A drug market data analysis method and system

Abstract

The present invention discloses a drug market data analysis method and system, which relates to the technical field of data analysis. The main scheme is: according to the market impact coefficient QA, consumer impact coefficient QB, economic impact coefficient QC, policy impact coefficient QD, seasonal impact value QE t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t , based on the drug sales forecast value Z t Optimizing drug production plans comprehensively considers external factors and seasonal characteristics of data, solving the problems of insufficient consideration of external factors and easy neglect of seasonal characteristics of data when preprocessing data, which leads to reduced accuracy of future drug sales forecasts. This helps companies optimize inventory management and reduce market risks.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a method and system for analyzing drug market data. Background Art

[0002] The pharmaceutical market data analysis system collects pharmaceutical sales data, pre-processes the pharmaceutical sales data into a time series, inputs the time series into a time series model, and obtains the forecast value of future pharmaceutical sales volume.

[0003] The existing technology still has the following shortcomings: the time series model is mainly based on historical sales data, and other influencing factors are not sufficiently considered. At the same time, when preprocessing the data, the seasonal characteristics of the data are easily ignored, resulting in a decrease in the accuracy of the future drug sales forecast. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides a drug market data analysis method and system, which can analyze the drug market data according to the market impact coefficient QA, consumer impact coefficient QB, economic impact coefficient QC, policy impact coefficient QD, seasonal impact value QE t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t , comprehensively considering external factors and seasonal characteristics of data, solves the problem of insufficient consideration of external factors and easy neglect of seasonal characteristics of data when preprocessing data, resulting in reduced accuracy of future drug sales forecasts.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: A drug market data analysis method, characterized in that it includes the following steps: collecting drug sales data, market data, consumer data, economic data, policy data, seasonal data and disease epidemic trend data;

[0008] Based on drug sales data and market data, calculate the price elasticity coefficient c1, market share loss rate c2 and popularity increase rate f3, and further calculate the market impact coefficient QA; calculate the age factor impact rate DY based on consumer data; and further calculate the consumer impact coefficient QB; calculate the gross domestic product impact rate EG and the consumer price index impact rate EC based on drug sales data and economic data; calculate the economic impact coefficient QC based on the gross domestic product impact rate EG and the consumer price index impact rate EC; calculate the policy impact coefficient QD based on policy data; calculate the seasonal impact value QE based on seasonal data t; Based on drug sales data and disease epidemic trend data, the slope coefficient β1 and intercept β0 are calculated, and the disease epidemic trend impact value QF is further calculated. t ;

[0009] According to the market impact coefficient QA, consumer impact coefficient QB, economic impact coefficient QC, policy impact coefficient QD, seasonal impact value QE t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t ; Based on the drug sales forecast value Z t Adjust the production plan of medicines.

[0010] In the preferred embodiment of the above-mentioned pharmaceutical market data analysis method, the method for calculating the price elasticity coefficient c1, the market share loss rate c2 and the popularity improvement rate f3 is:

[0011] The drug sales data at least includes the initial drug price a, the current drug price e2 and the price change A;

[0012] Market data include initial market demand b, demand change B, market share d1, competitor product price e1, initial drug popularity f1 and drug popularity after promotion f2;

[0013] The price elasticity coefficient c1 is calculated based on the initial drug price a, price change A, initial market demand b and demand change B. The formula is:

[0014]

[0015] The market share loss rate c2 is calculated based on the price elasticity coefficient c1, market share d1, competitor product price e1 and current drug price e2, based on the following formula:

[0016]

[0017] The formula for calculating the popularity increase rate f3 based on the initial popularity of the drug f1 and the popularity of the drug after promotion f2 is:

[0018]

[0019] In the preferred embodiment of the above-mentioned drug market data analysis method, the method for calculating the market impact coefficient QA is:

[0020] The market impact coefficient QA is calculated based on the market share loss rate c2 and the popularity increase rate f3, and the formula is:

[0021] QA=(1-c2)×f3.

[0022] In the preferred embodiment of the above-mentioned pharmaceutical market data analysis method, the method for calculating the consumer influence coefficient QB is:

[0023] Consumer data includes drug preference scores for different age groups g , average score of drug preference Sales sensitivity Y g , Preference scores of different occupational groups II u , the number of people in different occupational groups - RE u , the total number of people who scored RE, the preference scores of groups with different income levels YS v and the number of people in different income groups u ;

[0024] Drug preference scores according to different age groups g , average score of drug preference and sales sensitivity Y g The formula for calculating the age factor influence rate DY is:

[0025]

[0026] Among them, YE g is the drug preference score of the g-th age group for this drug; g is the serial number corresponding to different age groups, and its value is [1, h]; h is the number of different age groups, and its value is a positive integer; Y is the average drug preference score of the g-th age group for all drugs on the market; g is the sales sensitivity of the g-th age group;

[0027] According to the influence rate of age factor DY, preference scores of different occupational groups YF u , the number of people in different occupational groups - RE u , the total number of people who scored RE, the preference scores of groups with different income levels YS v and the number of people in different income groups u The calculation formula for the consumer impact coefficient QB is:

[0028]

[0029] Among them, YF u is the preference score of the u-th occupational group for this drug, RE u is the number of people in the u-th occupational group; u is the serial number corresponding to different occupational groups, and its value is [1, x]; x is the number of different occupational groups, and its value is a positive integer; YS v is the preference score of the vth income group for this drug, and its value is [1, r]; SR vis the number of people in the vth income level group; r is the number of groups with different income levels, which is a positive integer.

[0030] In the preferred embodiment of the above-mentioned drug market data analysis method, the method for calculating the economic impact coefficient QC is:

[0031] Economic data include the rate of change of gross domestic product (ΔGDP) and the consumer price index (E CPI ;

[0032] Drug sales data also include drug sales growth rate ΔDR;

[0033] The GDP impact rate EG is calculated based on the GDP change rate ΔGDP and the drug sales growth rate ΔDR. The formula is:

[0034]

[0035] According to the Consumer Price Index CPI , the initial drug price a and the current drug price e2 are used to calculate the consumer price index impact rate EC, based on the formula:

[0036]

[0037] The economic impact coefficient QC is calculated based on the gross domestic product impact rate EG and the consumer price index impact rate EC, and the formula is:

[0038] QC=EG-EC.

[0039] In the preferred embodiment of the above-mentioned drug market data analysis method, the method for calculating the policy impact coefficient QD based on policy data is:

[0040] Policy data include the change rate of medical insurance coverage population ΔFC, the change rate of medical insurance reimbursement ratio ΔFD, and the change rate of drug market access ΔFE;

[0041] The policy impact coefficient QD is calculated based on policy data, and the formula is:

[0042] QD=ΔFC×ρ1+ΔFD×ρ2+ΔFE×ρ3;

[0043] Among them, ρ1 is the weight coefficient of the change rate of medical insurance coverage population ΔFC, which takes a value of 0.2~0.5; ρ2 is the weight coefficient of the change rate of medical insurance reimbursement ratio ΔFD, which takes a value of 0.3~0.5; ρ3 is the weight coefficient of the change rate of drug market access ΔFE, which takes a value of 0.2~0.6; and ρ1+ρ2+ρ3=1.

[0044] In the preferred embodiment of the above-mentioned pharmaceutical market data analysis method: the seasonal impact value QE is calculated based on seasonal data.t The method is:

[0045] Seasonal data include drug Fourier coefficients γ n and the Fourier coefficient δ n ;

[0046] Calculate the seasonal impact value QE according to the seasonal cycle n t , the formula based on is:

[0047]

[0048] Among them, QE t is the seasonal impact value at time t; γ n is the Fourier coefficient of the nth seasonal cycle; n is the serial number corresponding to different seasonal cycles, and its value is [1, m]; m is the total number of seasonal cycles, and its value is a positive integer; δ n is the Fourier coefficient of the nth seasonal cycle; ε t is the seasonal error.

[0049] In the preferred embodiment of the above-mentioned pharmaceutical market data analysis method: calculating the disease epidemic trend impact value QF t The method is:

[0050] Drug sales data also includes monthly drug sales. i and monthly sales average

[0051] Disease epidemic trend data include monthly incidence rate k i and the average monthly incidence rate

[0052] Based on the monthly sales volume of drugs, the average monthly sales volume Monthly incidence rate k i and the average monthly incidence rate The slope coefficient β1 is calculated based on the formula:

[0053]

[0054] Among them, j i is the sales volume of the i-th month; i is the serial number corresponding to different months; is the average sales volume of the i-th month; k i is the incidence rate of the disease related to the drug in the i-th month; is the average incidence rate of the drug-related disease in the i-th month;

[0055] Based on the average monthly sales Slope coefficient β1 and monthly incidence mean The intercept β0 is calculated based on the formula:

[0056]

[0057] Based on the monthly sales volume of drugs j and monthly incidence rate k i , slope coefficient β1 and intercept β0 to calculate the disease epidemic trend impact value QF t , the formula based on is:

[0058] QF t =β0+β1×k t ;

[0059] Among them, QF t is the impact value of the disease epidemic trend at time t; k t is the incidence rate at time t.

[0060] In the preferred embodiment of the above-mentioned drug market data analysis method: calculating the drug sales forecast value Z t The method is:

[0061] According to the market impact coefficient QA, consumer impact coefficient QB, economic impact coefficient QC, policy impact coefficient QD, seasonal impact value QE t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t , the formula based on is

[0062] Z t =Z 0t ×(1+QA)×(1+QB)×(1+QC)+QE t +QF t ;

[0063] Among them, Z t is the predicted value of drug sales at time t; Z 0t is the basic forecast value considering only drug sales at time t.

[0064] The present invention also discloses a drug market data analysis system, which is characterized by comprising:

[0065] Data collection module, used to collect drug sales data, market data, consumer data, economic data, policy data, seasonal data and disease epidemic trend data;

[0066] The impact coefficient calculation module is used to calculate the price elasticity coefficient c1 and the popularity enhancement rate f3 based on drug sales data and market data; and further calculate the market impact coefficient QA; calculate the age factor impact rate DY based on consumer data; and further calculate the consumer impact coefficient QB; calculate the gross domestic product impact rate EG and the consumer price index impact rate EC based on drug sales data and economic data; calculate the economic impact coefficient QC based on the gross domestic product impact rate EG and the consumer price index impact rate EC; calculate the policy impact coefficient QD based on policy data; calculate the seasonal impact value QE based on seasonal data t ; Calculate the slope coefficient β1 and intercept β0 based on drug sales data and disease epidemic trend data; and further calculate the disease epidemic trend impact value QF t ;

[0067] The prediction module is used to predict the impact of the market on the QA, the consumer impact on the QB, the economic impact on the QC, the policy impact on the QD, and the seasonal impact on the QE. t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t ; Based on the drug sales forecast value Z t Adjust the production plan of medicines.

[0068] (III) Beneficial effects

[0069] The present invention provides a pharmaceutical market data analysis method and system, which has the following beneficial effects:

[0070] (1) By collecting drug sales data, market data, consumer data, economic data, policy data, seasonal data, and disease epidemic trend data, it can help companies understand market dynamics more comprehensively and provide relevant data for subsequent calculations;

[0071] (2) By calculating the market impact coefficient QA, companies can have a more comprehensive understanding of market dynamics and improve the scientific nature of their decisions. By calculating the consumer impact coefficient QB, age factors and consumer preferences can be comprehensively considered to more comprehensively reflect the impact of consumer factors on drug sales. Calculating the economic impact coefficient QC can help companies more comprehensively evaluate the impact of economic factors on drug sales and reduce operating risks brought about by changes in the economic environment. Calculating the policy impact coefficient QD based on policy data enables companies to promptly understand the impact of national policies on the pharmaceutical industry, ensure that the company's business activities comply with policy requirements, and make full use of policy opportunities to enhance the company's competitiveness. Calculating the seasonal impact value QE based on seasonal data t , enterprises can adjust production plans and inventory management according to the seasonal impact value to ensure sufficient product supply during the high-incidence season of diseases. t, enabling enterprises to understand the impact of disease epidemic trends on drug sales. Helping enterprises to predict changes in market demand in advance, providing reference for their R&D and production decisions, solving the problem of insufficient consideration of external factors and ignoring the seasonal characteristics of data during data preprocessing, which leads to reduced accuracy of future drug sales forecasts;

[0072] (3) By comprehensively considering multiple factors such as the market, consumers, economy, policy, season and disease epidemic trends, we can more comprehensively grasp the dynamic changes in the pharmaceutical market, thereby improving the accuracy of drug sales forecasts. t It helps enterprises optimize inventory management. Enterprises can arrange production plans reasonably, avoid overproduction or insufficient supply, and reduce market risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 The figure is a schematic diagram of the steps of a method for analyzing drug market data of the present invention. DETAILED DESCRIPTION

[0074] 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.

[0075] See also Figure 1 The present invention provides a method for analyzing drug market data, comprising the following steps:

[0076] Step 1: Collect drug sales data, market data, consumer data, economic data, policy data, seasonal data and disease epidemic trend data.

[0077] Combined with the content of step 1:

[0078] By collecting drug sales data, market data, consumer data, economic data, policy data, seasonal data and disease epidemic trend data, companies can gain a more comprehensive understanding of market dynamics and provide relevant data for subsequent calculations.

[0079] Step 2: Calculate the price elasticity coefficient c1, market share loss rate c2 and popularity increase rate f3 based on drug sales data and market data, and further calculate the market impact coefficient QA; calculate the age factor impact rate DY based on consumer data; and further calculate the consumer impact coefficient QB; calculate the gross domestic product impact rate EG and the consumer price index impact rate EC based on drug sales data and economic data; calculate the economic impact coefficient QC based on the gross domestic product impact rate EG and the consumer price index impact rate EC; calculate the policy impact coefficient QD based on policy data; calculate the seasonal impact value QE based on seasonal data t ; Based on drug sales data and disease epidemic trend data, the slope coefficient β1 and intercept β0 are calculated, and the disease epidemic trend impact value QF is further calculated. t .

[0080] Step 201: The method for calculating the price elasticity coefficient c1, the market share loss rate c2 and the popularity improvement rate f3 is:

[0081] The drug sales data at least includes the initial drug price a, the current drug price e2 and the price change A;

[0082] It should be noted that the initial drug price a refers to the price determined when the drug first enters the sales market, the current drug price e2 refers to the selling price of the drug at this time, and the price change A is the difference between the current drug price e2 and the initial drug price a.

[0083] Market data include initial market demand b, demand change B, market share d1, competitor product price e1, initial drug popularity f1 and drug popularity after promotion f2.

[0084] It should be noted that the initial market demand b refers to the total demand of consumers for a certain drug before any major external factors such as policy changes, major technological innovations, etc., and before any special marketing activities are carried out. It reflects the natural market demand level for the drug. By analyzing its own historical sales data of the drug, and excluding the influence of special promotional activities, market emergencies and other factors, the company estimates the drug sales volume in a relatively stable period through trend analysis and data modeling, and uses this as the initial market demand b.

[0085] The demand change B refers to the change in the market demand for drugs relative to the initial market demand b due to various factors. The demand change B is obtained through regular market research.

[0086] Market share d1 refers to the proportion of the company's drug sales to the total sales of similar drugs in the market, reflecting the competitiveness of the company's products in the market competition. It is obtained through market research and industry association data.

[0087] Competitor product price e1 refers to the average sales price of the drug produced by other companies in the same market that compete with the company's drugs. It reflects the competitor's pricing strategy and market positioning and is obtained through competitor announcements and news, market research, and industry reports and analysis.

[0088] Initial drug awareness f1 refers to the degree of awareness of a drug among consumers when it first enters the market. Post-promotion drug awareness f2 refers to the degree of awareness of a drug among consumers after the company has carried out a series of marketing activities, such as advertising, promotional activities, participation in academic conferences, and doctor recommendations. Initial drug awareness f1 and post-promotion drug awareness f2 are measured by consumers' awareness, memory, and impression of the drug.

[0089] The price elasticity coefficient c1 is calculated based on the initial drug price a, price change A, initial market demand b and demand change B. The formula is:

[0090]

[0091] It should be noted that this formula obtains the price elasticity coefficient c1 through the relative changes in price and demand. The price elasticity coefficient c1 is used to measure the sensitivity of drug demand to price changes. When c1 is greater than 1, it indicates that demand is elastic and price changes will lead to an increase in demand. When c1 is less than or equal to 1, it indicates that demand is inelastic and price changes have little effect on demand.

[0092] The market share loss rate c2 is calculated based on the price elasticity coefficient c1, market share d1, competitor product price e1 and current drug price e2, based on the following formula:

[0093]

[0094] It should be noted that this formula is based on the price elasticity theory. First, the ratio of the relative price difference to the competitor's product price e1 is calculated, and then it is multiplied by the price elasticity coefficient c1, which reflects the impact of price changes on demand. Finally, it is multiplied by the market share d1 to obtain the market share loss rate c2.

[0095] The formula for calculating the popularity increase rate f3 based on the initial popularity of the drug f1 and the popularity of the drug after promotion f2 is:

[0096]

[0097] It should be noted that this formula measures the impact of promotional activities on brand awareness by comparing the changes in brand awareness before and after the promotional activities.

[0098] Step 202: The method for calculating the market impact coefficient QA is:

[0099] The market impact coefficient QA is calculated based on the market share loss rate c2 and the popularity increase rate f3, and the formula is:

[0100] QA=(1-c2)×f3;

[0101] It should be noted that this formula takes into account the market share loss rate c2 and the popularity increase rate f3. The lower the market share loss rate c2, the better the market situation and the higher the market impact coefficient QA. The higher the popularity increase rate f3, the better the market situation and the higher the market impact coefficient QA.

[0102] Step 203: The method for calculating the consumer influence coefficient QB is:

[0103] Consumer data includes drug preference scores for different age groups g , average score of drug preference Sales sensitivity Y g , Preference scores of different occupational groups II u , the number of people in different occupational groups - RE u , the total number of people who scored RE, the preference scores of groups with different income levels YS v and the number of people in different income groups u .

[0104] It should be noted that the drug preference scores of different age groups are similar. g The method of obtaining the drug preference score is to design questionnaires for different age groups, including evaluation of the drug's effect, ease of use, side effects, brand impression, etc. The questionnaire scores of all participants are counted, and the average of the questionnaire scores of each age group is calculated as the drug preference score of different age groups. g The different age groups include adolescent group, youth group, middle-aged group and elderly group. The division method is: 10 to 19 years old is the adolescent group, 20 to 39 years old is the youth group, 40 to 59 years old is the middle-aged group, and 60 years old and above is the elderly group. The questionnaire scores of all participants were counted and the total value was calculated as the average score of drug preference.

[0105] Preference scores of different occupational groups u The method of obtaining the preference score of different occupations is to design questionnaires for different occupations, including the evaluation of the effect of the drug, convenience of use, side effects, brand impression, etc. The questionnaire scores of all participants are counted, and the average score of each occupational questionnaire score is calculated as the preference score of different occupational groups. u , different occupational groups include teachers, agricultural workers, freelancers, etc.

[0106] Preference scores of different income groups v The method of obtaining the data is as follows: design questionnaires for different income groups, including evaluation of the drug's effect, ease of use, side effects, brand impression, etc. Count the questionnaire scores of all participants, calculate the average of the scores of each income group, and use it as the preference score of different income groups. v Different income groups include high-income groups, middle-income groups and low-income groups. The classification method is: when the annual income exceeds 500,000, it is classified as a high-income group, when the annual income is between 100,000 and 500,000, it is classified as a middle-income group, and when the annual income is less than 100,000, it is classified as a low-income group. The number of people participating in the survey in each income group is counted to obtain the number of people in different income groups. u .

[0107] Sales sensitivity Y g It indicates the degree of influence of a one-unit change in drug preference on drug sales. It reflects the relationship between consumer preference for drugs and drug sales. Sales sensitivity Y g The method of obtaining is to collect drug sales data and consumer preference data over a period of time, and perform regression analysis on these two sets of data. By establishing a regression model, the relationship between drug preference scores and sales volume is found, thereby determining sales volume sensitivity.

[0108] The total number of people who made the ratings, RE, was obtained by counting all the people who participated in the questionnaire survey.

[0109] Drug preference scores according to different age groups g , average score of drug preference and sales sensitivity Y g The formula for calculating the age factor influence rate DY is:

[0110]

[0111] It should be noted that the operating principle of this formula is: considering the differences in drug preferences among different age groups, by comparing the preference of each age group for this drug with the average drug preference score And multiply it by the sales sensitivity Y of that age group g , and then sum them up to comprehensively evaluate the impact of age factors on drug sales.

[0112] Among them, YE g is the drug preference score of the g-th age group for this drug; g is the serial number corresponding to different age groups, and its value is [1, h]; h is the number of different age groups, and its value is a positive integer; Y is the average drug preference score of the g-th age group for all drugs on the market; g is the sales sensitivity of the g-th age group.

[0113] According to the influence rate of age factor DY, preference scores of different occupational groups YF u , the number of people in different occupational groups - RE u , the total number of people who scored RE, the preference scores of groups with different income levels YS v and the number of people in different income groups u The calculation formula for the consumer impact coefficient QB is:

[0114]

[0115] It should be noted that the operating principle of this formula is: By calculating the proportion of people in different occupational groups to the total population and multiplying it by the preference score of the occupational group, the sum is obtained to obtain the influence rate of consumers' occupation on drug preference. By calculating the proportion of different income groups to the total population and multiplying it by the preference score of the income group, the sum is obtained to get the impact rate of consumer income on drug preference. Finally, the consumer influence coefficient QB is obtained by comprehensively considering the impact rate of consumer age, occupation and income on drug preference. The consumer influence coefficient QB is used to measure the consumer's preference for the drug. The higher the consumer influence coefficient QB, the higher the consumer's preference for the drug, and the better the impact on drug sales.

[0116] Among them, YF u is the preference score of the u-th occupational group for this drug, RE u is the number of people in the u-th occupational group; u is the serial number corresponding to different occupational groups, and its value is [1, x]; x is the number of different occupational groups, and its value is a positive integer; YS v is the preference score of the vth income group for this drug, and its value is [1, r]; SR v is the number of people in the vth income level group; r is the number of groups with different income levels, which is a positive integer;

[0117] Step 204: The method for calculating the economic impact coefficient QC is:

[0118] Economic data include the rate of change of gross domestic product (ΔGDP) and the consumer price index (E CPI .

[0119] It should be noted that the GDP change rate ΔGDP represents the percentage increase of GDP in a certain period relative to the previous period. CPIIt is a macroeconomic indicator that reflects the changes in the price level of consumer goods and services over a certain period of time. The GDP change rate ΔGDP and the consumer price index E CPI Obtained through official economic data publishing agencies such as the National Bureau of Statistics.

[0120] Drug sales data also includes drug sales growth rate ΔDR.

[0121] It should be noted that the drug sales growth rate ΔDR refers to the rate of change of drug sales in a certain period relative to the drug sales in the previous period, which is used to measure the degree of change in drug sales volume in a certain period. This data is obtained through internal sales data statistics of the enterprise.

[0122] The GDP impact rate EG is calculated based on the GDP change rate ΔGDP and the drug sales growth rate ΔDR. The formula is:

[0123]

[0124] It should be noted that this formula measures the sensitivity of drug sales to changes in GDP growth by calculating the ratio of the drug sales growth rate ΔDR to the GDP change rate ΔGDP. When the GDP impact rate EG is greater than 0, it indicates that drug sales are positively correlated with GDP growth, and drug sales will increase as GDP grows. When the GDP impact rate EG is less than 0, it indicates that drug sales are negatively correlated with GDP growth, and drug sales will decrease as GDP grows. When the GDP impact rate EG is equal to 0, it indicates that drug sales are not affected by changes in GDP growth.

[0125] According to the Consumer Price Index CPI , the initial drug price a and the current drug price e2 are used to calculate the consumer price index impact rate EC, based on the formula:

[0126]

[0127] It should be noted that this formula calculates the price of drugs relative to the consumer price index E through the relative price change formula. CPI When the consumer price index impact rate EC is greater than 0, it indicates that the drug price has increased relatively. When the consumer price index impact rate EC is less than 0, it indicates that the drug price has decreased relatively. When the consumer price index impact rate EC is equal to 0, it indicates that the drug price remains unchanged.

[0128] The economic impact coefficient QC is calculated based on the gross domestic product impact rate EG and the consumer price index impact rate EC, and the formula is:

[0129] QC = EG-EC;

[0130] It should be noted that this formula obtains the economic impact coefficient QC by comprehensively considering the gross domestic product impact rate EG and the consumer price index impact rate EC. The higher the gross domestic product impact rate EG, the higher the economic impact coefficient QC, and the better the impact of economic changes on drug sales. The lower the consumer price index impact rate EC, the lower the drug price, the higher the economic impact coefficient QC, and the better the impact of economic changes on drug sales.

[0131] Step 205: The method for calculating the policy impact coefficient QD based on the policy data is:

[0132] Policy data include the change rate of medical insurance coverage population ΔFC, the change rate of medical insurance reimbursement ratio ΔFD and the change rate of drug market access ΔFE.

[0133] It should be noted that the change rate of the medical insurance covered population ΔFC refers to the proportion of the change in the number of people who can enjoy medical insurance reimbursement relative to the number of people in the previous period due to medical insurance policy adjustments and other reasons within a certain period of time. It reflects the impact of medical insurance policies on the potential consumer population of drugs. The data is obtained through medical insurance management agencies.

[0134] The rate of change in the medical insurance reimbursement ratio ΔFD refers to the extent of change in the medical insurance reimbursement ratio for specific drugs over a certain period of time relative to the reimbursement ratio in the previous period. It reflects the impact of medical insurance policies on patients' drug cost burden at the economic level. The data is obtained through medical insurance policy documents or hospital settlement systems.

[0135] The drug market access change rate ΔFE refers to the percentage change in the degree to which a drug enters different markets or obtains different sales licenses during a certain period of time relative to the previous period. It reflects changes in the drug's market sales scope and opportunities. The data is obtained through announcements from drug regulatory authorities or industry reports.

[0136] The policy impact coefficient QD is calculated based on policy data, and the formula is:

[0137] QD=ΔFC×ρ1+ΔFD×ρ2+ΔFE×ρ3;

[0138] It should be noted that the formula obtains the policy impact coefficient QD through a weighted formula. The policy impact coefficient QD is used to measure the impact of policy changes on drug sales. The higher the policy impact coefficient QD, the better the impact of policy changes on drug sales.

[0139] Among them, ρ1 is the weight coefficient of the change rate ΔFC of the medical insurance coverage population, and its value ranges from 0.2 to 0.5, which is determined according to the degree of influence of the change rate ΔFC of the medical insurance coverage population on the policy impact coefficient QD; ρ2 is the weight coefficient of the change rate ΔFD of the medical insurance reimbursement ratio, and its value ranges from 0.3 to 0.5, which is determined according to the degree of influence of the change rate ΔFD of the medical insurance reimbursement ratio on the policy impact coefficient QD; ρ3 is the weight coefficient of the drug market access change rate ΔFE, and its value ranges from 0.2 to 0.6, which is determined according to the degree of influence of the drug market access change rate ΔFE on the policy impact coefficient QD; and ρ1+ρ2+ρ3=1.

[0140] Step 206: Calculate the seasonal impact value QE based on the seasonal data t The method is:

[0141] Seasonal data include drug Fourier coefficients γ n and the Fourier coefficient δ n .

[0142] It should be noted that the Fourier coefficient γ n and the Fourier coefficient δ n The method of obtaining γ is as follows: statistically analyze the historical drug sales data and randomly initialize the values ​​of Fourier coefficients 1 and 2, calculate the seasonal impact value based on the historical drug sales data and the randomly initialized coefficient values, calculate the error between the seasonal impact value and the actual historical drug sales data, and then use the gradient descent method to continuously update the coefficients to gradually reduce the error value until the error reaches a predetermined convergence state, that is, when the error improvement brought by further adjusting the coefficients is very limited, the coefficient at this time is the Fourier coefficient 1γ. n and the Fourier coefficient δ n ; Fourier coefficient -γ n and the Fourier coefficient δ n The acquisition process can be calculated through existing computing tools and belongs to the existing technology. The specific analysis process can be implemented through the Python tools of the existing technology. By clarifying and preprocessing the historical drug sales data, using the Pandas library to load the data, checking the time series characteristics of the data, determining whether there is an obvious periodic pattern, using Fourier transform to extract the periodic component, and adjusting the Fourier coefficients through gradient descent or other optimization algorithms to minimize the prediction error.

[0143] The seasonal cycle n of a drug refers to the regular changes in drug sales over time that are repeated at a certain fixed interval n. The seasonal cycle n is determined through autocorrelation function analysis.

[0144] Calculate the seasonal impact value QE according to the seasonal cycle n t , the formula based on is:

[0145]

[0146] It should be noted that this formula fits the periodic fluctuations in drug sales data through a combination of trigonometric functions, thereby capturing the law of seasonal changes. It is assumed that the seasonal component can be composed of the superposition of sine and cosine functions of different frequencies, among which the combination of sine and cosine functions can effectively simulate various periodic fluctuation patterns. By adjusting the coefficients γ of the sine and cosine functions of different frequencies n and δ n , seasonal fluctuations of different shapes and amplitudes can be fitted.

[0147] Among them, QE t is the seasonal impact value at time t, which is used to characterize the fluctuations in drug sales data that occur repeatedly with seasons or fixed cycles. n is the Fourier coefficient of the nth seasonal cycle, n is the serial number corresponding to different seasonal cycles, and its value is [1, m], and m is the total number of seasonal cycles, and its value is a positive integer. n is the Fourier coefficient of the nth seasonal cycle. t is the seasonal error, which represents the impact of other random factors on the seasonal component besides the seasonal fluctuations that can be explained by the trigonometric function combination, and is determined by residual analysis.

[0148] Step 207: Calculate the disease epidemic trend impact value QF t The method is:

[0149] Drug sales data also includes monthly drug sales. i and monthly sales average

[0150] It should be noted that the monthly sales volume of drugs i It reflects the market demand and sales of the drug in a specific period of time, obtained through sales channel data statistics and market research company data. It refers to the average monthly sales volume of drugs within a certain time frame. It can help us understand the long-term trend and stability of drug sales. It is obtained by collecting the monthly sales volume data of drugs within a certain time frame and then calculating the arithmetic average.

[0151] Disease epidemic trend data include monthly incidence rate k i and the average monthly incidence rate

[0152] It should be noted that the monthly incidence rate k iIt refers to the ratio of the number of new cases of the drug-related disease to the total number of people at risk of the disease in a specific month, reflecting the prevalence and risk of the disease in a specific period of time. It is obtained through the public health monitoring system and the medical records of hospitals, clinics and other medical institutions. Refers to the average monthly incidence rate within a certain time frame. It can help us understand the long-term trend and stability of the disease. It is obtained by collecting monthly incidence data within a certain time frame and then calculating the arithmetic average.

[0153] Based on the monthly sales volume of drugs, the average monthly sales volume Monthly incidence rate k i and the average monthly incidence rate The slope coefficient β1 is calculated based on the formula:

[0154]

[0155] It should be noted that this formula calculates the monthly sales volume j and the average monthly sales volume The deviation and monthly incidence rate k i The average monthly incidence The deviations are multiplied and then divided by the monthly incidence k i The average monthly incidence The square of the sum of the deviations is used to obtain the slope coefficient β1. The slope coefficient β1 is used to measure the incidence rate k in the current month. i The change in monthly sales volume j when one unit is added.

[0156] Among them, j i is the sales volume of the drug in the i-th month; i is the serial number corresponding to different months; is the average sales volume of the drug in the i-th month; k i is the incidence rate of the disease related to the drug in the i-th month; is the average incidence rate of the drug-related disease in the i-th month;

[0157] Based on the average monthly sales Slope coefficient β1 and monthly incidence mean The intercept β0 is calculated based on the formula:

[0158]

[0159] It should be noted that this formula is based on the principle of linear regression and obtains the intercept β0.

[0160] Calculate the disease epidemic trend impact value QF based on the monthly drug sales volume j, slope coefficient β1 and intercept β0 t , the formula based on is:

[0161] QF t =β0+β1×k t ;

[0162] It should be noted that this formula is based on the principle of linear regression. According to the incidence rate at time t, the sales value of the drug affected by the incidence rate at time t is obtained, that is, the disease epidemic trend impact value QF t The incidence rate k at time t t Determined by time series analysis.

[0163] Among them, QF t is the impact value of the disease epidemic trend at time t; k t is the incidence rate at time t.

[0164] Combined with the contents of step 201 to step 207:

[0165] By calculating the market impact coefficient QA, companies can have a more comprehensive understanding of market dynamics and improve the scientific nature of their decisions. By calculating the consumer impact coefficient QB, age factors and consumer preferences can be comprehensively considered to more comprehensively reflect the impact of consumer factors on drug sales. Calculating the economic impact coefficient QC can help companies more comprehensively evaluate the impact of economic factors on drug sales and reduce operating risks brought about by changes in the economic environment. Calculating the policy impact coefficient QD based on policy data enables companies to promptly understand the impact of national policies on the pharmaceutical industry, ensure that the company's business activities comply with policy requirements, and make full use of policy opportunities to enhance the company's competitiveness. Calculate the seasonal impact value QE based on seasonal data t , enterprises can adjust production plans and inventory management according to the seasonal impact value to ensure sufficient product supply during the high-incidence season of diseases. t , enabling companies to understand the impact of disease epidemic trends on drug sales. Helping companies predict changes in market demand in advance and providing reference for their R&D and production decisions.

[0166] Step 3: Based on the market impact coefficient QA, consumer impact coefficient QB, economic impact coefficient QC, policy impact coefficient QD, and seasonal impact value QE t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t ; Based on the drug sales forecast value Z t Adjust the production plan of medicines.

[0167] Step 301: Calculate the drug sales forecast value Z t The method is:

[0168] According to the market impact coefficient QA, consumer impact coefficient QB, economic impact coefficient QC, policy impact coefficient QD, seasonal impact value QE t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t , the formula based on is

[0169] Z t =Z 0t ×(1+QA)×(1+QB)×(1+QC)+QE t +QF t ;

[0170] It should be noted that this formula is based on the basic forecast value and adjusts the forecast value through various influencing coefficients. Basic forecast value Z 0t The basis for calculating the forecast value is the predicted drug sales volume before considering changes in other influencing factors, which is obtained according to the time series model.

[0171] Among them, Z t is the predicted value of drug sales at time t; Z 0t is the basic forecast value considering only drug sales at time t.

[0172] Combined with the content of step 301:

[0173] By comprehensively considering multiple factors such as the market, consumers, economy, policy, season and disease epidemic trends, we can more comprehensively grasp the dynamic changes in the pharmaceutical market, thereby improving the accuracy of drug sales forecasts. t It helps enterprises optimize inventory management. Enterprises can arrange production plans reasonably, avoid overproduction or insufficient supply, and reduce market risks.

[0174] On the other hand, the present invention also discloses a drug market data analysis system, which is used to implement the above-mentioned drug market data analysis method, comprising:

[0175] Data collection module, used to collect drug sales data, market data, consumer data, economic data, policy data, seasonal data and disease epidemic trend data;

[0176] The impact coefficient calculation module is used to calculate the price elasticity coefficient c1 and the popularity enhancement rate f3 based on drug sales data and market data; and further calculate the market impact coefficient QA; calculate the age factor impact rate DY based on consumer data; and further calculate the consumer impact coefficient QB; calculate the gross domestic product impact rate EG and the consumer price index impact rate EC based on drug sales data and economic data; calculate the economic impact coefficient QC based on the gross domestic product impact rate EG and the consumer price index impact rate EC; calculate the policy impact coefficient QD based on policy data; calculate the seasonal impact value QE based on seasonal data t ; Calculate the slope coefficient β1 and intercept β0 based on drug sales data and disease epidemic trend data; and further calculate the disease epidemic trend impact value QF t ;

[0177] The prediction module is used to predict the impact of the market on the QA, the consumer impact on the QB, the economic impact on the QC, the policy impact on the QD, and the seasonal impact on the QE. t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t ; Based on the drug sales forecast value Z t Adjust the production plan of medicines.

[0178] 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 combination with 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.

[0179] 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.

[0180] 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 method for analyzing drug market data, characterized in that: The following steps are involved: Collect drug sales data, market data, consumer data, economic data, policy data, seasonal data and disease epidemic trend data; Based on drug sales data and market data, calculate the price elasticity coefficient c1, market share loss rate c2 and brand awareness increase rate f3, and further calculate the market impact coefficient QA; Calculate the age factor impact rate DY based on consumer data; and further calculate the consumer impact coefficient QB; calculate the gross domestic product impact rate EG and the consumer price index impact rate EC based on drug sales data and economic data; calculate the economic impact coefficient QC based on the gross domestic product impact rate EG and the consumer price index impact rate EC; calculate the policy impact coefficient QD based on policy data; Calculate seasonal impact value QE based on seasonal data t ; Based on drug sales data and disease epidemic trend data, the slope coefficient β1 and intercept β0 are calculated, and the disease epidemic trend impact value QF is further calculated. t ; According to the market impact coefficient QA, consumer impact coefficient QB, economic impact coefficient QC, policy impact coefficient QD, seasonal impact value QE t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t ; Based on the drug sales forecast value Z t Adjust the production plan of medicines.

2. A pharmaceutical market data analysis method according to claim 1, characterized in that: The method for calculating the price elasticity coefficient c1, market share loss rate c2 and popularity increase rate f3 is: The drug sales data at least includes the initial drug price a, the current drug price e2 and the price change A; Market data include initial market demand b, demand change B, market share d1, competitor product price e1, initial drug popularity f1 and drug popularity after promotion f2; The price elasticity coefficient c1 is calculated based on the initial drug price a, price change A, initial market demand b and demand change B. The formula is: The market share loss rate c2 is calculated based on the price elasticity coefficient c1, market share d1, competitor product price e1 and current drug price e2, based on the following formula: The formula for calculating the popularity increase rate f3 based on the initial popularity of the drug f1 and the popularity of the drug after promotion f2 is:

3. A pharmaceutical market data analysis method according to claim 2, characterized in that: The method for calculating the market impact coefficient QA is: The market impact coefficient QA is calculated based on the market share loss rate c2 and the popularity increase rate f3, and the formula is: QA=(1-c2)×f3.

4. A pharmaceutical market data analysis method according to claim 3, characterized in that: The method for calculating the consumer influence coefficient QB is: Consumer data includes drug preference scores for different age groups g , average score of drug preference Sales sensitivity Y g , Preference scores of different occupational groups II u , the number of people in different occupational groups - RE u , the total number of people who scored RE, the preference scores of groups with different income levels YS v and the number of people in different income groups u ; Drug preference scores according to different age groups g , average score of drug preference and sales sensitivity Y g The formula for calculating the age factor influence rate DY is: Among them, YE g is the drug preference score of the g-th age group for this drug; g is the serial number corresponding to different age groups, and its value is [1, h]; h is the number of different age groups, and its value is a positive integer; Y is the average drug preference score of the g-th age group for all drugs on the market; g is the sales sensitivity of the g-th age group; According to the influence rate of age factor DY, preference scores of different occupational groups YF u , the number of people in different occupational groups - RE u , the total number of people who scored RE, the preference scores of groups with different income levels YS v and the number of people in different income groups u The calculation formula for the consumer impact coefficient QB is: Among them, YF u is the preference score of the u-th occupational group for this drug, RE u is the number of people in the u-th occupational group; u is the serial number corresponding to different occupational groups, and its value is [1, x]; x is the number of different occupational groups, and its value is a positive integer; YS v is the preference score of the vth income group for this drug, and its value is [1, r]; SR v is the number of people in the vth income level group; r is the number of groups with different income levels, which is a positive integer.

5. A pharmaceutical market data analysis method according to claim 4, characterized in that: The method for calculating the economic impact coefficient QC is: Economic data include the rate of change of gross domestic product (ΔGDP) and the consumer price index (E CPI ; Drug sales data also include drug sales growth rate ΔDR; The GDP impact rate EG is calculated based on the GDP change rate ΔGDP and the drug sales growth rate ΔDR. The formula is: According to the Consumer Price Index CPI , the initial drug price a and the current drug price e2 are used to calculate the consumer price index impact rate EC, based on the formula: The economic impact coefficient QC is calculated based on the gross domestic product impact rate EG and the consumer price index impact rate EC, and the formula is: QC=EG-EC.

6. A pharmaceutical market data analysis method according to claim 5, characterized in that: The method for calculating the policy impact coefficient QD based on policy data is: Policy data include the change rate of medical insurance coverage population ΔFC, the change rate of medical insurance reimbursement ratio ΔFD, and the change rate of drug market access ΔFE; The policy impact coefficient QD is calculated based on policy data, and the formula is: QD=ΔFC×ρ1+ΔFD×ρ2+ΔFE×ρ3; Among them, ρ1 is the weight coefficient of the change rate of medical insurance coverage population ΔFC, which takes a value of 0.2~0.5; ρ2 is the weight coefficient of the change rate of medical insurance reimbursement ratio ΔFD, which takes a value of 0.3~0.5; ρ3 is the weight coefficient of the change rate of drug market access ΔFE, which takes a value of 0.2~0.6; and ρ1+ρ2+ρ3=1.

7. A pharmaceutical market data analysis method according to claim 6, characterized in that: Calculate seasonal impact value QE based on seasonal data t The method is: Seasonal data include drug Fourier coefficients γ n and the Fourier coefficient δ n ; Calculate the seasonal impact value QE according to the seasonal cycle n t , the formula based on is: Among them, QE t is the seasonal impact value at time t; γ n is the Fourier coefficient of the nth seasonal cycle; n is the serial number corresponding to different seasonal cycles, and its value is [1, m]; m is the total number of seasonal cycles, and its value is a positive integer; δ n is the Fourier coefficient of the nth seasonal cycle; ε t is the seasonal error.

8. A pharmaceutical market data analysis method according to claim 7, characterized in that: Calculate the impact value QF of disease epidemic trend t The method is: Drug sales data also includes monthly drug sales. i and monthly sales average Disease epidemic trend data include monthly incidence rate k i and the average monthly incidence rate Based on the monthly sales volume of drugs, the average monthly sales volume Monthly incidence rate k i and the average monthly incidence rate The slope coefficient β1 is calculated based on the formula: Among them, j i is the sales volume of the i-th month; i is the serial number corresponding to different months; is the average sales volume of the i-th month; k i is the incidence rate of the disease related to the drug in the i-th month; is the average incidence rate of the drug-related disease in the i-th month; Based on the average monthly sales Slope coefficient β1 and monthly incidence mean The intercept β0 is calculated based on the formula: Based on the monthly sales volume of drugs j and monthly incidence rate k i , slope coefficient β1 and intercept β0 to calculate the disease epidemic trend impact value QF t , the formula based on is: QF t =β0+β1×k t ; Among them, QF t is the impact value of the disease epidemic trend at time t; k t is the incidence rate at time t.

9. A pharmaceutical market data analysis method according to claim 8, characterized in that: Calculate the drug sales forecast value Z t The method is: According to the market impact coefficient QA, consumer impact coefficient QB, economic impact coefficient QC, policy impact coefficient QD, seasonal impact value QE t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t , the formula based on is Z t =Z 0t ×(1+QA)×(1+QB)×(1+QC)+QE t +QF t ; Among them, Z t is the predicted value of drug sales at time t; Z 0t is the basic forecast value considering only drug sales at time t.

10. A drug market data analysis system, characterized in that: include: Data collection module, used to collect drug sales data, market data, consumer data, economic data, policy data, seasonal data and disease epidemic trend data; The impact coefficient calculation module is used to calculate the price elasticity coefficient c1 and the popularity increase rate f3 based on the drug sales data and market data; and further calculate the market impact coefficient QA; Calculate the age factor impact rate DY based on consumer data; and further calculate the consumer impact coefficient QB; calculate the gross domestic product impact rate EG and the consumer price index impact rate EC based on drug sales data and economic data; calculate the economic impact coefficient QC based on the gross domestic product impact rate EG and the consumer price index impact rate EC; calculate the policy impact coefficient QD based on policy data; Calculate seasonal impact value QE based on seasonal data t ; Calculate the slope coefficient β1 and intercept β0 based on drug sales data and disease epidemic trend data; and further calculate the disease epidemic trend impact value QF t ; The prediction module is used to predict the impact of the market on the QA, the consumer impact on the QB, the economic impact on the QC, the policy impact on the QD, and the seasonal impact on the QE. t and the disease epidemic trend impact value QF t Calculate the drug sales forecast value Z t ; Based on the drug sales forecast value Z t Adjust the production plan of medicines.

Images