CN115083560A - Medicine sales data processing method and device and electronic equipment - Google Patents
Medicine sales data processing method and device and electronic equipment Download PDFInfo
- Publication number
- CN115083560A CN115083560A CN202210613628.3A CN202210613628A CN115083560A CN 115083560 A CN115083560 A CN 115083560A CN 202210613628 A CN202210613628 A CN 202210613628A CN 115083560 A CN115083560 A CN 115083560A
- Authority
- CN
- China
- Prior art keywords
- hospital
- sales data
- sample
- target
- drug
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000003814 drug Substances 0.000 title claims abstract description 327
- 229940079593 drug Drugs 0.000 title claims abstract description 217
- 238000003672 processing method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 49
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 29
- 238000004458 analytical method Methods 0.000 claims abstract description 18
- 238000010219 correlation analysis Methods 0.000 claims description 20
- 230000002159 abnormal effect Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000010586 diagram Methods 0.000 description 8
- 239000000047 product Substances 0.000 description 8
- 238000003860 storage Methods 0.000 description 7
- 230000002860 competitive effect Effects 0.000 description 6
- 230000035699 permeability Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 101100356682 Caenorhabditis elegans rho-1 gene Proteins 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001225 therapeutic effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 239000007795 chemical reaction product Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 239000000955 prescription drug Substances 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 229940126673 western medicines Drugs 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H20/00—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H20/10—ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance relating to drugs or medications, e.g. for ensuring correct administration to patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0202—Market predictions or forecasting for commercial activities
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Medicinal Chemistry (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a medicine sales data processing method, a device and electronic equipment, wherein the method comprises the following steps: determining a target drug and a target hospital; under the condition that the target hospital is a non-sample hospital, inputting first hospital information of the non-sample hospital into a drug sales data prediction model to obtain predicted sales data of the target drug in the non-sample hospital, which is output by the drug sales data prediction model; the drug sales data prediction model is obtained by training based on first hospital information of a sample hospital and sample sales data of the target drug in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, department information and city information. The medicine sales data processing method, the medicine sales data processing device and the electronic equipment achieve objective, accurate and complete analysis and processing of the hospital sales data.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a medicine sales data processing method and device and electronic equipment.
Background
The hospital is one of the main sales channels of prescription drugs, and the sales data investigation at the hospital end is performed in advance in consideration of the huge cost investment required by drug research and development, so that the hospital is very important for ensuring the normal operation of a drug supply system and the sustainable development of pharmaceutical enterprises.
At present, a pharmaceutical enterprise can obtain the sales data of medicines of the enterprise at a hospital end, and can only obtain the sales data of competitive products at a part of hospitals through a public data source, and cannot obtain the sales conditions of the competitive products from the whole hospital end level.
Disclosure of Invention
The invention provides a medicine sales data processing method and device and electronic equipment, which are used for solving the defect that the sales condition of a competitive product cannot be acquired from the whole hospital end level when the sales data of a hospital end is investigated in the prior art.
The invention provides a medicine sales data processing method, which comprises the following steps:
determining a target medicine and a target hospital;
under the condition that the target hospital is a non-sample hospital, inputting first hospital information of the non-sample hospital into a drug sales data prediction model to obtain predicted sales data of the target drug in the non-sample hospital, which is output by the drug sales data prediction model;
the drug sales data prediction model is obtained by training based on first hospital information of a sample hospital and sample sales data of the target drug in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, department information and city information.
According to the medicine sales data processing method provided by the invention, the medicine sales data prediction model is obtained by training based on the following steps:
determining an initial model;
inputting second hospital information of the sample hospital into an initial model to obtain sample predicted sales data of the target drug in the sample hospital, wherein the sample predicted sales data is output by the initial model, and the second hospital information comprises the first hospital information;
and performing parameter iteration on the initial model based on the sample predicted sales data and the sample sales data of the target medicine in the sample hospital to obtain the medicine sales data prediction model.
According to the drug sales data processing method provided by the present invention, the inputting of the second hospital information of the sample hospital into the initial model to obtain the sample predicted sales data of the target drug in the sample hospital output by the initial model further comprises:
determining importance analysis results of parameters in the second hospital information on sales data prediction based on correlation analysis results between at least two sample predicted sales data and the sample sales data respectively;
and determining the parameters contained in the first hospital information from the parameters of the second hospital information based on the importance analysis result of the parameters in the second hospital information on sales data prediction.
According to the drug sales data processing method provided by the invention, at least two initial models exist;
the parameter iteration is carried out on the initial model based on the sample predicted sales data and the sample sales data of the target medicine in the sample hospital to obtain the medicine sales data prediction model, and the method comprises the following steps:
performing parameter iteration on the at least two initial models based on correlation analysis results between the sample predicted sales data and the sample sales data respectively output by the at least two initial models to obtain at least two regression models;
determining the drug sales data prediction model based on the at least two regression models.
According to the drug sales data processing method provided by the present invention, the determining the drug sales data prediction model based on the at least two regression models includes:
and determining the medicine sales data prediction model based on the at least two regression models and the correlation analysis result of the regression models in the parameter iteration process.
According to the method for processing drug sales data provided by the present invention, the target hospital includes the sample hospital and the non-sample hospital, and the method further includes the following steps:
and determining the sales strategy of the target medicine in each target hospital based on the predicted sales data and the sample sales data.
According to the drug sales data processing method provided by the invention, the determining the sales strategies of the target drugs in the target hospitals based on the predicted sales data and the sample sales data comprises the following steps:
determining at least one of a market sales level for the target drugs for the target hospitals, a drug sales level for the target enterprise drugs for the target hospitals, and a sales share level for the target enterprise drugs for the target hospitals based on the forecasted sales data and the sample sales data; the target enterprise drug is determined based on an enterprise identity of the target drug;
determining a sales strategy of the target drugs at each target hospital based on at least one of a marketing level, a drug sales level, and a sales share level of the target hospital.
According to the method for processing the drug sales data provided by the present invention, the obtaining of the predicted sales data of the target drug in the non-sample hospital output by the drug sales data prediction model further includes:
in a case where the predicted sales data indicates abnormal data, the predicted sales data is replaced based on similar predicted sales data belonging to a same class of hospitals as the non-sample hospital, the class of hospitals being determined based on hospital information.
The present invention also provides a medicine sales data processing apparatus, comprising:
a medicine and hospital determination unit for determining a target medicine and a target hospital;
the system comprises a sales data determining unit, a sales data predicting unit and a data processing unit, wherein the sales data determining unit is used for inputting first hospital information of a non-sample hospital into a medicine sales data predicting model to obtain predicted sales data of a target medicine in the non-sample hospital, and the predicted sales data is output by the medicine sales data predicting model;
the medicine sales data prediction model is obtained by training based on first hospital information of a sample hospital and sample sales data of the target medicine in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, hospital department information and hospital city information.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor executes the program to realize the drug sales data processing method.
The present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method of processing drug sales data as in any one of the above.
The invention also provides a computer program product comprising a computer program which, when executed by a processor, implements a method of processing drug marketing data as described in any of the above.
According to the medicine sales data processing method, the medicine sales data processing device and the electronic equipment, under the condition that a non-sample hospital cannot obtain the sales data of medicines in the hospital through a public channel, the first hospital information and the sample sales data of the sample hospital and a medicine sales data prediction model are adopted to effectively predict the sales data of target medicines in the non-sample hospital, so that the sales data of the target medicines in the target hospital can be obtained, and objective, accurate and complete analysis and processing of the sales data of a hospital end are realized.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for processing drug sales data according to the present invention;
FIG. 2 is a schematic flow chart diagram of a drug sales data prediction model training method provided by the present invention;
FIG. 3 is a schematic diagram of a drug sales data processing apparatus provided by the present invention;
fig. 4 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is obvious that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a drug sales data processing method provided by the present invention, and as shown in fig. 1, the method includes:
Specifically, the target drug is a drug that needs to be analyzed and processed for sales data, and for a pharmaceutical enterprise, the target drug may be a competitive product of the drug of the enterprise. The target drug may be determined based on a dimension selected by the user, where the dimension may be an ATC (automatic Therapeutic chemical) classification dimension, and the target drug thus determined is a collection of drugs of the same ATC category; it may also be a drug generic name dimension (i.e., the target drug is a set of drugs of the same generic name); it may also be the component name dimension of the drug (i.e., the target drug is a set of drugs with the same component name); but also the dimension of the indication (i.e. the target drugs are a set of drugs of the same therapeutic suitability). In addition, enterprise dimensions, city dimensions, specification dimensions, date dimensions and the like can be further selected; of course, any combination of the above dimensions may be used, and the embodiment of the present invention is not limited to this.
The target hospital is the hospital where the target drug may be sold, i.e. the hospital where the target drug may be on the market. The target hospital may be any hospital, or may be a set of hospitals of the same category selected by the user, such as the same hospital level, the same hospital special department, and the like, which is not specifically limited in this embodiment of the present invention.
Further, hospital information of the target hospital can be obtained, where the hospital information includes, but is not limited to, the name of the hospital, the province/city where the hospital is located, the hospital level (e.g., second level, third level), the hospital level (e.g., first level, second level, etc.), the professional nature of the hospital (e.g., general, special), the regional classification (e.g., provincial hospital, county level hospital), the industrial nature (e.g., general hospital, military and police hospital), the special department of the hospital, the total number of doctors in the hospital, the number of doctors in each department of the hospital, the number of beds in each department of the hospital, etc.
the medicine sales data prediction model is obtained by training on the basis of first hospital information of the sample hospital and sample sales data of the target medicine in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, department information and city information.
Specifically, considering that a pharmaceutical enterprise can only obtain sales data of competitive products in a part of hospitals through a public data source in addition to obtaining sales data of medicines of the enterprise at a hospital side, a sample hospital here refers to a hospital that can obtain medicine sales data through a public channel, and a non-sample hospital refers to a hospital that cannot obtain medicine sales data through a public channel.
And (3) predicting the sales data of the target medicine in the non-sample hospital according to the condition that the target hospital is the non-sample hospital, inputting the first hospital information of the non-sample hospital into the medicine sales data prediction model, and obtaining the predicted sales data of the target medicine in the non-sample hospital output by the medicine sales data prediction model.
The first hospital information here may select hospital scale information related to the drug sales data from the hospital information, and the hospital scale information may specifically include one or more of the following parameters: hospital grade, specialty department, total number of beds in hospital, total number of doctors in hospital, drug sales income in hospital, western drug sales income in hospital, number of outpatients/inpatients, etc.
The first hospital information may further include department information corresponding to the target drug, and the department information may specifically include one or more of the following parameters: total number of department beds, total number of department doctors, and total number of department patients.
The first hospital information may further include information of a city where the hospital is located, and the information of the city where the hospital is located may specifically include one or more of the following parameters: total urban population, number of urban households, Gross Domestic Product (GDP) and natural population growth rate.
Before step 120 is performed, the initial model may be trained to obtain a drug sales data prediction model based on the first hospital information of the sample hospital and the sample sales data of the target drug at the sample hospital. In the training process of the initial model, the mapping relation between the first hospital information of the sample hospital and the sample sales data of the sample hospital can be learned, so that the trained medicine sales data prediction model can objectively and accurately predict the sales data of the target medicine in the non-sample hospital.
Here, the sales data may be sales of the target medicine or sales volume.
According to the method provided by the embodiment of the invention, under the condition that the non-sample hospital can not obtain the sales data of the medicines in the hospital through a public channel, the first hospital information and the sample sales data of the sample hospital and the medicine sales data prediction model are adopted to effectively predict the sales data of the target medicines in the non-sample hospital, so that the sales data of the target medicines in the target hospital can be obtained, and objective, accurate and complete analysis and processing of the sales data at the hospital end are realized.
Fig. 2 is a schematic flow chart of a drug sales data prediction model training method provided by the present invention, and as shown in fig. 2, the drug sales data prediction model is trained based on the following steps:
and step 230, performing parameter iteration on the initial model based on the sample predicted sales data and the sample sales data of the target medicine in the sample hospital to obtain a medicine sales data prediction model. In particular, the initial model here may be a tree model, considering that the tree model has a good interpretability for the input and output of the model compared to a neural network model. Further, considering that the sales data prediction problem belongs to a regression task, the initial model may select a pre-trained regression tree model, such as randomfort model, LightGBM model or XGBoost model, that performs better in handling the regression problem.
It should be noted that the number of the initial models may be one regression tree model, or may be more than two regression tree models, which is not specifically limited in the embodiment of the present invention.
After the initial model is determined, the second hospital information of the sample hospital can be input into the initial model, and sample predicted sales data of the target drug in the sample hospital, which is output by the initial model, is obtained.
The second hospital information here includes the first hospital information, that is, the second hospital information includes more parameters than the first hospital information. The second hospital information may be understood as initial parameters of the initial model, and the first hospital information may be understood as final parameters of the drug sales data prediction model obtained through training. For example, in the training process, it is found that part of parameters in the second hospital information has very little influence on the prediction result of the sales data, that is, in order to reduce the parameter amount of the model, the part of parameters is removed, so as to obtain the parameters included in the first hospital information.
After the sample predicted sales data of the target medicine output by the initial model in the sample hospital is obtained, the sample predicted sales data and the sample sales data can be subjected to statistical analysis, and a statistical analysis result between the sample predicted sales data and the sample sales data is obtained. For example, a correlation analysis method may be used to analyze the correlation between the sample predicted sales data and the sample sales data, and further a spearman (spearman) correlation analysis may be used to obtain a spearman correlation coefficient; the difference between the sample predicted sales data and the sample sales data may also be counted by using a difference method or a ratio method, which is not specifically limited in the embodiment of the present invention.
Then, parameter iteration is carried out on the initial model based on the obtained correlation or difference statistical analysis result, and the initial model can learn the importance of each parameter of the input first hospital information relative to the output result in the training process, so that each parameter of the first hospital information is screened to obtain second hospital information; meanwhile, the difference or the correlation between the output sample predicted sales data and the real sample sales data can be learned, so that parameter iteration is performed on the initial model to obtain a drug sales data prediction model.
It is understood that the thus obtained drug sales data prediction model includes not only various input parameters closely related to drug sales data of the target hospital, i.e., parameters contained in the second hospital information; the drug sales data prediction model may also characterize a mapping between input parameters and drug sales data.
According to the method provided by the embodiment of the invention, parameter iteration is carried out on the initial model based on the predicted sample sales data and the sample sales data output by the initial model by inputting the second hospital information of the sample hospital, so that the trained medicine sales prediction model can objectively and accurately predict the sales data of the target medicine in the non-sample hospital.
Based on any of the above embodiments, step 220 further includes:
determining the importance analysis result of each parameter in the second hospital information on the sales data prediction based on the correlation analysis result between the at least two sample prediction sales data and the sample sales data respectively;
the parameters included in the first hospital information are determined from the parameters of the second hospital information based on the result of the importance analysis of the parameters of the second hospital information on the sales data prediction.
Specifically, considering that there are many factors affecting the drug sales data, in order to reduce the parameter amount of the model, a parameter with a higher importance degree in the sales data prediction may be further selected, that is, an input parameter of the initial model, that is, the second hospital information, is screened in the model training process.
In the model training process, the importance analysis result of each parameter in the second hospital information on the sales data prediction can be determined based on the correlation analysis result between at least two sample prediction sales data and the sample sales data. It is to be understood that the at least two sample predictive sales data, i.e., the initial model, herein are based on different input parameters in the second hospital information, resulting in at least two sample predictive sales data.
Then, according to the importance analysis result of each parameter in the second hospital information on the sales data prediction, the parameter included in the first hospital information is determined from each parameter in the second hospital information, and the parameter included in the obtained first hospital information is a parameter with a higher importance degree in the sales data prediction.
According to the method provided by the embodiment of the invention, the parameters in the second hospital information are further screened according to the importance analysis result of the parameters in the second hospital information on the sales data prediction, so that the parameters contained in the first hospital information are obtained, the parameter quantity is further reduced, and the model prediction efficiency is improved.
Based on any of the above embodiments, there are at least two initial models;
accordingly, step 230 includes:
231, performing parameter iteration on the at least two initial models based on correlation analysis results between the at least two sample predicted sales data output by the at least two initial models and the sample sales data respectively to obtain at least two regression models;
step 232, determining a drug sales data prediction model based on the at least two regression models.
Specifically, in order to achieve more accurate drug sales data prediction, the initial models may be two or more tree models, i.e., at least two initial models may be selected to participate in training at the same time.
Understandably, inputting second hospital information of the sample hospital into the initial model 1 to obtain sample predicted sales data 1 output by the initial model 1; inputting second hospital information of the sample hospital into the initial model 2 to obtain sample predicted sales data 2 output by the initial model 2; and in the same way, obtaining at least two sample predicted sales data output by at least two initial models.
And then, carrying out correlation analysis between each sample predicted sales data and each sample sales data to obtain at least two correlation analysis results. And aiming at each initial model, performing parameter iteration on at least two initial models according to the correlation analysis result corresponding to each initial model to obtain at least two regression models.
On the basis, a medicine sales data prediction model can be determined based on the obtained at least two regression models. For example, at least two regression models may be weighted and fused to obtain a drug sales data prediction model.
According to the method provided by the embodiment of the invention, the at least two initial models are trained simultaneously, and the medicine sales data prediction model is determined based on the at least two regression models obtained through training, so that the accuracy of medicine sales data prediction is further improved by the obtained medicine sales data prediction model.
Based on any of the above embodiments, step 232 specifically includes:
and determining a medicine sales data prediction model based on the at least two regression models and the correlation analysis result of the regression models in the parameter iteration process.
Specifically, the initial model may be two or more tree models, a corresponding number of regression models may be obtained in the training process, and the correlation analysis result of the regression models in the parameter iteration process may be specifically a correlation coefficient. Furthermore, the weights of the regression models can be determined based on the correlation analysis result, and the regression models are weighted based on the weights of the regression models to obtain the drug sales data prediction model.
In one embodiment, the number of the initial models is three, and the initial models are a RandomForest model M1, a LightGBM model M2 and an XGBoost model M3, and the optimal regression models of the three models are obtained by training respectively: m1b, M2b and M3b, and obtaining the spearman correlation coefficients corresponding to the three regression models as rho 1, rho 2 and rho 3 respectively. The drug sales data prediction model may be determined by the results of the weighted votes from M1b, M2b, M3b at ρ 1, ρ 2, ρ 3. That is, the drug sales data prediction model may be expressed in the form:
M＝(M1b*ρ1+M2b*ρ2+M3b*ρ3)/(ρ1+ρ2+ρ3)
based on any of the above embodiments, the target hospital includes a sample hospital and a non-sample hospital, and after step 120, the method further includes:
and step 130, determining the sales strategy of the target medicine in each target hospital based on the predicted sales data and the sample sales data.
Specifically, considering that a pharmaceutical enterprise formulates a sales strategy for a hospital end at present, it is usually necessary to manually calculate the increase rate/decrease rate and share change of the sales volume of a drug in each hospital, and the increase rate/decrease rate and the share change are simply compared with the competitive products, so that the obtained analysis result cannot accurately represent the actual sales condition, and the formulated drug sales strategy is not perfect.
The sales policy here refers to a plan of dealing with or a development policy that is made by a pharmaceutical enterprise for how a target drug is sold in each target hospital as a segment sales market. For example, for target hospital 1, maintenance is maintained; aiming at the target hospital 2, strengthening sales support; continuous monitoring, etc. for the target hospital 3.
It is understood that the target hospitals include sample hospitals and non-sample hospitals, and the sales data of the target drugs at the whole hospital side is the sum of the sample sales data of the target drugs at the sample hospitals and the predicted sales data at the non-sample hospitals. The sample sales data or the predicted sales data may be used as sales data for each target hospital.
And on the basis of obtaining the sales data of the target medicines in each target hospital and the sales data of the target medicines at the whole hospital end, the sales data can be further analyzed and processed, and the sales strategies of the target medicines in each target hospital are determined. For example, the target hospitals can be classified according to the sales data, and corresponding sales strategies can be formulated according to the levels corresponding to the target hospitals.
The method provided by the embodiment of the invention can better guide the medicine enterprises to make timely and accurate sales strategies aiming at each target hospital based on the support of sales data, thereby avoiding subjectivity.
Based on any of the above embodiments, step 130 specifically includes:
determining at least one of a market sales level of each target hospital corresponding to the target drug, a drug sales level of each target hospital corresponding to the target enterprise drug, and a sales share level of each target hospital corresponding to the target enterprise drug based on the predicted sales data and the sample sales data; determining the target enterprise medicine based on the enterprise identification of the target medicine;
and determining the sales strategy of the target medicine in each target hospital based on at least one of the market sales level, the medicine sales level and the sales share level of each target hospital.
Specifically, when a sales strategy of the target drug at each target hospital is established, at least one of the following three aspects can be considered:
the market sales level of each target hospital reflects a hierarchical representation of the sales data of each target hospital for the target drugs, the drug sales level reflects a hierarchical representation of the sales data of each target hospital for each target enterprise drug, and the sales share level reflects a hierarchical representation of the sales shares of each target hospital for each target enterprise drug.
It can be understood that the target enterprise drugs, that is, the target drugs of each target enterprise, may be determined based on the enterprise identifiers of the target drugs, for example, the target drugs may be classified into target enterprise drug a, target enterprise drug B, and target enterprise drug C by screening according to the enterprise identifiers, so as to obtain the sales data of each target enterprise drug in each target hospital.
In one embodiment, the marketing level calculation method for each target hospital is as follows:
acquiring the total sales amount/total amount of target medicines in each hospital, performing reverse arrangement on each target hospital based on the total sales amount/total amount of the target medicines (namely arranging the total sales amount/total amount from high to low), calculating the accumulated ratio of the total sales amount/total amount of each hospital, and performing market sales level division on the hospitals based on the accumulated ratio;
for example, 10 marketing levels may be preset, which are D0-D9 in the order from high to low, the hospital marketing level with the occupation ratio of the top 10% is D0, the hospital marketing level with the occupation ratio of the top 10% -20% is D1, and the hospital marketing level with the occupation ratio of the top 90% -100% is D9.
The method for calculating the drug sales level of each target hospital is as follows:
acquiring the total sales amount/total amount of target medicines of a target enterprise in each hospital, arranging the hospitals in a reverse order based on the total sales amount/total amount of the target medicines (namely arranging the total sales amount/total amount from high to low), calculating the cumulative ratio of the total sales amount/total amount of each hospital, and dividing the sales data of the target medicines of the target enterprise in each hospital according to levels (representing the contribution degree of the hospitals to the target medicines of the target enterprise) based on the cumulative ratio;
for example, 10 marketing levels may be preset, which are P0-P9 in the order from top to bottom, the hospital medicine sales level with the percentage of the first 10% is P0, the hospital medicine sales level with the percentage of the first 10% -20% is P1, and the hospital medicine sales level with the percentage of the first 90% -100% is P9. In addition, PX represents that the target enterprise does not have a sale of the target drug at the hospital.
The method for calculating the sales share level of each target hospital is as follows:
acquiring the sales share of a client in the whole hospital end market, wherein the sales share is the own sales data of a target medicine user/the sales data of the target medicine in the hospital;
the hospital is graded by the sales share of the selected drug, the permeability of the reaction product in the hospital is based on the sales habit, and 1.5 times of the sales share is taken as the target market permeability. If the sales share is larger than or equal to the target market penetration rate, the sales share is represented by R10;
the target market permeability is divided into 10 equal parts from zero, and the equal parts from high to low are respectively represented by R9-R0, R9 is slightly lower than the target permeability, and R0 is far lower than the target permeability; RX denotes permeability of 0.
On the basis of obtaining the market sales level, the medicine sales level and the sales share level of each target hospital, the sales strategy of the target medicine in each target hospital can be determined by only considering any one of the market sales level, the medicine sales level and the sales share level, or by comprehensively considering the three indexes.
Based on any embodiment, a hospital strategy analysis matrix graph can be further constructed according to the market sales level and the medicine sales level, namely based on the D/P value relation; or a hospital performance analysis matrix chart is constructed according to the market sales level and the sales share level, namely based on the D/R value relation, and enterprises can be objectively, comprehensively and accurately guided to make a timely and accurate market strategy based on the matrix chart, so that higher profits can be obtained for the enterprises.
Based on any of the above embodiments, the obtaining, in step 120, the predicted sales data of the target drug in the non-sample hospital output by the drug sales data prediction model further includes:
in the case where the predicted sales data indicates abnormal data, the predicted sales data is replaced based on the same type of predicted sales data belonging to the same type of hospitals as the non-sample hospitals, the type of the hospitals being determined based on the hospital information.
Specifically, in order to further ensure the accuracy of the drug sales data prediction, whether the predicted sales data of the target drug in the non-sample hospital, which is output by the drug sales prediction model, is abnormal data may be further checked. For abnormal data, the predicted sales data can be replaced based on similar predicted sales data belonging to the same class of hospitals as non-sample hospitals.
The anomaly data herein may include the following situations:
(1) the predicted sales data for non-sample hospitals were negative.
(2) The predicted sales data of the non-sample hospital has an abnormal relationship with the sales income of the medicines in the non-sample hospital, or with the sales income of the western medicines, or with the number of outpatients/inpatients.
According to the predicted sales data of the non-sample hospital and the drug sales income, the two groups of data are used as scatter diagrams, so that abnormal values are obtained;
according to the predicted sales data of the non-sample hospital and the western medicine sales income, two groups of data are used as scatter diagrams, so that abnormal values are obtained;
according to the predicted sales data of the non-sample hospital and the number of outpatients/inpatients, two groups of data are used for making a scatter diagram so as to obtain abnormal values; for example, the scatter plot shows that hospital a has many outpatients associated with indications of the target drug, but has a small sales of the target drug, and the prediction data can be judged as abnormal data.
(3) Sales data of medicines sold by customers in non-sample hospitals are obtained in advance, and the predicted sales data of the non-sample hospitals are smaller than the sales data of the medicines sold by the customers in the non-sample hospitals (namely, the whole data is smaller than partial data).
For the above two abnormal data situations (1) or (2), that is, the predicted sales data is a negative value, or the sales data and the hospital data have an abnormal relationship, the average value of the similar predicted sales data of the same kind of hospitals can be used for replacement.
The hospital of the same kind is determined based on hospital information, and can be province/city of the same hospital, level of the same hospital, special department of the same hospital and total number of beds of the same hospital.
For the above abnormal data situation (3), i.e. the situation that the predicted sales is smaller than the actual sales of the customer, the predicted sales can be replaced by the actual sales of the customer.
According to the method provided by the embodiment of the invention, the predicted sales data obtained by prediction is subjected to abnormal data replacement, so that the accuracy of medicine sales data prediction is further improved.
Based on any one of the embodiments, a method for processing drug sales data is provided, including:
and S1, determining the target medicine and the target hospital.
In addition, sample data of the target drug in the sample hospital within a preset year is acquired. Preferably, the predetermined year is sales data of two years of history, in order to reduce overfitting in subsequent model training.
The acquired sales data of the target medicine in the sample hospital are cleaned and deduplicated, and can be stored according to the common name, production enterprises and indications of the target medicine. Sales data for a target drug at a sample hospital may be presented in the form shown in table 1:
TABLE 1
S2, when the target hospital is a non-sample hospital, inputting first hospital information of the non-sample hospital into a drug sales data prediction model to obtain predicted sales data of the target drug in the non-sample hospital, which is output by the drug sales data prediction model;
the medicine sales data prediction model is obtained by training based on first hospital information of a sample hospital and sample sales data of the target medicine in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, department information and city information. The medicine sales data prediction model is obtained by training based on the following steps:
determining an initial model;
inputting second hospital information of the sample hospital into an initial model to obtain sample predicted sales data of the target drug in the sample hospital, wherein the sample predicted sales data is output by the initial model, and the second hospital information comprises the first hospital information;
and performing parameter iteration on the initial model based on the sample predicted sales data and the sample sales data of the target medicine in the sample hospital to obtain the medicine sales data prediction model.
And S3, in the case that the predicted sales data indicate abnormal data, replacing the predicted sales data based on the same type of predicted sales data belonging to the same type of hospitals as the non-sample hospitals, the type of hospitals being determined based on hospital information.
S4, determining at least one of a market sales level of the target medicines corresponding to the target hospitals, a medicine sales level of the target medicines corresponding to the target hospitals and a sales share level of the target medicines corresponding to the target enterprises based on the predicted sales data and the sample sales data; the target enterprise drug is determined based on an enterprise identity of the target drug;
determining a sales strategy of the target drugs at each target hospital based on at least one of a marketing level, a drug sales level, and a sales share level of the target hospital.
The following describes the drug sales data processing apparatus provided by the present invention, and the drug sales data processing apparatus described below and the drug sales data processing method described above may be referred to in correspondence with each other.
Based on any of the above embodiments, fig. 3 is a schematic structural diagram of a drug sales data processing apparatus provided by the present invention, and as shown in fig. 3, the apparatus includes:
a medicine and hospital determination unit 310 for determining a target medicine and a target hospital;
a sales data determining unit 320, configured to, if the target hospital is a non-sample hospital, input first hospital information of the non-sample hospital into a drug sales data prediction model, and obtain predicted sales data of the target drug in the non-sample hospital, which is output by the drug sales data prediction model;
the medicine sales data prediction model is obtained by training based on first hospital information of a sample hospital and sample sales data of the target medicine in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, hospital department information and hospital city information.
According to the medicine sales data processing device provided by the embodiment of the invention, under the condition that a non-sample hospital can not obtain the sales data of medicines in the hospital through a public channel, the first hospital information and the sample sales data of the sample hospital and a medicine sales data prediction model are adopted to effectively predict the sales data of target medicines in the non-sample hospital, so that the sales data of the target medicines in the target hospital can be obtained, and objective, accurate and complete analysis and processing of the sales data at the hospital end are realized.
Based on any of the above embodiments, the drug sales data processing apparatus further comprises a model training unit configured to:
determining an initial model;
inputting second hospital information of the sample hospital into an initial model to obtain sample predicted sales data of the target drug in the sample hospital, wherein the sample predicted sales data is output by the initial model, and the second hospital information comprises the first hospital information;
and performing parameter iteration on the initial model based on the sample predicted sales data and the sample sales data of the target medicine in the sample hospital to obtain the medicine sales data prediction model.
Based on any of the above embodiments, the drug sales data processing apparatus further comprises a parameter determination unit configured to:
determining importance analysis results of parameters in the second hospital information on sales data prediction based on correlation analysis results between at least two sample predicted sales data and the sample sales data respectively;
and determining the parameters contained in the first hospital information from the parameters of the second hospital information based on the importance analysis result of the parameters in the second hospital information on sales data prediction.
Based on any of the above embodiments, the model training unit is further configured to:
performing parameter iteration on the at least two initial models based on correlation analysis results between the at least two sample predicted sales data output by the at least two initial models and the sample sales data respectively to obtain at least two regression models;
determining the drug sales data prediction model based on the at least two regression models.
Based on any of the above embodiments, the model training unit is further configured to:
and determining the medicine sales data prediction model based on the at least two regression models and the correlation analysis result of the regression models in the parameter iteration process.
Based on any of the above embodiments, the drug sales data processing apparatus further comprises a policy determination unit configured to:
determining a sales strategy of the target drug at each target hospital based on the predicted sales data and/or the sample sales data.
Based on any of the above embodiments, the policy determination unit is further configured to:
determining at least one of a market sales level for the target drugs for the target hospitals, a drug sales level for the target enterprise drugs for the target hospitals, and a sales share level for the target enterprise drugs for the target hospitals based on the forecasted sales data and the sample sales data; the target enterprise drug is determined based on an enterprise identity of the target drug;
determining a sales strategy of the target drugs at each target hospital based on at least one of a marketing level, a drug sales level, and a sales share level of the target hospital.
Based on any of the above embodiments, the drug sales data processing apparatus further comprises a data replacement unit configured to:
in a case where the predicted sales data indicates abnormal data, the predicted sales data is replaced based on similar predicted sales data belonging to a same class of hospitals as the non-sample hospital, the class of hospitals being determined based on hospital information.
Fig. 4 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 4: a processor (processor)410, a communication Interface 420, a memory (memory)430 and a communication bus 440, wherein the processor 410, the communication Interface 420 and the memory 430 are communicated with each other via the communication bus 440. The processor 410 may invoke logic instructions in the memory 430 to perform a drug sales data processing method comprising: determining a target medicine and a target hospital; under the condition that the target hospital is a non-sample hospital, inputting first hospital information of the non-sample hospital into a drug sales data prediction model to obtain predicted sales data of the target drug in the non-sample hospital, which is output by the drug sales data prediction model; the medicine sales data prediction model is obtained by training based on first hospital information of a sample hospital and sample sales data of the target medicine in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, department information and city information.
In addition, the logic instructions in the memory 430 may be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program, the computer program being stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is capable of executing the drug sales data processing method provided by the above methods, the method comprising: determining a target medicine and a target hospital; under the condition that the target hospital is a non-sample hospital, inputting first hospital information of the non-sample hospital into a drug sales data prediction model to obtain predicted sales data of the target drug in the non-sample hospital, which is output by the drug sales data prediction model; the medicine sales data prediction model is obtained by training based on first hospital information of a sample hospital and sample sales data of the target medicine in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, department information and city information.
In yet another aspect, the present invention also provides a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements a method for processing drug sales data provided by the above methods, the method comprising: determining a target medicine and a target hospital; under the condition that the target hospital is a non-sample hospital, inputting first hospital information of the non-sample hospital into a drug sales data prediction model to obtain predicted sales data of the target drug in the non-sample hospital, which is output by the drug sales data prediction model; the medicine sales data prediction model is obtained by training based on first hospital information of a sample hospital and sample sales data of the target medicine in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, department information and city information.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for processing drug marketing data, comprising:
determining a target medicine and a target hospital;
under the condition that the target hospital is a non-sample hospital, inputting first hospital information of the non-sample hospital into a drug sales data prediction model to obtain predicted sales data of the target drug in the non-sample hospital, which is output by the drug sales data prediction model;
the medicine sales data prediction model is obtained by training based on first hospital information of a sample hospital and sample sales data of the target medicine in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, department information and city information.
2. The method of claim 1, wherein the drug sales data prediction model is trained based on the following steps:
determining an initial model;
inputting second hospital information of the sample hospital into an initial model to obtain sample predicted sales data of the target drug in the sample hospital, wherein the sample predicted sales data is output by the initial model, and the second hospital information comprises the first hospital information;
and performing parameter iteration on the initial model based on the sample predicted sales data and the sample sales data of the target medicine in the sample hospital to obtain the medicine sales data prediction model.
3. The method for processing drug sales data according to claim 2, wherein the inputting second hospital information of the sample hospital into an initial model to obtain sample predicted sales data of the target drug at the sample hospital output by the initial model, further comprises:
determining importance analysis results of parameters in the second hospital information on sales data prediction based on correlation analysis results between at least two sample predicted sales data and the sample sales data respectively;
and determining the parameters contained in the first hospital information from the parameters of the second hospital information based on the importance analysis result of the parameters in the second hospital information on sales data prediction.
4. The drug sales data processing method of claim 2, wherein there are at least two initial models;
the parameter iteration is carried out on the initial model based on the sample predicted sales data and the sample sales data of the target medicine in the sample hospital to obtain the medicine sales data prediction model, and the method comprises the following steps:
performing parameter iteration on the at least two initial models based on correlation analysis results between the at least two sample predicted sales data output by the at least two initial models and the sample sales data respectively to obtain at least two regression models;
determining the drug sales data prediction model based on the at least two regression models.
5. The method of claim 4, wherein determining the drug sales data prediction model based on the at least two regression models comprises:
and determining the medicine sales data prediction model based on the at least two regression models and the correlation analysis result of the regression models in the parameter iteration process.
6. The method for processing drug sales data according to claim 1, wherein the target hospitals include the sample hospital and the non-sample hospital, and the obtaining of the predicted sales data of the target drugs output by the drug sales data prediction model at the non-sample hospital further comprises:
and determining the sales strategy of the target medicine in each target hospital based on the predicted sales data and the sample sales data.
7. The method of claim 6, wherein the determining the sales strategy of the target drug at each target hospital based on the predicted sales data and the sample sales data comprises:
determining at least one of a market sales level for the target drugs for the target hospitals, a drug sales level for the target enterprise drugs for the target hospitals, and a sales share level for the target enterprise drugs for the target hospitals based on the forecasted sales data and the sample sales data; the target enterprise drug is determined based on an enterprise identity of the target drug;
determining a sales strategy of the target drugs at each target hospital based on at least one of a marketing level, a drug sales level, and a sales share level of the target hospital.
8. The drug sales data processing method according to any one of claims 1 to 7, wherein the obtaining of the predicted sales data of the target drug at the non-sample hospital output by the drug sales data prediction model further comprises:
in a case where the predicted sales data indicates abnormal data, the predicted sales data is replaced based on similar predicted sales data belonging to a same class of hospitals as the non-sample hospital, the class of hospitals being determined based on hospital information.
9. A medicine sales data processing apparatus, comprising:
a medicine and hospital determination unit for determining a target medicine and a target hospital;
the system comprises a sales data determining unit, a sales data predicting unit and a data processing unit, wherein the sales data determining unit is used for inputting first hospital information of a non-sample hospital into a medicine sales data predicting model to obtain predicted sales data of a target medicine in the non-sample hospital, and the predicted sales data is output by the medicine sales data predicting model;
the medicine sales data prediction model is obtained by training based on first hospital information of a sample hospital and sample sales data of the target medicine in the sample hospital, wherein the first hospital information comprises at least one of hospital scale information, hospital department information and hospital city information.
10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the drug sales data processing method according to any of claims 1 to 8 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210613628.3A CN115083560A (en) | 2022-05-31 | 2022-05-31 | Medicine sales data processing method and device and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210613628.3A CN115083560A (en) | 2022-05-31 | 2022-05-31 | Medicine sales data processing method and device and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115083560A true CN115083560A (en) | 2022-09-20 |
Family
ID=83248657
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210613628.3A Pending CN115083560A (en) | 2022-05-31 | 2022-05-31 | Medicine sales data processing method and device and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115083560A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006080989A2 (en) * | 2005-01-25 | 2006-08-03 | Ims Software Services, Inc. | System and method for product level projections of pharmacy prescriptions within product therapy classes |
| CN108363752A (en) * | 2018-01-30 | 2018-08-03 | 中国人民解放军战略支援部队信息工程大学 | User's social effectiveness analysis method of scale forecast is propagated based on microblogging |
| CN109785003A (en) * | 2019-01-17 | 2019-05-21 | 四川骏逸富顿科技有限公司 | A kind of Pharmaceutical retail industry medicine sales forecasting system and method |
| CN112001740A (en) * | 2020-06-19 | 2020-11-27 | 南京理工大学 | Combined prediction method based on adaptive neural network |
| CN113570162A (en) * | 2021-08-30 | 2021-10-29 | 平安医疗健康管理股份有限公司 | Hospitalization cost prediction method and device based on artificial intelligence and computer equipment |
| CN113642755A (en) * | 2021-05-20 | 2021-11-12 | 中国科学院重庆绿色智能技术研究院 | Whole sales prediction method based on partial medicine sales data of hospital |
| CN114445120A (en) * | 2021-12-27 | 2022-05-06 | 苏州联科医疗科技有限公司 | Medicine market scale prediction system based on machine learning |
-
2022
- 2022-05-31 CN CN202210613628.3A patent/CN115083560A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2006080989A2 (en) * | 2005-01-25 | 2006-08-03 | Ims Software Services, Inc. | System and method for product level projections of pharmacy prescriptions within product therapy classes |
| CN108363752A (en) * | 2018-01-30 | 2018-08-03 | 中国人民解放军战略支援部队信息工程大学 | User's social effectiveness analysis method of scale forecast is propagated based on microblogging |
| CN109785003A (en) * | 2019-01-17 | 2019-05-21 | 四川骏逸富顿科技有限公司 | A kind of Pharmaceutical retail industry medicine sales forecasting system and method |
| CN112001740A (en) * | 2020-06-19 | 2020-11-27 | 南京理工大学 | Combined prediction method based on adaptive neural network |
| CN113642755A (en) * | 2021-05-20 | 2021-11-12 | 中国科学院重庆绿色智能技术研究院 | Whole sales prediction method based on partial medicine sales data of hospital |
| CN113570162A (en) * | 2021-08-30 | 2021-10-29 | 平安医疗健康管理股份有限公司 | Hospitalization cost prediction method and device based on artificial intelligence and computer equipment |
| CN114445120A (en) * | 2021-12-27 | 2022-05-06 | 苏州联科医疗科技有限公司 | Medicine market scale prediction system based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dakin et al. | “Yes”,“No” or “Yes, but”? Multinomial modelling of NICE decision-making | |
| Millard et al. | Machine learning to assist risk-of-bias assessments in systematic reviews | |
| AU2012245343B2 (en) | Predictive modeling | |
| CN106933956B (en) | Data mining method and device | |
| CN111430029A (en) | Multi-dimensional stroke prevention screening method based on artificial intelligence | |
| CN110263827B (en) | Abnormal transaction detection method and device based on transaction rule identification | |
| CN107507016A (en) | A kind of information push method and system | |
| Ollech et al. | A random forest-based approach to identifying the most informative seasonality tests | |
| EP2169572A2 (en) | System and method for using classification trees to predict rare events | |
| CA3020921A1 (en) | Query optimizer for combined structured and unstructured data records | |
| CN115101160A (en) | Drug sales data mining and retrieving method and device | |
| CN112308623A (en) | High-quality client loss prediction method and device based on supervised learning and storage medium | |
| CN113342939A (en) | Data quality monitoring method and device and related equipment | |
| Fu et al. | Utilizing timestamps of longitudinal electronic health record data to classify clinical deterioration events | |
| Blut | Meta-analysis in information systems research: method choices and recommendations for future research | |
| CN115083560A (en) | Medicine sales data processing method and device and electronic equipment | |
| CN114462910A (en) | Abnormal investigation method and system for grain storage data | |
| CN113537759A (en) | User experience measurement model based on weight self-adaptation | |
| CN106845686A (en) | Tobacco Method for Sales Forecast method based on factor scores | |
| CN113656692A (en) | Product recommendation method, device, equipment and medium based on knowledge migration algorithm | |
| CN113763181A (en) | Risk pressure test system | |
| CN112562854A (en) | Accurate medical care service recommendation method and system for elderly people | |
| Krusinskas et al. | THE RESEARCH OF RELIABILITY OF BANKRUPTCY PREDICTION MODELS IN LITHUANIAN COMPANIES. | |
| Ostengo et al. | Selecting sugarcane genotypes (Saccharum spp.) according to sucrose accumulation | |
| CN117522419B (en) | Resource allocation method applied to customer relationship management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |