Drug purchase decision support optimization method based on big data

Abstract

The invention discloses a big data-based drug purchase decision support optimization method, and relates to the technical field of drug purchase, and the method comprises the steps: screening drugs with the same purchase name in a purchase platform, and calculating a coincidence coefficient of a first to-be-purchased drug; calculating a first manufacturer evaluation coefficient and a second manufacturer evaluation coefficient of medicines in the first to-be-purchased medicine library, and calculating a manufacturer comprehensive evaluation index according to the first manufacturer evaluation coefficient and the second manufacturer evaluation coefficient; obtaining characters, prices and weights of drugs in the first to-be-purchased drug library, calculating unit prices of the drugs in the first to-be-purchased drug library, calculating purchase weights of the drugs in the first to-be-purchased drug library in combination with a coincidence coefficient and a manufacturer comprehensive evaluation index, sorting and outputting the drugs from small to large according to the purchase weights, and comprehensively considering multiple dimension information of the drugs, and drugs and manufacturers with high cost performance and reliable quality can be selected, and the scientificity and accuracy of purchase decision making are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of drug procurement, and in particular to a drug procurement decision support optimization method based on big data. Background Art

[0002] With the rapid development of the pharmaceutical industry, the complexity of drug procurement continues to increase. Traditional drug procurement decision-making methods are subjective and inaccurate, and it is difficult to adapt to the changing needs of the modern pharmaceutical market. In order to overcome these challenges, drug procurement decision support optimization methods based on big data have emerged. The emergence of big data technology provides strong support for drug procurement decisions. Through in-depth mining and analysis of massive drug procurement data, market trends, competitor information, etc., companies can more accurately predict market demand, optimize procurement strategies, reduce procurement costs, and improve the scientificity and accuracy of procurement decisions.

[0003] In the Chinese invention application with application publication number CN110782170A, a drug procurement optimization method and system are disclosed, including calculating the substitution rate, medical insurance rate and historical procurement rate of each supplier's quoted drug set based on each supplier's quoted drug set; calculating the ranking weight value of each drug of each supplier based on the calculated substitution rate, medical insurance rate and historical procurement rate; based on each supplier's quoted drug set, counting the set of drugs quoted by at least two suppliers, recorded as the first set, and calculating the substitution rate, medical insurance rate and historical procurement rate of the drugs in the first set; calculating the ranking weight values ​​of all drugs of each supplier corresponding to the drugs in the first set and sorting them, and taking the supplier corresponding to the set ranking as the supplier to be selected this time.

[0004] In the above invention application, based on the set of drugs quoted by each supplier, the set of drugs quoted by at least two suppliers is counted, the substitution rate, medical insurance rate and historical procurement rate of the drugs in the first set, and the ranking weight value of the optimal solution for each drug of each supplier are calculated, the ranking weight values ​​of all drugs of each supplier corresponding to the drugs in the first set are calculated and sorted, and the supplier corresponding to the set ranking is taken as the supplier to be selected this time, but all purchased drugs are from the same supplier. Relying on a single supplier means that if the supplier encounters production interruptions, quality problems, financial difficulties or legal disputes, the entire drug supply chain will face huge risks, which may lead to drug shortages and affect the operation of medical institutions and patient treatment.

[0005] To this end, the present invention provides a drug procurement decision support optimization method based on big data. Summary of the invention

[0006] 1. Technical issues to be solved

[0007] In view of the deficiencies in the prior art, the present invention provides a drug procurement decision support optimization method based on big data. The present invention inputs the procurement name of the drug to be purchased, screens out the drugs with the same procurement name in the procurement platform, constructs a first drug library to be purchased, calculates the compliance coefficient, the manufacturer's comprehensive evaluation index and the unit price of the first drug to be purchased, calculates the procurement weight of the drugs in the first drug library to be purchased according to the unit price, the compliance coefficient and the manufacturer's comprehensive evaluation index, and outputs the drugs in ascending order according to the procurement weight. The present invention comprehensively considers multiple dimensional information of the drugs, avoids one-sided decisions caused by a single factor, and can select drugs and manufacturers with high cost performance and reliable quality, which helps to ensure the quality and supply stability of the drugs, and ensures the scientificity and accuracy of procurement decisions, thereby solving the technical problems recorded in the background technology.

[0008] (II) Technical solution

[0009] To achieve the above objectives, the present invention is implemented through the following technical solutions: a drug procurement decision support optimization method based on big data, comprising the following steps:

[0010] Enter the purchase name of the drug to be purchased, filter out the drugs with the same purchase name in the procurement platform, build the first drug library to be purchased, and obtain the validity period of the drugs in the first drug library to be purchased Sc i , concentration Nd i and trait Xz i , calculate the compliance coefficient Df of the first drug to be purchased i ;

[0011] Based on the production years Sn of the drug manufacturers in the first drug library to be purchased i , production capacity Sc i and market share Sf i , calculate the first manufacturer evaluation coefficient Sdp of the drugs in the first drug library to be purchased i , and based on the debt-to-asset ratio Fz in the past year i , Cash inflow and outflow ratio Xb i , Cash flow to debt ratio Xf i , Cash flow to total assets ratio Xz i and annual profit margin Nv i , calculate the second manufacturer evaluation coefficient Sep of the drugs in the first drug library to be purchased i , and finally based on the first manufacturer's assessment coefficient Sdp i and the second producer assessment factor Sep i Calculation of the producer comprehensive assessment index Zp i ;

[0012] Get the properties Xz of the drugs in the first drug library to be purchased i 、Pricei and weight La i , calculate the unit price Dj of the drugs in the first drug library to be purchased i , combined with the compliance coefficient Df i , Manufacturer comprehensive evaluation index Zp i , calculate the purchase weight Qz of the drugs in the first drug library to be purchased i , the drugs are divided into i Sort the output from smallest to largest.

[0013] Furthermore, the purchase name, purchase concentration Cn and purchase property Cx (solid, liquid, gas) of the medicine to be purchased are input, and the medicines with the same purchase name are screened out in the purchase platform according to the purchase name to construct the first library of medicines to be purchased.

[0014] Further, the validity period of the drug in the first drug library to be purchased is obtained from the drug packaging and instructions. i , concentration Nd i and trait Xz i , calculate the compliance coefficient Df of the first drug to be purchased i :

[0015]

[0016] Among them, when the drug is solid, Xz i Take 3, when the drug is liquid, Xz i Take 2, when the drug is gaseous, Xz i Take 1, i represents the serial number of the drugs in the first drug library to be purchased, i = 1, 2, ..., r.

[0017] Furthermore, the manufacturer of the drug in the first drug library to be purchased is obtained from the drug packaging and instructions, and the manufacturer's production year Sn is obtained from the manufacturer's official website or annual report. i , production capacity Sc i and market share Sf i , calculate the first manufacturer evaluation coefficient Sdp of the drugs in the first drug library to be purchased i :

[0018]

[0019] The first manufacturer evaluation coefficient Sdp of the corresponding first drug library to be purchased i The calculation formula is as above.

[0020] Furthermore, the debt-to-asset ratio Fz of the manufacturer in the past year is obtained from the manufacturer's official website or annual report. i , Cash inflow and outflow ratio Xb i , Cash flow to debt ratio Xf i, Cash flow to total assets ratio Xz i and annual profit margin Nv i , calculate the second manufacturer evaluation coefficient Sep of the drugs in the first drug library to be purchased i :

[0021]

[0022] The corresponding second manufacturer evaluation coefficient Sep of the drugs in the first drug library to be purchased i The calculation formula is as above.

[0023] Further, the first manufacturer evaluation coefficient Sdp of the drug in the first drug library to be purchased is obtained. i and the second producer assessment factor Sep i , calculate the comprehensive evaluation index Zp of the manufacturer i :

[0024]

[0025] Among them, max(Sdp i ) represents the maximum value of the first manufacturer evaluation coefficient of the drugs in the first drug library to be purchased, min(Sdp i ) represents the minimum value of the first manufacturer evaluation coefficient of the drugs in the first drug library to be purchased, max(Sep i ) represents the maximum value of the second manufacturer evaluation coefficient of the drugs in the first drug library to be purchased, min(Sep i ) represents the minimum value of the second manufacturer evaluation coefficient of the drugs in the first drug library to be purchased.

[0026] Further, the properties Xz of the drugs in the first drug library to be purchased are obtained from the procurement platform i 、Price i and weight La i , calculate the unit price Dj of the drugs in the first drug library to be purchased i :

[0027]

[0028] The corresponding unit price Dj of the drug in the first drug library to be purchased i The calculation formula is as above.

[0029] Further, obtain the unit price Dj of the drugs in the first drug library to be purchased i , compliance coefficient Df i , Manufacturer comprehensive evaluation index Zp i , calculate the purchase weight Qzx of the drugs in the first drug library to be purchased:

[0030]

[0031] The corresponding purchase weight Qz of the drugs in the first drug library to be purchased i The calculation formula is as above.

[0032] Furthermore, the purchase weight Qz of the drugs in the first drug library to be purchased is i After sorting from small to large, the drugs are output according to the sorting for purchasing decisions.

[0033] (III) Beneficial effects

[0034] The present invention provides a drug procurement decision support optimization method based on big data, which has the following beneficial effects:

[0035] 1. Enter the purchase name of the drug to be purchased, filter out the drugs with the same purchase name in the procurement platform, build the first drug library to be purchased, and obtain the validity period of the drugs in the first drug library to be purchased Sc i , concentration Nd i and trait Xz i , calculate the compliance coefficient Df of the first drug to be purchased i , a comprehensive assessment can be made on whether the drugs meet the procurement standards, thereby ensuring that the purchased drugs meet the usage requirements.

[0036] 2. Based on the production years Sn of the drug manufacturers in the first drug library to be purchased i , production capacity Sc i and market share Sf i , calculate the first manufacturer evaluation coefficient Sdp of the drugs in the first drug library to be purchased i , and based on the debt-to-asset ratio Fz in the past year i , Cash inflow and outflow ratio Xb i , Cash flow to debt ratio Xf i , Cash flow to total assets ratio Xz i and annual profit margin Nv i , calculate the second manufacturer evaluation coefficient Sep of the drugs in the first drug library to be purchased i , and finally based on the first manufacturer's assessment coefficient Sdp i and the second producer assessment factor Sep i Calculation of the producer comprehensive assessment index Zp i By comprehensively considering multiple dimensions of information from manufacturers, we can avoid one-sided decisions caused by a single factor, help ensure the quality and supply stability of drugs, and improve the scientificity and accuracy of procurement decisions.

[0037] 3. Obtain the properties Xz of the drugs in the first drug library to be purchased i 、Price i and weight La i, calculate the unit price Dj of the drugs in the first drug library to be purchased i , combined with the compliance coefficient Df i , Manufacturer comprehensive evaluation index Zp i , calculate the purchase weight Qz of the drugs in the first drug library to be purchased i , the drugs are divided into i By sorting the output from small to large and comprehensively considering the multi-dimensional information of drugs, we can select drugs and manufacturers with high cost performance and reliable quality, ensuring the scientificity and accuracy of procurement decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 The present invention is a flowchart of a drug procurement decision support optimization method based on big data. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of 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.

[0040] See also Figure 1 The present invention provides a drug procurement decision support optimization method based on big data, comprising the following steps:

[0041] Step 1: Enter the purchase name of the drug to be purchased, filter out the drugs with the same purchase name in the procurement platform, build the first drug library to be purchased, and obtain the validity period of the drugs in the first drug library to be purchased Sc i , concentration Nd i and trait Xz i , calculate the compliance coefficient Df of the first drug to be purchased i .

[0042] The step 2 includes the following contents:

[0043] Step 101: Input the purchase name, purchase concentration Cn and purchase property Cx (solid, liquid, gas) of the medicine to be purchased, filter out the medicines with the same purchase name in the purchase platform according to the purchase name, and build the first medicine library to be purchased.

[0044] Step 102: Obtain the validity period Sc of the drug in the first drug library from the drug packaging and instructions. i , concentration Nd i and trait Xz i , calculate the compliance coefficient Df of the first drug to be purchased i :

[0045]

[0046] Among them, when the drug is solid, Xz i Take 3, when the drug is liquid, Xz i Take 2, when the drug is gaseous, Xz i Take 1, i represents the serial number of the drugs in the first drug library to be purchased, i = 1, 2, ..., r.

[0047] When using, combine the contents in steps 101 and 102:

[0048] Enter the purchase name of the drug to be purchased, filter out the drugs with the same purchase name in the procurement platform, build the first drug library to be purchased, and obtain the validity period of the drugs in the first drug library to be purchased Sc i , concentration Nd i and trait Xz i , calculate the compliance coefficient Df of the first drug to be purchased i , a comprehensive assessment can be made on whether the drugs meet the procurement standards, thereby ensuring that the purchased drugs meet the usage requirements.

[0049] Step 2: Based on the production years Sn of the drug manufacturers in the first drug library to be purchased i , production capacity Sc i and market share Sf i , calculate the first manufacturer evaluation coefficient Sdp of the drugs in the first drug library to be purchased i , and based on the debt-to-asset ratio Fz in the past year i , Cash inflow and outflow ratio Xb i , Cash flow to debt ratio Xf i , Cash flow to total assets ratio Xz i and annual profit margin Nv i , calculate the second manufacturer evaluation coefficient Sep of the drugs in the first drug library to be purchased i , and finally based on the first manufacturer's assessment coefficient Sdp i and the second producer assessment factor Sep i Calculation of the producer comprehensive assessment index Zp i .

[0050] The second step mentioned includes the following:

[0051] Step 201: Obtain the manufacturer of the drug in the first drug library from the drug packaging and instructions, and obtain the manufacturer's production year Sn from the manufacturer's official website or annual report. i , production capacity Sc i and market share Sf i, calculate the first manufacturer evaluation coefficient Sdp of the drugs in the first drug library to be purchased i :

[0052]

[0053] The first manufacturer evaluation coefficient Sdp of the corresponding first drug library to be purchased i The calculation formula is as above.

[0054] Step 202: Obtain the debt-to-asset ratio Fz of the manufacturer in the past year from the manufacturer's official website or annual report i , Cash inflow and outflow ratio Xb i , Cash flow to debt ratio Xf i , Cash flow to total assets ratio Xz i and annual profit margin Nv i , calculate the second manufacturer evaluation coefficient Sep of the drugs in the first drug library to be purchased i :

[0055]

[0056] The corresponding second manufacturer evaluation coefficient Sep of the drugs in the first drug library to be purchased i The calculation formula is as above.

[0057] Step 203: Obtain the first manufacturer evaluation coefficient Sdp of the drugs in the first drug library to be purchased i and the second producer assessment factor Sep i , calculate the comprehensive evaluation index Zp of the manufacturer i :

[0058]

[0059] Among them, max(Sdp i ) represents the maximum value of the first manufacturer evaluation coefficient of the drugs in the first drug library to be purchased, min(Sdp i ) represents the minimum value of the first manufacturer evaluation coefficient of the drugs in the first drug library to be purchased, max(Sep i ) represents the maximum value of the second manufacturer evaluation coefficient of the drugs in the first drug library to be purchased, min(Sep i ) represents the minimum value of the second manufacturer evaluation coefficient of the drugs in the first drug library to be purchased.

[0060] When using, combine the contents in steps 201 to 203:

[0061] Based on the production years Sn of the drug manufacturers in the first drug library to be purchased i , production capacity Sc i and market share Sf i, calculate the first manufacturer evaluation coefficient Sdp of the drugs in the first drug library to be purchased i , and based on the debt-to-asset ratio Fz in the past year i , Cash inflow and outflow ratio Xb i , Cash flow to debt ratio Xf i , Cash flow to total assets ratio Xz i and annual profit margin Nv i , calculate the second manufacturer evaluation coefficient Sep of the drugs in the first drug library to be purchased i , and finally based on the first manufacturer's assessment coefficient Sdp i and the second producer assessment factor Sep i Calculation of the producer comprehensive assessment index Zp i By comprehensively considering multiple dimensions of information from manufacturers, we can avoid one-sided decisions caused by a single factor, help ensure the quality and supply stability of drugs, and improve the scientificity and accuracy of procurement decisions.

[0062] Step 3: Obtain the properties Xz of the drugs in the first drug library to be purchased i 、Price i and weight La i , calculate the unit price Dj of the drugs in the first drug library to be purchased i , combined with the compliance coefficient Df i , Manufacturer comprehensive evaluation index Zp i , calculate the purchase weight Qz of the drugs in the first drug library to be purchased i , the drugs are divided into i Sort the output from smallest to largest.

[0063] The step three includes the following contents:

[0064] Step 301: Obtain the properties Xz of the drugs in the first drug library to be purchased from the procurement platform i 、Price i and weight La i , calculate the unit price Dj of the drugs in the first drug library to be purchased i :

[0065]

[0066] The corresponding unit price Dj of the drug in the first drug library to be purchased i The calculation formula is as above.

[0067] Step 302: Obtain the unit price Dj of the drugs in the first drug library to be purchased i , compliance coefficient Df i , Manufacturer comprehensive evaluation index Zp i , calculate the purchase weight Qz of the drugs in the first drug library to be purchasedi :

[0068]

[0069] The corresponding purchase weight Qz of the drugs in the first drug library to be purchased i The calculation formula is as above.

[0070] Step 303: Set the purchase weight Qz of the drugs in the first drug library to be purchased i After sorting from small to large, the drugs are output according to the sorting for purchasing decisions.

[0071] When using, combine the contents in steps 301 to 303:

[0072] Get the properties Xz of the drugs in the first drug library to be purchased i 、Price i and weight La i , calculate the unit price Dj of the drugs in the first drug library to be purchased i , combined with the compliance coefficient Df i , Manufacturer comprehensive evaluation index Zp i , calculate the purchase weight Qz of the drugs in the first drug library to be purchased i , the drugs are divided into i By sorting the output from small to large and comprehensively considering the multi-dimensional information of drugs, we can select drugs and manufacturers with high cost performance and reliable quality, ensuring the scientificity and accuracy of procurement decisions.

[0073] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0074] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0075] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A drug procurement decision support optimization method based on big data, characterized by: The steps include: Input the purchase name of the drug to be purchased, filter out drugs with the same purchase name in the procurement platform, build a first drug library to be purchased, obtain the validity period Sci, concentration Ndi and property Xzi of the drugs in the first drug library to be purchased, and calculate the compliance coefficient Dfi of the first drug to be purchased; Based on the production years Sni, production capacity Sci and market share Sfi of the drug manufacturers in the first drug library to be purchased, the evaluation coefficient Sdpi of the first drug manufacturer in the first drug library to be purchased is calculated, and based on the asset-liability ratio Fzi, cash inflow-outflow ratio Xbi, cash inflow-liability ratio Xfi, cash inflow-to-total asset ratio Xzi and annual profit margin Nvi in ​​the past year, the evaluation coefficient Sepi of the second drug manufacturer in the first drug library to be purchased is calculated. Finally, the comprehensive evaluation index Zpi of the manufacturer is calculated based on the evaluation coefficient Sdpi of the first manufacturer and the evaluation coefficient Sepi of the second manufacturer; Obtain the properties Xzi, price Jgi and weight Lai of the drugs in the first drug library to be purchased, calculate the unit price Dji of the drugs in the first drug library to be purchased, combine the compliance coefficient Dfi and the manufacturer's comprehensive evaluation index Zpi, calculate the purchase weight Qzi of the drugs in the first drug library to be purchased, and output the drugs in ascending order according to the purchase weight Qzi.

2. According to the big data-based drug procurement decision support optimization method of claim 1, it is characterized by: Obtain the validity period Sci, concentration Ndi and properties Xzi of the drugs in the first drug library to be purchased from the drug packaging and instructions, and calculate the compliance coefficient Dfi of the first drug to be purchased: Among them, when the property of the drug is solid, Xzi is 3, when the property of the drug is liquid, Xzi is 2, and when the property of the drug is gas, Xzi is 1. i represents the sequential number of the drugs in the first drug warehouse to be purchased, i=1, 2,..., r.

3. The drug procurement decision support optimization method based on big data according to claim 2 is characterized by: Obtain the manufacturer of the drugs in the first drug library from the drug packaging and instructions, obtain the manufacturer's production years Sni, production capacity Sci and market share Sfi from the manufacturer's official website or annual report, and calculate the first manufacturer evaluation coefficient Sdpi of the drugs in the first drug library: The calculation formula for the first manufacturer evaluation coefficient Sdpi of the corresponding drugs in the first drug library to be purchased is as above.

4. The drug procurement decision support optimization method based on big data according to claim 3 is characterized by: Obtain the debt-to-asset ratio Fzi, cash inflow-outflow ratio Xbi, cash inflow-to-liability ratio Xfi, cash inflow-to-total-asset ratio Xzi and annual profit margin Nvi of the manufacturer in the past year from the manufacturer's official website or annual report, and calculate the second manufacturer evaluation coefficient Sepi of the drugs in the first drug library to be purchased: The calculation formula for the second manufacturer evaluation coefficient Sepi of the corresponding drugs in the first drug library to be purchased is as above.

5. The drug procurement decision support optimization method based on big data according to claim 4 is characterized by: Get the first manufacturer evaluation coefficient Sdpi and the second manufacturer evaluation coefficient Sepi of the drugs in the first drug library to be purchased, and calculate the manufacturer comprehensive evaluation index Zpi: Among them, max(Sdpi) represents the maximum value of the first manufacturer's evaluation coefficient of the drugs in the first drug library to be purchased, min(Sdpi) represents the minimum value of the first manufacturer's evaluation coefficient of the drugs in the first drug library to be purchased, max(Sepi) represents the maximum value of the second manufacturer's evaluation coefficient of the drugs in the first drug library to be purchased, and min(Sepi) represents the minimum value of the second manufacturer's evaluation coefficient of the drugs in the first drug library to be purchased.

6. The drug procurement decision support optimization method based on big data according to claim 1 is characterized by: Obtain the properties Xzi, price Jgi and weight Lai of the drugs in the first drug library to be purchased from the procurement platform, and calculate the unit price Dji of the drugs in the first drug library to be purchased: The calculation formula for the corresponding unit price Dji of the drugs in the first drug library to be purchased is as above.

7. The drug procurement decision support optimization method based on big data according to claim 6 is characterized by: Get the unit price Dji, compliance coefficient Dfi, and manufacturer comprehensive evaluation index Zpi of the drugs in the first drug library to be purchased, and calculate the purchase weight Qzi of the drugs in the first drug library to be purchased: The calculation formula for the corresponding purchase weight Qzi of the drugs in the first drug library to be purchased is as above.

8. The drug procurement decision support optimization method based on big data according to claim 7 is characterized by: After sorting the purchase weights Qzi of the drugs in the first drug library to be purchased from small to large, the drugs are output according to the sorting.

Images