request item set and the shared item set appear independently, the number of times the items in the request item set and the shared item set appear simultaneously in the data set, and the total number of times they appear. The evaluation and allocation module (33) is used to receive the mined support and mined confidence in the frequency statistics module (32), and use the mined support and mined confidence to evaluate the lift, and then use the evaluated lift to judge the correlation with the set standard lift, and then optimize the allocation of shared plasma resources based on the judged correlation.

Citation Information

Cited By

  • Biological resource identification method and system based on Internet of Things technology, and medium

    CN120895157A