Medical Sales Support Information Processing Device and Method

Abstract

It is necessary to support efficient marketing and sales promotion activities by pharmaceutical companies, thereby enabling reductions in marketing costs and optimization of pharmaceutical costs, and ultimately improving the social situation in which lives that could be saved are not being saved. [Solution] An acquisition unit that acquires data including the attributes of each physician, the history or schedule of sales promotion activities including sending email newsletters to the physician, notifications of opening the email newsletters, web interviews, or face-to-face interviews, or the results of the sales promotion activities; and a storage unit that stores a program and the data. The present invention provides a device, program, or method having medical sales support information processing technology, which includes a calculation unit that calls the aforementioned program and data, calculates the probability of use or prescription using a statistical method including logistic regression analysis, or calculates recommended sales activities using a logit function based on the probability of use or prescription, and an output unit that shows the recommended sales activities calculated by the calculation unit.

Description

Technical Field

[0001] The present invention relates to a medical sales support information processing apparatus and method.

Background Art

[0002] The soaring of pharmaceutical prices has become a serious social problem, especially in developed countries, causing a situation where lives that could be saved are not saved. Behind this, for example, there is a current situation where pharmaceutical companies are investing more funds in marketing activities and sales promotion activities rather than research and development (R&D). Therefore, in the United States, marketing costs drive up drug prices, preventing access to the latest treatments and becoming a social problem. In Japan, where the state determines the reimbursement price of pharmaceuticals, the attractiveness of the Japanese market with its low reimbursement prices is lost, and 143 pharmaceutical products that have been approved in Europe and the United States but not in Japan remain unapproved in Japan, 86 of which have been left undeveloped as of March 2023. On the other hand, a part of the marketing expenditure does not reach the appropriate targets, resulting in waste. One of the major factors contributing to this waste is that the optimal sales targets for products have not been determined from the perspective of users. In order to reduce the waste of such inefficient marketing activities and inefficient sales promotion activities and suppress the increase in drug price costs, it is effective to improve the accuracy of marketing activities and optimize resource allocation. In the past, the marketing of pharmaceuticals and medical devices mainly relied on qualitative activities from an experiential and intuitive perspective. However, with the significant changes in the external environment, decision-making based on experience and intuition has a high degree of uncertainty. Therefore, in recent years, a Customer Relationship Management system (CRM) that applies information technology to marketing activities has been proposed and used in some cases. Relationship Management system (CRM) has been proposed and used in some cases.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

[0004] However, there is a problem in that the success rate of sales support systems that have actually been implemented is low. Some reports even indicate that up to 70% of implementations end in failure. This is partly because the theoretical models used in conventional sales support systems are weak, and in particular, they are not based on statistically processed theoretical models that clearly target individual physicians, who are the decision-makers in drug adoption. This invention was made to solve the above-mentioned problems and provides sales support technology that is in line with a theoretical model based on statistical processing that utilizes the latest logistic regression analysis and logit functions, etc., and clearly targets individual physicians who are the decision-makers for adopting pharmaceuticals, etc. Furthermore, this invention has multiple functions to achieve this objective. [Means for solving the problem]

[0005] According to the present invention, an acquisition unit acquires data including the attributes of each physician, the history or schedule of sales promotion activities including sending email newsletters to the physician, notifications of opening the email newsletters, web interviews, or face-to-face interviews, or the results of the sales promotion activities, A storage unit for storing the program and the aforementioned data, A calculation unit that retrieves the aforementioned program and data, calculates the probability of use or prescription using statistical methods including logistic regression analysis, or calculates recommended sales activities using a logit function based on the probability of use or prescription, An output unit showing the recommended sales activities calculated by the calculation unit, A medical sales support information processing device, including the following, will be provided. [Effects of the Invention]

[0006] According to this invention, it is possible to support pharmaceutical companies in achieving efficient marketing and sales promotion activities, thereby enabling a reduction in marketing costs and optimization of pharmaceutical costs, and contributing to the improvement of the social situation in which lives that could be saved are not saved. [Brief explanation of the drawing]

[0007] [Figure 1] This is a conceptual diagram showing the configuration of the medical sales support information processing device 1 when the server 10 and customer information terminals are connected via network N. [Figure 2] This is a block diagram showing the functional configuration of the server 10 that enables the operation of the medical sales support information processing device 1. [Figure 3] This diagram shows the data structure of the initial value input doctor table 1012. [Figure 4] This diagram shows the data structure of product table 1013 for initial value input. [Figure 5] This diagram shows the data structure of input table 1014 for initial value input and ROI analysis. [Figure 6] This diagram shows the data structure of the activity simulation table 1015. [Figure 7] This diagram shows the data structure of ROI simulation table 1016. [Figure 8] This diagram shows the data structure of the Sales Report Consulting Table 1017. [Figure 9] This is a flowchart showing the operation of the activity simulation. [Figure 10] This is a flowchart showing the process for selecting doctors with high similarity. [Figure 11] This is a flowchart showing how the ROI simulation works. [Figure 12] This chart illustrates the operation of the sales report consulting service. [Figure 13] This is an example of an Excel A FORM for uploading initial values ​​for an activity simulation. [Figure 14]It is a block diagram showing the basic hardware configuration of a general computer 90 that constitutes an information processing apparatus.

Embodiments for Carrying Out the Invention

[0008] Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings for describing the embodiments, common components are denoted by the same reference numerals, and repeated descriptions are omitted. Note that the following embodiments do not unduly limit the content of the present invention described in the claims. Also, not all of the components shown in the embodiments are essential components of the present invention. Further, each drawing is a schematic diagram and is not necessarily drawn precisely.

[0009] <Configuration of Medical Sales Support Information Processing Apparatus> Hereinafter, a description will be given while referring to the drawings related to the information processing apparatus. As shown in FIG. 1, the medical sales support information processing apparatus 1 in the present invention includes a connected server 10 and a management information processing terminal 15, and can also connect arbitrary information processing terminals 20, 30, etc. of customers and the like. Some or all of them may be connected by a network N. The network N is disclosed assuming the Internet or a line of a mobile phone carrier, but is not limited thereto, and may be, for example, a dedicated line. Similarly, although the server 10 is disclosed as being connected to the management information processing terminal 15 by the network N, some or all of it may be stored in the management information processing terminal 15.

[0010] <Configuration of Information Processing Apparatus> FIG. 2 is a block diagram showing the functional configuration of the server 10.

[0011] Each information processing device consists of a computer equipped with an arithmetic unit and memory for control and calculations. The basic hardware configuration of the computer and the basic functional configuration of the computer realized by said hardware configuration will be described later. For each of the following, such as server 10, management information processing terminal 15, and arbitrary information processing terminals 20, 30, etc., explanations that overlap with the basic hardware configuration and basic functional configuration of the computer described later will be omitted.

[0012] <Server 10 Configuration> Server 10 acquires and stores information related to the medical sales support information processing device 1, and as needed. This is an information processing device that calculates and provides information. Server 10 comprises a storage unit 101 and a control unit 104.

[0013] <Configuration of the storage unit 101 of server 10> The storage unit 101 of the server 10 includes an application program 1011, a doctor table 1012, a product table 1013, an ROI table 1014, an activity simulation table 1015, an ROI simulation table 1016, and a sales report consulting table 1017.

[0014] <Configuration of the control unit 104 of server 10> The control unit 104 of the server 10 includes an acquisition unit 1041, a calculation unit 1042, and an output unit 1043.

[0015] <Functions of the medical sales support information processing device>

[0016] <Optimized Sales Action Calculation Process> According to this invention, firstly, in order to improve the accuracy of targeting of sales targets, physicians with a high probability of using or prescribing the target drug are predicted and identified, and their probabilities are evaluated. As a result, similar target customers can be identified and matched, enabling effective resource allocation. In other words, physicians who are predicted to have a desired range of usage or prescription probabilities, such as a high probability, can be identified, and their probabilities can be presented.

[0017] <Overview of the process for calculating optimized sales actions> The optimized sales action calculation process utilizes statistical methods, particularly logistic regression analysis, to quantify the results of sales activities for each physician and derive the amount of activity necessary to maximize sales effectiveness.

[0018] The inventor of the present invention has demonstrated that logistic regression analysis of multiple regressions can be applied to the calculation of optimized sales actions, that is, We found that by fixing the explanatory variables corresponding to each physician's attributes and varying the explanatory variables corresponding to sales promotion activities, we could evaluate multiple aforementioned usage or prescription probabilities and determine the sales promotion activity that maximizes the usage or prescription probability as the optimal sales action, or recommended sales activity. To explain in more detail, In this invention, we found that by calculating the maximum probability and the optimal combination of regression coefficients (sales activity items) that constitute the maximum probability when, in principle, the regression coefficient related to physician attributes is fixed among the 21 regression coefficients used in logistic regression analysis of multiple regressions, while the remaining regression coefficients related to sales activities are freely set, it is possible to derive the maximum usage or prescription probability for each physician and to calculate the minimum amount of sales activity required when the usage or prescription probability of each sales activity is maximized. The regression coefficient related to physician attributes that is fixed represents the attributes of each individual physician, and the regression coefficient related to sales activities that is freely set represents the content of the sales activity. Therefore, this invention provides an efficient apparatus and method for calculating the optimal sales action by utilizing the logistic function (probability transformation) and its inverse function, the logit function (linear combination). Specifically, the optimal sales activity model will be constructed using the following procedure. 1. Data Collection • Collect activity history data for each physician (e.g., number of visits, number of information sessions attended, number of times materials were provided, etc.) • Collect physician attribute information (e.g., specialty, workplace, prescribing tendencies, etc.) • Predict or collect the results of sales activities (e.g., adoption and prescription status of pharmaceuticals). 2. Analysis using statistical methods Using the collected data, the relationship between each activity and its outcome (use or prescription) will be statistically analyzed, and a coefficient showing the correlation between the activity and the outcome will be calculated. • Apply the logit function to calculate the probability of use or prescription for each physician. 3. Development of a sales optimization model (a model for each physician with a desired range of usage or adoption probability) For physicians with a low prescribing or usage rate (e.g., less than 50%), quantitatively calculate which sales activities need to be increased and by how much to improve sales. • For physicians with a certain usage or prescription rate (e.g., 50% or more), it is possible to generate proposals to reduce unnecessary sales activities. 4. Visualization and output of results • Output the analysis results to a file and provide them in a format that sales and marketing personnel can view. • Present an optimization strategy for each sales activity in a report, and provide actionable plans. Details of the process will be described later.

[0019] <Cosine Similarity Analysis> The outline of the cosine similarity analysis of the present invention is disclosed in the patent publications obtained by the inventor (Japanese Patent No. 7636838), but the present invention particularly relates to a system and method for quantifying the similarity between medical professionals based on attribute data of physicians or medical professionals (age, specialty, certifications, employment type, etc.) and outputting it visually or in data format. This system converts attribute data into a numerical format, then standardizes continuous variables and calculates cosine similarity on a scale of 0 to 100. This allows the system to present the similarity between healthcare professionals in a way that is intuitively understandable to the user. In other words, this system has the following steps. 1. Obtain attribute data of healthcare professionals in Excel or a similar format. 2. Perform data preprocessing to convert attribute data into numerical format and standardize continuous variables. 3. Calculate cosine similarity and generate similarity scores between each healthcare professional on a scale of 0 to 100. 4. Output the calculation results as an Excel file or database, providing them in a format that can be used for analysis. For more details, do the following: A. Data entry and preprocessing ·Receive the attribute data for each medical professional as input. ·The attribute data includes age, qualifications, specialized fields, number of activities, etc. ·Standardize continuous variables and adjust scale differences. B. Similarity calculation ·Calculate the cosine similarity based on the quantified attribute data. ·Convert the calculation result of the cosine similarity to a scale of 0 - 100 and provide it as a score that can be intuitively interpreted. C. Output of results ·Save the calculation results to an Excel file or database. ·Visualize the similarity scores between medical professionals and make them available for optimizing educational programs and proposing team compositions. According to the present invention, advanced analysis based on the characteristics of medical professionals becomes possible, promoting the efficiency of resource management and the discovery of new interactions. Furthermore, 1. It can efficiently analyze the attribute - based similarity between medical professionals. 2. The similarity scores can be intuitively interpreted, enabling the utilization of a high degree of consistency among medical professionals with scores of, for example, 70% or more. 3. Based on the analysis results, it becomes possible to optimize educational programs and resource allocation. 4. It can process a large amount of data in a short time and provide highly accurate results.

[0020] <ROI analysis> According to the present invention, the present invention conducts ROI analysis on each sales promotion activity, enabling optimal budget allocation. Until now, within a certain period (e.g., one year), multiple events (campaigns) have been carried out, and even when the effects appeared, it was not clear which event contributed to the sales performance and to what extent. Therefore, both efficient and inefficient events had to be continued.

[0021] <Details of ROI analysis> ROI stands for "Return On Investment," meaning "return on investment." ROI analysis is a return on investment analysis, that is, it represents the ratio of the resulting effect, i.e., sales, to the funds invested in sales support. According to the present invention, it is an indicator that shows the extent to which sales increased as a result of the invested event (campaign) before and after the investment. With the present invention, the ROI can be calculated for each campaign, making it easy to judge whether or not it is desirable to continue individual campaigns, thus contributing to sales efficiency.

[0022] Traditionally, it has been difficult to quantitatively evaluate the ROI (Return on Investment) analysis—specifically, how much each campaign contributed to sales before and after a given period, especially when multiple campaigns were running simultaneously within that period—and there has been a lack of suitable methods for doing so. The inventors of this invention have found a regression analysis model that fits to an ROI analysis that quantitatively evaluates how much each campaign contributed to sales when multiple campaigns are conducted in the same year, and have invented a technique to calculate the impact of each campaign on the increase in sales using the regression coefficients calculated by this regression analysis model. In other words, this invention provides an efficient method and system for performing regression analysis on sales increase data and campaign data to quantitatively evaluate the impact of each campaign and calculate ROI.

[0023] Specifically, the present invention further calculates the ROI for each campaign based on sales data and campaign data in the following steps. 1. Acquisition of sales increase amount The increase in sales is calculated based on the annual sales figures for the target year and the sales figures for the previous year. If there are significant differences in the increase in sales among individual doctors, the growth rate (for the period before and after the relevant period) may be used instead. 2. Impact assessment using regression analysis The inventors of this invention have found that, for each customer implementing a campaign, the relationship between whether each campaign was implemented or not (represented as zero or one) for each doctor, and the impact of the investment amount in each campaign on the increase in sales to each doctor, fits well to the following multiple regression equation (1). Furthermore, they have found that the regression coefficient multiplied by each investment amount in each term of this equation can represent the weight, i.e., the degree of impact, of each investment.

[0024]

number

[0025] In other words, in equation (1) above, y is the increase in sales, m is the number of investments made, x1 x2 ... is the investment amount for each campaign, and the calculated regression coefficient represents the weight, or influence, of each investment.

[0026] Furthermore, (1) above can be expressed as follows: (2).

[0027]

number

[0028] The regression coefficients can then be calculated using the least squares method from equation (2) above. The formula for calculating each regression coefficient (= the impact of each campaign) is the following formula (3). The calculation method could be the same as the least squares method, which calculates the regression coefficient β that minimizes the loss function, for example, as follows.

[0029]

number

[0030] Based on the regression coefficients obtained from the regression analysis described above, the relative impact of each campaign n is calculated using the following equation (4). m is a natural number representing the number of campaigns, and n is any natural number between 1 and m.

[0031]

number

[0032] Calculation of total ROI: The total ROI is calculated by dividing the total increase in sales by the total investment in all campaigns. 4. Calculating ROI for each campaign The ROI for each campaign is calculated by multiplying the relative impact of each campaign by the total ROI. 5. Visualization and Export of Results Export the analysis results in Excel format and use them for decision-making.

[0033] <Daily report analysis> According to the present invention, it is possible to analyze the daily reports of sales representatives, analyze doctors' prescribing trends and market feedback, and make summaries and strategic recommendations.

[0034] <Details of daily report analysis> In the pharmaceutical and related industries, sales reports are recognized as an important source of information for those working in the field. However, the vast amount of data from these sales reports is not being fully utilized, leading to the following challenges. 1. Bias in human analysis When sales representatives and managers analyze daily reports, only subjectively favorable aspects are emphasized, and objective data analysis is lacking. 2. Insufficient application of analysis results to tactics and strategies The information from daily reports is not effectively reflected in sales activities or strategic planning, and the value of daily reports is not being fully utilized. 3. Waste of resources The failure to properly analyze daily reports leads to inefficient sales activities and unnecessary costs, which ultimately contribute to increased drug prices. To address these challenges, this invention utilizes AI generation to automatically and objectively analyze sales reports and propose optimal sales activities tailored to the specific needs of the field.

[0035] This invention applies a generation AI (e.g., a general-purpose generation AI server such as ChatGPT) to sales report data to extract important information, perform quantitative and qualitative analysis, and automatically generate sales strategies. This reduces the burden on human resources and contributes to the optimization of sales activities and the suppression of increases in pharmaceutical prices. The main features of this invention are as follows: 1. Automated data analysis Significant sales data will be extracted from sales reports, and an objective analysis will be performed using a data generation AI. This will enable analysis free from the human bias of traditional methods. A general-purpose data generation AI server, such as ChatGPT, can be a commonly available one. 2. Proposal for sales optimization Based on the analysis results, the system automatically generates tactics and strategies that are appropriate for the situation on site. 3. Cost reduction By using general-purpose generative AI technology to streamline traditional human analysis processes and eliminate unnecessary sales activities, overall cost reductions can be achieved.

[0036] To achieve the above functions, the present invention sets initial values ​​in the medical sales support information processing device. These initial values ​​are stored in the storage unit 104 of the server 10 as the doctor table 1012, the product table 1013, and the ROI table 1014. Details of the doctor table 1012, the product table 1013, and the ROI table 1014 are described below.

[0037] Figure 3 shows the data structure of Doctor Table 1012. Doctor Table 1012 is a table that stores and manages affiliation and attribute information of physicians who have the authority or the de facto decision-making power to adopt or prescribe pharmaceuticals and medical devices. The administrator of the medical sales support information processing device inputs this information about physicians into Doctor Table, and the information is stored in the records of Doctor Table 1012. This allows users of the medical sales support information processing device to use the services of the present invention. Doctor Table 1012 is a table that has the facility physician code as the primary key and columns for physician no., physician name, facility no., facility name, attribute 1, attribute 2, attribute 3, attribute 4, attribute 5, attribute 6, attribute 7, attribute 8, and registration date and time D, which is the date and time when this information was input.

[0038] The facility physician code is an item that stores identification information (numerical symbols, etc.) related to the target of sales activities, assigned to each combination of physician and affiliated facility. The facility physician code is an item with a unique value assigned to each combination of physician and facility. The physician / facility code may be a combination of physician number and facility number. The physician name and facility name are the personal name of the physician or the name of the hospital or other facility that the physician number and facility number refer to, respectively. The physician name and facility name may be written as a shortened name, nickname, or any other arbitrary string. Attributes 1 through 8 are fields for recording attributes that may be relevant to the sales activities of the target salesperson. While much of this information is publicly available, such as age, gender, affiliated academic societies, and affiliated research groups, it may also include information that is not publicly available, such as newsletter subscriptions the physician has shown interest in. The information registered in the Doctor Table 1012 record can be modified by the administrator, or it may be modified by the user of the medical sales support information processing device based on the information entered during use and recorded in the Activity Simulation Table 1015 described below. All input and output information to the medical sales support information processing device, including initial values, is recorded in the Input / Output Record Table (no diagram), and the administrator can trace its history.

[0039] Figure 4 shows the data structure of product table 1013. Product table 1013 is a table that stores and manages information such as regression coefficients calculated from the results of a logistics regression analysis performed in advance on pharmaceuticals and other products that are the target of sales activities. Product table 1013 is also a management table within the server. Therefore, it has fields for product number and product name, and can distinguish and manage information for many users. Product table 1013 has columns for product number, product name, regression coefficients β01, β02, β03, β04, β05, β06, β07, β08 corresponding to attributes 1 to 8, regression coefficients β09, β10, β11, β12, β13, β14, β15, β16, β17, β18, β19, β20, β21 corresponding to activities 1 to 13, and registration date and time P for input date and time.

[0040] The product number is identification information that identifies the medical product targeted by multiple users of the medical sales support information processing device. The product name is the name of the product represented by the product number. Logistic regression analysis is performed for each individual product number, and regression coefficients, etc., are predetermined. The product number is an item for which a unique value is set for each individual product. Furthermore, individual users do not need to present the product number each time they use this invention. The method for determining regression coefficients for each individual product number is performed by logistic regression analysis based on pre-collected information on the attributes of each physician for each individual product number, the type and frequency of sales activities, and the probability of product use and prescription. In addition, the factor analysis method invented and patented by the inventor of this invention, as described in Japanese Patent No. 7418877, can also be utilized. As with general logistic regression analysis, data preprocessing, such as imputing missing data and handling outliers, is completed before inputting regression coefficients as initial values. Furthermore, a sufficient number of data points are secured, and sufficient consideration is given to avoiding multicollinearity and overfitting before using them as initial values. In addition, more advanced methods of logistic regression analysis, such as penalized logistic regression or multiclass logistic regression, may be used. The regression coefficients obtained in this manner are stored in columns β01 to β08 for those corresponding to physician attributes 1 to 8, and in columns β09 to β21 for those corresponding to sales activities 1 to 13. The date and time when these values ​​were input into the medical sales support information processing device is stored in the registration date and time P column.

[0041] The inventor of the present invention has obtained a factor analysis method (Japanese Patent No. 7418877 (JP7418877B)) which is a sales support technology based on factor analysis of physician data.

[0042] Figure 5 shows the data structure of ROI table 1014. ROI table 1014 is a table used to input initial values ​​into a medical sales support device for conducting ROI analysis for each campaign when medical customers conduct sales campaigns for pharmaceuticals and other products that are the target of sales activities. Specifically, ROI table 1014 consists of calculated values ​​such as whether or not each campaign was implemented for each physician who is a customer, the monthly sales for each physician, the monthly sales for each physician in the previous year, and the sales increase amount calculated from these. ROI table 1014 has columns for Customer_ID representing each physician, Campaign_1, 2, 3 etc. representing whether or not campaigns 1 to 3 (the numbers are examples; the same applies below) were implemented for each customer physician, the year and month storing the monthly sales for each physician in the implementation year, the year and month storing the monthly sales for the previous year, the total annual sales TOTAL calculated from these, the sales increase amount Incremental, and the sales increase rate Incremental (%).

[0043] The Customer_ID is an identifier that identifies each physician or their affiliated institution, who is a customer. This field must have a unique value assigned to each physician. Campaigns 1, 2, 3, etc., are stored in each Customer ID field as either zero or one, indicating whether or not each campaign (1 to 3) was implemented. The year and month column stores the sales performance corresponding to each Customer ID for the campaign year, as well as the sales performance for the previous year. The total annual sales calculated from these are stored in the TOTAL column, the sales increase in the Incremental column, and the sales increase rate in the Incremental(%) column. These values ​​can also be input by creating an Excel spreadsheet and uploading it in bulk to the medical sales support information processing system.

[0044] <Configuration of the control unit 104 of server 10> The control unit 104 of the server 10 includes an acquisition unit 1041, a calculation unit 1042, and an output unit 1043. The control unit 104 realizes the functions of each functional unit by executing the application program 1011 stored in the storage unit 101.

[0045] The acquisition unit 1041 acquires information that the administrator of the medical sales support information processing device has pre-input as initial values, and stores it in the doctor table 1012, product table 1013, and ROI table 1014 of the storage unit 101. This completes the initial registration, and the information stored in the doctor table 1012, product table 1013, or ROI table 1014 becomes available for use. In addition, it acquires information entered by the user of the medical sales support information processing device and stores it in the activity simulation table 1015, ROI simulation table 1016, and sales report consulting table 1017 of the storage unit 101. This enables calculations by the calculation unit.

[0046] The calculation unit 1042 retrieves information from the activity simulation table 1015, ROI simulation table 1016, and sales report consulting table 1017, which have been acquired by the acquisition unit 1041 and stored in the storage unit 101. It then performs calculations using logit functions, etc., by the application program 1011, and stores the results in designated sections of the activity simulation table 1015, ROI simulation table 1016, and sales report consulting table 1017.

[0047] The output unit 1043 retrieves information from the activity simulation table 1015, ROI simulation table 1016, and sales report consulting table 1017, which include the results calculated by the calculation unit 1042 and stored in the storage unit 101, and provides the user of the medical sales support information processing device with the information to display on a monitor, print, or export as an electronic file in an appropriate format such as Excel. In addition, the output unit 1043 may also display, print, or export as an electronic file in an appropriate format such as Excel the information from the doctor table 1012, product table 1013, or ROI table 1014, as needed by the user. The output unit 1043 may be configured to allow the administrator of the medical sales support information processing device to display, print, or export electronic files in an appropriate format such as Excel for the doctor table 1012, product table 1013, and ROI table 1014 information from the storage unit 101, which are information that has been input as initial values ​​in advance, to a monitor display, print, or export electronic files in an appropriate format such as Excel for the information stored in the input / output history table to a monitor display, print, or export electronic files in an appropriate format such as Excel.

[0048] The medical sales support information processing device may include a communication unit that performs communication processing with the customer's information processing terminals 20-30 or any other information processing terminal.

[0049] <Configuration of Information Processing Terminals 20 and 30> The customer information processing terminals 20 and 30 may be any type of terminal as long as they can transmit the necessary information to the user of the medical sales support information processing device, regardless of whether they are servers, desktop PCs, notebook PCs, mobile terminals, dedicated terminals, etc. Also, the customer information processing terminals 20 and 30 may have a function to display the information received from the server 10 by the user of the medical sales support information processing device, but this is not limited thereto.

[0050] <Configuration of the storage unit 201 of the information processing terminals 20 and 30> The storage unit 201 (not shown in the drawings) of the information processing terminals 20 and 30 includes an application program 2011 and a terminal table 2012 (not shown in the drawings).

[0051] The application program 2011 may be stored in advance in the storage unit 201, or may be configured to be downloaded from a web server or the like operated by a service provider via a communication IF. The application program 2011 includes applications such as a web browser application. The application program 2011 may include an interpreter-type programming language such as JavaScript (registered trademark) that is executed on the web browser application stored in the information processing terminals 20 and 30.

[0052] <Operation of the medical sales support information processing device> Hereinafter, each process of the medical sales support information processing device will be described in detail. FIG. 6 is an activity simulation table 1015 used for <optimal sales action calculation process>. FIG. 9 related thereto is a flowchart showing the operation of <optimal sales action calculation process>. FIG. 10 is a flowchart showing the operation of <cosine similarity analysis> process. FIG. 7 is an ROI simulation table 1016 used for <ROI analysis> process. FIG. 11 related thereto is a flowchart showing the operation of <ROI analysis> process. Figure 8 shows the sales report consulting table 1017 used for the <sales report analysis> process. Figure 12, related to this, is a chart illustrating the operation of the <Sales Report Analysis> process.

[0053] <Activity simulation table 1015 for calculating optimized sales actions> Figure 6 shows the data structure of the activity simulation table 1015 used in the <Optimized Sales Action Calculation Process>. Note that Figure 6 is an example of a management table and is not, in principle, displayed to customers. The activity simulation table 1015 is a table in which users of the medical sales support information processing device input the attributes of physicians they have actually approached for sales activities regarding pharmaceuticals and other products targeted for sales activities, as well as the details of the sales activities performed on those physicians, in order to perform the <Optimized Sales Action Calculation Process>, and also stores and manages the calculated <Optimized Sales Actions>. The activity simulation table 1015 is located on the server. The activity simulation table 1015 has columns for product number, product name, facility physician code, physician no., physician name, facility no., facility name, usage or prescription probability "before" p0, x01, x02, x03, x04, x05, x06, x07, x08 as explanatory variables corresponding to attributes 1 to 8, multiplied by the regression coefficient obtained by logistic regression analysis, x09, x10, x11, x12, x13, x14, x15, x16, x17, x18, x19, x20, x21 as explanatory variables corresponding to activities 1 to 13, registration date a0 for the above, usage or prescription probability "after" p1 to store the results after the <optimized sales action calculation process>, R1, R2, R3 to store the recommended activity name, and registration date a1 to store the results after the <optimized sales action calculation process>. Additional columns may be added if necessary.

[0054] The product number is identification information that identifies the medical product that a user of the medical sales support information processing system intends to use. The product name is the name of the product represented by the product number. However, it is only used by the management information processing terminal and server 10 and does not need to be disclosed to the user. The <Optimized Sales Action Calculation Process> is performed for each individual product number. The product number is an item with a unique value set for each individual product, and it corresponds to the product number in product table 1013.

[0055] The "before" probability of use or prescription p0 is calculated from x01, x02, x03, x04, x05, x06, x07, x08 as explanatory variables corresponding to attributes 1 to 8, which are stored in advance in the activity simulation table 1015, and x09, x10, x11, x12, x13, x14, x15, x16, x17, x18, x19, x20, x21 as explanatory variables corresponding to activities 1 to 13, as well as the regression coefficients stored as initial values ​​in the rows of the product table 1013 with the same product number. This is the probability that the target product will be used or prescribed by the physician in question. On the other hand, the probability of use or prescription "after" p1 is the probability that the target product will be used or prescribed by the physician after the <optimized sales action calculation process> has been performed. In addition, R1, R2, and R3, which store the names of recommended activities, are the names of activities that have a high contribution to achieving the probability of use or prescription "after" p1, but it is not limited to the three highest contributing activities; more activity names may be recorded by adding record fields. The registration date and time a1 stores the date and time when the results after the <optimized sales action calculation process> were recorded.

[0056] <Details of the process for calculating optimized sales actions> Figure 9, related to Figure 6, is a flowchart showing the operation of the <Optimized Sales Action Calculation Process>. The details of the <Optimized Sales Action Calculation Process> are explained below.

[0057] In step S100 of Figure 9, the control unit 104 of the server 10 acquires information for the doctor table 1012 and the product table 1013 input from the management information processing terminal 15, and stores it as initial values ​​in the respective columns of the doctor table 1012 and the product table 1013.

[0058] In step S110, the control unit 104 of the server 10 acquires information for the activity simulation table 1015 collected by the customer from any terminal such as the customer's information processing terminals 20 and 30, and stores it in each column of the activity simulation table 1015 for use before the <optimized sales action calculation process>. Specifically, from any terminal, the following are stored: the target product name, facility physician code, facility name, physician name, x01, x02, x03, x04, x05, x06, x07, x08 as explanatory variables corresponding to attributes 1 to 8, x09, x10, x11, x12, x13, x14, x15, x16, x17, x18, x19, x20, x21 as explanatory variables corresponding to activities 1 to 13, and the registration date and time a0 for the above.

[0059] In step S120, the control unit 104 of the server 10 compares the information identifying the physician stored in the activity simulation table 1015 and the explanatory variables for the physician's attributes, namely the facility physician code, facility name, physician name, and the values ​​of x01, x02, x03, x04, x05, x06, x07, x08 as explanatory variables corresponding to attributes 1 to 8, with the corresponding records stored in the doctor table 1012 (step S130). If there is a discrepancy, the relevant record in the doctor table is overwritten with the information stored in the activity simulation table 1015 (step S135). Then the process returns to step S120 and executes step S120 again. If there is no discrepancy, nothing is done and the process proceeds to the next step S140. All input / output information is recorded in the input / output history table (no diagram), so even if it is later discovered that the overwritten information was incorrect, it is possible to find out what the original data was.

[0060] In step S140, the <Optimized Sales Action Calculation Process> is performed. Prior to this, the control unit 104 of the server 10 first reads the regression coefficients etc. corresponding to the product numbers of the activity simulation table 1015 stored in the product table 1013, and extracts x01, x02, x03, x04, x05, x06, x07, x08 as explanatory variables corresponding to attributes 1 to 8 of the activity simulation table 1015, and x09, x10, x11, x12, x13, x14, x15, x16, x1 as explanatory variables corresponding to activities 1 to 13. 7, x18, x19, x20, x21 and β01, β02, β03, β04, β05, β06, β07, β08, β09, β10, β11, β12, β13, β14, β15, β16, β17, β18, β19, β20, β21 stored in product table 1013 are multiplied by those with the same product number, and the usage or prescription probability "before" p0 is calculated using a logit function and stored in the corresponding column of activity simulation table 1015. An example of an equation for calculating p0 using the logit function in this case is given by equation (5) below (where pi = p0), but this is not the only example.

[0061]

number

[0117] )

[0062] Furthermore, in step S140, the combination of the usage or prescription probability "after" p1, which is the maximum probability that the target product will be used or prescribed by the target physician after the <optimized sales action calculation process> has been performed, and the value of x related to the activities to obtain it is calculated and recorded. That is, while the explanatory variables x01, x02, x03, x04, x05, x06, x07, and x08, which correspond to attributes 1 to 8 that identify the physician and are stored in the activity simulation table 1015, remain fixed, the explanatory variables x09, x10, x11, x12, x13, x14, x15, x16, x17, x18, x19, x20, and x21, which correspond to activities 1 to 13, are changed to calculate the combination of x09 to x21 that maximizes the usage or prescription probability "after" p1. These calculated values ​​are stored in the input / output history table, and at the same time, in step S150, the names of the activities with the greatest contribution, the usage or prescription probability "after" p1, and the date and time of their calculation are stored in the activity simulation table 1015 in the columns for usage or prescription probability "after" p1, R1, R2, R3, and registration date and time a1.

[0063] When calculating the combination of x09~x21 that maximizes the probability of use or prescription "after" p1, p1 is given by the above formula (5), p i We can set =p1. To calculate the combination of x09 to x21 that maximizes the probability of use or prescription "after" p1, in addition to the formulas shown herein, general methods for calculating the optimal combination using the logistic function or logit function may be used, or the maximum likelihood method may be used. Then, the activities with the greatest impact are selected from the terms (terms about activities) in the following equation (6) that have β09 to β21.

[0064]

number

[0065] In other words, for each term in the following equation (7), you could, for example, select three with the largest calculated values ​​and store the corresponding activity names as the top 3 high-contributing activities.

[0066]

number

[0067] Furthermore, the target of this <optimized sales action calculation process> may be limited to physicians who use it with a set threshold, or to physicians whose prescription probability "before" p0 is low (for example, less than 50%).

[0068] In step S160, the control unit 104 of the server 10 may output, via the output unit, the combination of the usage or prescription probability "after" p1, which is the probability that the target product will be used or prescribed by the physician after the <optimized sales action calculation process> has been performed, the x value related to the activities to obtain it, and the name of the activity with the greatest contribution. The output may be displayed on a monitor display, printed, or written to an electronic file.

[0069] For cosine similarity analysis, a dedicated table is not required.

[0070] <Details of cosine similarity analysis> Figure 10 is a flowchart showing the operation of the <Cosine Similarity Analysis> calculation process. The details of the <Cosine Similarity Analysis> are explained below. Because the <Optimized Sales Action Calculation Process> described above allows for similarity analysis to be performed on physicians with a high probability of use or prescription, it can be said that the <Cosine Similarity Analysis> performed after the <Optimized Sales Action Calculation Process> has a synergistic effect.

[0071] In step S200 of Figure 10, the control unit 104 of the server 10 obtains information for the doctor table 1012 and the product table 1013 from the management information processing terminal 15 and stores it in the respective columns of the doctor table 1012 and the product table 1013 as initial values.

[0072] In step S210, after the control unit 104 of the server 10 performs <Optimized Business Action Calculation Process>, the facility doctor code stored in the product table 1013 or the facility doctor code specified by the customer from any terminal such as the customer's information processing terminals 20 and 30 is obtained through the acquisition unit as information representing the similarity source.

[0073] In step S220, the calculation unit of the control unit 104 of the server 10 calculates the cosine similarity between the attribute information of the doctor having the facility doctor code obtained in step S210 and the attribute information of each doctor stored in the doctor table. The results of each similarity may be recorded in the input / output history table. Also, in step S230, the control unit 104 of the server 10 may store the results in the doctor table 1012. Incidentally, columns for storage may be added to the doctor table 1012.

[0074] In step S240, the control unit 104 of the server 10 selects a doctor with a high similarity from the results of step S220. Note that the selection of a doctor with a high similarity is an example, and it is also possible to select by specifying a desired similarity range.

[0075] Also, in step S240, the output unit 1043 of the control unit 104 of the server 10 outputs information on doctors having a desired similarity. The output may be a display on a monitor display, printing, or writing to an electronic file.

[0076] FIG. 7 is a diagram showing the data structure of the ROI simulation table 1016 used for <ROI analysis>. The ROI simulation table 1016 is a table that stores and manages the campaign activities carried out by customers, etc., the sales performance during the target period for result verification, the sales performance of the previous year, and the <ROI analysis> results, etc. for products such as pharmaceuticals targeted for sales activities. The ROI simulation table 1016 has columns for customer no, customer name, investment amounts for each of the implemented campaigns 1 to 5, total number of implemented campaigns, total absolute value of relative influence degrees for the implemented campaigns, calculated relative influence degrees for campaigns 1 to 5, monthly settlement 1 (Jan - Dec, Total) which is the sales performance during the target period, monthly settlement 0 (Jan - Dec, Total) which is the sales performance of the previous year, sales increase amount which is the increase in sales performance, total ROI, ROI for each campaign of campaigns 1 to 5, and registration date and time r when these are stored. Note that the ROI analysis according to the present invention statistically aggregates and analyzes individual customer data stored in the ROI simulation table 1016 to evaluate the overall impact of the campaigns. Therefore, the "ROI per campaign" and "relative influence degree" described in the table are not values for individual customers but aggregated indicators based on overall analysis.

[0077] A customer is an enterprise that uses a medical sales support information processing device, such as a pharmaceutical company or a medical device manufacturing and sales enterprise. Customer no is an item for which a unique value corresponding to the customer name is set. A campaign is a special event implemented to promote sales to doctors, which incurs costs but is carried out in anticipation of increased sales. The investment amount in the implemented campaign activities is the actual amount of money invested by the customer in each campaign. Note that even if the same campaign is implemented multiple times in the same target year, it is regarded as separate campaign events by attaching numbers, etc. for distinction. The number of implementations is the total number of campaigns implemented by the customer in that year.

[0078] The regression coefficient β value corresponding to each campaign is calculated by the ROI analysis. The sum of the absolute values ​​of the regression coefficient β values ​​corresponding only to the campaigns that were implemented, as shown in ROI Simulation Table 1016, is stored in the "Implemented β Value Absolute Sum" column. The relative impact is calculated using the actual sum of absolute β values ​​as the denominator and the β value of each campaign as the numerator.

[0079] The monthly sales figures for the target product from January to December of the target year are read from the aforementioned ROI table 1014, which is the initial value table, and stored in the monthly settlement 1 (Jan-Dec column), with the total amount stored in the total1 column. The monthly sales figures for the target product from January to December of the previous year are stored in the monthly settlement 0 (Jan-Dec column), with the total amount stored in the total0 column. The difference between the total1 column and the total0 column is then stored in the sales increase column. Note that this sales increase may be obtained by the data acquisition unit based on the value entered by the user at the time of use. As long as the corresponding months for the current year and the previous year are stored, it is acceptable for some months' sales figures to be missing, and it is not necessary for all figures for December to be filled in. In that case, figures such as campaign investment amount will also be calculated based on the entered sales period.

[0080] The Total ROI column stores the value obtained by dividing the sales increase by the total campaign investment. The ROI columns for Campaigns 1-5 store the percentage obtained by dividing the funds invested in each campaign by the sales increase multiplied by the relative impact. The Registration Date and Time column stores the date and time when the ROI was calculated. Note that the number of campaigns is not limited to 5, and columns such as Campaigns 1-5 may be added as needed.

[0081] Furthermore, if it is possible to calculate the total cost of the normal sales activities that users conduct with doctors under normal circumstances over the relevant period, it may be treated as the investment amount for a single campaign. If this is possible, it will be possible to more comprehensively capture the factors influencing the increase in sales and to consider whether each other campaign is more or less efficient than normal sales activities.

[0082] <Details of ROI Analysis> Figure 11 related to Figure 7 is a flowchart showing the operation of <ROI Analysis>. The details of <ROI Analysis> will be described below. In step S300 of Figure 11, the control unit 104 of the server 10 acquires and stores the information for the ROI table 1014 from the management information processing terminal 15.

[0083] In steps S310 and S320, the control unit 101 of the server 10 acquires the information of the ROI table 1014 which is the initial value, and stores it in each column for the investment amount in each campaign activity implemented, the number of implementations, monthly settlement 0, and monthly settlement 1.

[0084] The number of implementations of the implemented campaigns and the investment amounts in each campaign activity of the implemented campaigns 1 to 5 are acquired and stored from a predetermined terminal. Incidentally, for the acquisition of these information, a prompt by a general-purpose generation AI or Python (registered trademark) etc. may be used.

[0085] In step S330, the calculation unit 1042 of the control unit 104 of the server 10 applies the acquired respective values to the above-described mathematical formula to calculate the regression coefficient for each campaign activity. The control unit 104 of the server 10 stores the total value of the absolute values of those regression coefficients in the implemented β value absolute value total column. Further, the calculation unit 1042 of the control unit 104 of the server 10 divides the regression coefficient β value corresponding to the campaign 1 to 5 columns in which numerical values are stored in the investment amount column for each implemented campaign activity of the ROI simulation table 1016 by the value in the implemented β value absolute value total column, and stores the obtained value in the corresponding campaign 1 to 5 columns of the relative influence degree. The calculation unit 1042 of the control unit 104 of the server 10 separately stores the value obtained by dividing the sales increase amount by the total investment amount in the campaign activities in the total ROI column.

[0086] In step S340, the calculation unit of the control unit 104 of the server 10 stores the value obtained by multiplying the sales increase by the relative impact of each campaign and dividing that amount by the investment amount made in each campaign into the ROI column for campaigns 1 to 5. In other words, the calculation result of the following formula (8) is stored.

[0087]

number

[0088] In step S350, the output unit of the control unit 104 of the server 10 outputs the ROI for each campaign. The output may be displayed on a monitor, printed, or written to an electronic file.

[0089] <Sales report consulting table 1017 for sales report analysis> Figure 8 shows the data structure of the sales report consulting table 1017 used for the <sales report analysis> process. The sales report consulting table 1017 is a table that inputs sales report text data of activities actually carried out by MRs (Medical Representatives; the same applies hereinafter) etc. to physicians approached for pharmaceuticals and other products targeted for sales activities, in order to perform <sales report analysis>, and also stores and manages reports including summaries and countermeasure recommendations as a result of the <sales report analysis>. The sales report consulting table 1017 is located on a server. The sales report consulting table 1017 has columns for product number, product name, physician facility code, physician no., physician name, facility no., facility name, daily report data, AI_response, and registration date and time t where the AI_response is recorded.

[0090] The product number is identification information that identifies the medical product that a user of the medical sales support information processing system intends to use. However, the product number is usually not displayed on the screen, etc., and is used for internal processing. The product name is the name of the product represented by the product number. <Sales report analysis> is performed for each individual product number. The product number is an item with a unique value set for each individual product and corresponds to the product number in product table 1013.

[0091] The daily report data column stores the data of the sales report text for the pharmaceutical products targeted for sales activities, specifically the activities conducted by MRs (Medical Representatives) with the doctors they actually approached, prior to the implementation of the <Sales Report Analysis> process. The report, including summaries and recommended actions, is created using an external general-purpose AI server. The general-purpose AI server can be a common one such as ChatGPT. The generated report, including summaries and recommended actions, is stored in the AI_response column. The registration date and time column stores the date and time when the data was stored in the AI_response column after the <Sales Report Analysis> process.

[0092] <Details of Sales Report Analysis> Figure 12, related to Figure 8, is a chart illustrating the operation of the <Sales Report Analysis> process. The details of <Sales Report Analysis> are explained below.

[0093] In step S12 of Figure 12, the acquisition unit 1041 of the control unit 104 of the server 10 acquires the sales report (text) information (S11) for the target period collected by the customer from any terminal such as the customer's information processing terminals 20 and 30, and stores it in the daily report data column of the sales report consulting table 1017.

[0094] The acquisition unit 1041 of the control unit 104 of the server 10 identifies the physician facility code (S14), the target period (S15), etc., from the character information entered in the daily report data column, or from any terminal such as the customer's information processing terminals 20 and 30.

[0095] The acquisition unit 1041 of the control unit 104 of the server 10 creates a prompt that includes instructions for an external general-purpose generation AI server to analyze the text stored in the daily report data using natural language processing (NLP) technology, extract important information from the vast amount of daily reports and summarize it concisely (summary generation function), objectively identify problems on site (issue extraction function), and generate appropriate sales strategy proposals (improvement proposal function), and requests the generation AI server to generate the data (S17). The generation server performs the specified summary and item text generation, embedding it into a predetermined form (without attached drawings), and responds to server 10 (S19). The control unit 104 of server 10 stores the response in the AI_response column of the sales report consulting table 1017, and at the same time stores the date and time of storage in the AI_response column in the registration date and time t column.

[0096] In step S22, the output unit 1043 of the control unit 104 of the server 10 outputs the contents of the AI_response field in a predetermined format. This output may be displayed on a monitor display (S22) by sending the content to the customer's information processing terminal 20 or the like (S21), or it may be printed or written to an electronic file.

[0097] <Basic Computer Hardware Configuration> Figure 14 is a block diagram showing the basic hardware configuration of a typical computer 90. The computer 90 includes at least a processor 901, main memory 902, auxiliary storage 903, and a communication interface IF991. These are electrically connected to each other by a communication bus 921.

[0098] The processor 901 is hardware for executing the instruction set written in a program. The processor 901 consists of an arithmetic unit, registers, peripheral circuits, etc.

[0099] Main memory 902 is used to temporarily store programs and data processed by programs, etc. For example, it is a volatile memory such as DRAM (Dynamic Random Access Memory).

[0100] Auxiliary storage device 903 is a storage device for saving data and programs. Examples include flash memory, HDD (Hard Disc Drive), magneto-optical disk, CD-ROM, DVD-ROM, and semiconductor memory.

[0101] The IF991 communication interface is an interface for inputting and outputting signals for communication with other computers via a network using wired or wireless communication standards. A network consists of various mobile communication systems built by the internet, LANs, wireless base stations, etc. For example, a network includes 3G, 4G, 5G mobile communication systems, LTE (Long Term Evolution), and wireless networks that can connect to the internet via designated access points (e.g., Wi-Fi®). When connecting wirelessly, communication protocols include, for example, Z-Wave®, ZigBee®, and Bluetooth®. When connecting via a wired connection, the network includes USB (Universal Serial This includes connections made directly via bus cables or other means.

[0102] Furthermore, it is possible to virtually realize a computer 90 by distributing all or part of each hardware configuration across multiple computers 90 and connecting them to each other via a network. Thus, the concept of computer 90 includes not only a computer 90 housed in a single enclosure, but also a virtualized computer system.

[0103] <Basic Functional Configuration of Computer 90> The functional configuration of the computer realized by the basic hardware configuration of computer 90 (Figure 14) will be explained. The computer comprises at least one functional unit: a control unit, a memory unit, and a communication unit.

[0104] Furthermore, the functional units of computer 90 can also be realized by distributing all or part of each functional unit across multiple computers 90 interconnected via a network. The concept of computer 90 includes not only a single computer 90 but also a virtualized computer system.

[0105] The control unit reads various programs stored in the auxiliary storage device 903 by the processor 901, loads them into the main memory 902, and executes processing according to the program. The control unit can realize the functions of various information processing units depending on the type of program. In this way, the computer becomes an information processing device that performs information processing.

[0106] The memory unit is implemented by the main memory 902 and the auxiliary memory 903. The memory unit stores data, various programs, and various databases. The processor 901 can also reserve memory areas corresponding to the memory unit in the main memory 902 or the auxiliary memory 903 according to the program. The control unit can also cause the processor 901 to perform operations such as adding, updating, and deleting data stored in the memory unit according to the various programs.

[0107] A database, specifically a relational database, is a system for managing and relating tabular data sets called masters, which are structurally defined by rows and columns. In a database, tables are called tables, masters are called masters, the columns of tables are called columns, and the rows of tables are called records. In a relational database, relationships can be established and linked between tables and masters. Typically, each table and master has a primary key column to uniquely identify records, but setting a primary key column is not mandatory. The control unit can instruct the processor 901 to add, delete, or update records in specific tables and masters stored in the memory unit, according to various programs.

[0108] Furthermore, each table, database, and master in this invention may include any data structure (list, dictionary, associative array, object, etc.) in which information is structurally defined. The data structure also includes data that can be considered a data structure by combining data with functions, classes, methods, etc., written in any programming language.

[0109] The communication unit is implemented by the communication IF991. The communication unit provides the functionality to communicate with other computers 90 via the network. The communication unit can receive information transmitted from other computers 90 and input it to the control unit. The control unit can cause the processor 901 to perform information processing on the received information according to various programs. Furthermore, the communication unit can transmit information output from the control unit to other computers 90. Specific implementation example

[0110] Embodiments 1, 2, and 3 are described below as specific examples of implementation.

[0111] <Embodiment 1> Company A is a pharmaceutical company that developed a new drug, P, for weight loss and launched it two years ago. Company A's MRs (Medical Representatives) and wholesalers have achieved a 15% market share through various sales activities, including visits to doctors at hospitals and other facilities. While the clinical prescribing results for drug P are positive, and Company A believes it can still increase sales, it also feels that some doctors are inexplicably reluctant to prescribe drug P, and that allocating sales resources uniformly to such doctors is wasteful. Therefore, Company A will utilize the present invention.

[0112] In the medical sales support information processing device of the present invention, after the launch of the new drug P, the data on the attributes of each hospital facility and the doctors belonging to them, as well as the content of sales activities and their results (use or prescription), are obtained by the control unit 104 of the server 10 from the management information processing terminal 15 for the doctor table 1012 and the product table 1013, and stored in the respective columns of the doctor table 1012 and the product table 1013, and the input of initial values ​​has already been completed.

[0113] Company A's medical representatives (MRs) compile, in Excel Form A, the attributes of each hospital facility and physician they intend to approach regarding the new drug P, to the best of their knowledge, along with their planned sales activities.

[0114] In the medical sales support information processing device of the present invention, in step S110, the control unit 104 of the server 10 acquires the information necessary for the <optimized sales action calculation process> for the activity simulation table 1015 and stores it in each column of the activity simulation table 1015.

[0115] Specifically, the system retrieves facility physician code, facility name, physician name, attributes (gender, age, affiliated academic societies, etc.), planned activities 1 through 13 (future sales activities such as in-person consultations, web consultations, email awareness campaigns, and newsletter distribution), product names, product numbers, other affiliation information, and regression coefficients for logistic regression analysis that have been pre-calculated and appropriately pre-processed using other technologies.

[0116] In step S120, the control unit 104 of the server 10 compares the information identifying the physician stored in the activity simulation table 1015 and the explanatory variables for the physician's attributes, namely the facility physician code, facility name, physician name, and the values ​​of x01, x02, x03, x04, x05, x06, x07, x08 as explanatory variables corresponding to attributes 1 to 8, with the corresponding records stored in the doctor table 1012 (step S130). If there is a discrepancy, the relevant record in the doctor table 1012 is overwritten with the information stored in the activity simulation table 1015 (step S135). Then the process returns to step S120 and executes step S120 again. If there is no discrepancy, nothing is done and the process proceeds to the next step S140. All input / output information is recorded in the input / output history table, so even if it is later discovered that the overwritten information was incorrect, it is possible to find out what the original data was.

[0117] In step S140, the control unit 104 of the server 10 performs the <optimized sales action calculation process>. Prior to this, the control unit 104 of the server 10 first reads the regression coefficients etc. corresponding to the product numbers of the activity simulation table 1015 stored in the product table 1013, and extracts x01, x02, x03, x04, x05, x06, x07, x08 as explanatory variables corresponding to attributes 1 to 8 of the activity simulation table 1015, and x09, x10, x11, x12, x13, x14, x15, x16, x1 as explanatory variables corresponding to activities 1 to 13. 7, x18, x19, x20, x21 and β01, β02, β03, β04, β05, β06, β07, β08, β09, β10, β11, β12, β13, β14, β15, β16, β17, β18, β19, β20, β21 stored in product table 1013 are multiplied by those with the same product number, and the usage or prescription probability "before" p0 is calculated using a logit function and stored in the corresponding column of activity simulation table 1015. In addition, the registration date a0 is stored.

[0118] Furthermore, in step S140, the combination of the usage or prescription probability "after" p1, which is the maximum probability that the target product will be used or prescribed by the physician after the <optimized sales action calculation process> is performed, and the value of x related to the activity to obtain it is calculated and recorded. That is, x01, x02, x03, x04, x05, x06, x07, and x08, which are explanatory variables corresponding to attributes 1 to 8 that identify the physician and are stored in the activity simulation table 1015, are kept fixed, while the values ​​of x09, x10, x11, x12, x13, x14, x15, x16, x17, x18, x19, x20, and x21, which are explanatory variables corresponding to activities 1 to 13, are opened up, and the combination of x09 to x21 that maximizes the "after" usage or prescription probability p1 is calculated using the logit function or the like as described above. The calculated value is stored in the input / output history table, and at the same time, in step S150, the names of the three activities with the greatest contribution, the usage or prescription probability "after" p1, and the calculation date and time are stored in the activity simulation table 1015 in the columns for usage or prescription probability "after" p1, R1, R2, R3, and registration date and time a1.

[0119] In step S160, the control unit 104 of the server 10 displays the combination of the usage or prescription probability "after" p1, which is the maximum probability that the target product will be used or prescribed to the physician after the <optimized sales action calculation process> has been performed, and the values ​​of x related to the activities to obtain it, along with the names of the three activities with the greatest contribution, on the monitor display via the output unit 1043.

[0120] According to the results, even if Company A's MR attempts to approach Dr. D, the planned activities—8 in-person meetings, 12 email outreach campaigns, and 2 mailings of materials—the new drug will not be adopted. The probability of Dr. P being adopted and prescribed by Dr. D is only 44%, but if 19 in-person consultations, 15 email awareness campaigns, and 5 mailings of materials are conducted, the probability of the new drug P being adopted and prescribed by Dr. D increases. The probability increases to 83%, and it is shown that the above three activities are the activities with a large contribution for this reason. On the other hand, for Doctor F whom the MR of Company A is trying to approach, the currently planned activities are 11 face-to-face interviews, 15 email inspirations, and 7 material mailings. Even if these are carried out, the probability that the new drug P will be adopted by Doctor D and prescribed is only expected to be 21%. Even if the maximum number of activities is increased and the maximum predicted probability is obtained by conducting 29 face-to-face interviews, 29 email inspirations, and 13 material mailings, it is shown that the probability that the new drug P will be adopted by Doctor D and prescribed will only increase to 26%.

[0121] After seeing this, the MR of Company A decides to write the relevant content to an Excel file and prioritize activities for Doctor D over Doctor F.

[0122] In addition, the person in charge of the MR of Company A wants to know whether the various sales campaigns carried out this year have actually been effective and how efficient an approach has been made in each of the campaigns. Therefore, the person decides to conduct the ROI analysis provided by the present invention.

[0123] Specifically, for performing the ROI analysis of the campaign, the medical sales support information processing device of the present invention of the present invention acquires each information of the sales performance for the two years of this year and the previous year, the total number of times the implemented campaigns have been carried out, and the investment amount of each campaign. After implementing the procedure of the flowchart of <ROI analysis>, the investment efficiency for each campaign can be displayed. According to this, although the overall ROI is 43.6%, the ROI of Campaign 3 has shown an efficiency of 217%. It can be seen that Campaign 1 is below the overall ROI value at 38%, and Campaign 2 is holding back the whole at 23%.

[0124] Therefore, the person in charge of the MR of Company A decides to focus on Campaign 3 in future campaigns, cancel Campaign 2, and implement Campaign 1 for another year to observe the change in ROI.

[0125] By canceling Campaign 2, which is inefficient for both our company and our customers, we should be able to reduce our investment.

[0126] <Embodiment 2> Company B is a pharmaceutical company that developed a new anti-allergic drug, AL, for the treatment of hay fever and launched it a year and a half ago. Due to the increasing number of patients and subtle year-to-year changes in allergens, new anti-allergic drugs for hay fever are launched by various companies almost every year, and sales of older treatments decline, making it important to switch to new drugs. Although Company B's medical representatives (MRs) and wholesalers have not been able to fully carry out activities such as visiting doctors at hospitals and other facilities, and other sales activities, a competitor, Company C, has started selling an AG drug (a generic equivalent) of an anti-allergic drug with very similar efficacy and mechanism of action three years ago. However, this AG drug still has a low market share of less than 10%, and Company B would like to target the same market. The medical sales support information processing device of the present invention has a small amount of registered activity data for Company B's new drug AL, but it has accumulated a considerable amount of data on anti-allergic drugs for the treatment of hay fever, including AG drugs. Therefore, we will use the present invention.

[0127] As described above, data on each hospital facility, the attributes of the physicians belonging to them, and the sales activities and their results (use or prescription) for AG drugs and other products similar to the new drug AL, since their market launch, have been registered in advance by the administrator of the medical sales support information processing device of the present invention. Whenever the information becomes available in the past, in step S100 of Figure 9, the control unit 104 of the server 10 of the medical sales support information processing device of the present invention acquires information for the doctor table 1012 and product table 1013 from the management information processing terminal 15 and stores it in the respective columns of the doctor table 1012 and product table 1013, providing sufficient stored information as initial values. Then, the data for AG drugs and other similar drugs similar to the new drug AL are integrated in the preprocessing and registered as initial values ​​with new similar product numbers.

[0128] Company B's medical representatives (MRs) will compile, in Excel Form A, the attributes of each hospital facility and physician they intend to approach regarding the new drug AL, to the best of their knowledge, along with the planned sales activities they intend to undertake.

[0129] In the medical sales support information processing device of the present invention, in step S110, the control unit 104 of the server 10 acquires the information for the activity simulation table 1015 and stores it in the columns necessary for performing the <optimized sales action calculation process> of the activity simulation table 1015.

[0130] Specifically, this includes facility physician code, facility name, physician name, attributes (gender, age, affiliated academic societies, etc.), and planned activities (visiting interviews, web interviews, email awareness campaigns, newsletter distribution, etc.). The system obtains the planned sales activities from now on, the product name, product number, other affiliation information that have been stored in the server in advance, and regression coefficients for logistic regression analysis that have been calculated in advance using other technologies and appropriately pre-processed.

[0131] In step S120, the control unit 104 of the server 10 compares the information identifying the physician stored in the activity simulation table 1015 with explanatory variables regarding the physician's attributes and performs necessary updates based on the called application program 1011.

[0132] In step S140, the <Optimized Sales Action Calculation Process> is performed. Prior to this, the control unit 104 of the server 10 first reads the regression coefficients etc. corresponding to the aforementioned similar product numbers from the activity simulation table 1015, which is stored in the product table 1013. The explanatory variables corresponding to attributes 1 to 8 of the activity simulation table 1015, and the explanatory variables corresponding to activities 1 to 13, along with β01, β02, β03, β04, β05, β06, β07, β08, β09, β10, β11, β12, β13, β14, β15, β16, β17, β18, β19, β20, β21 stored in the product table 1013, are multiplied together for those with the same product number, and the usage or prescription probability "before" p0 is calculated using a logit function in the same manner as in Embodiment 1, and stored in the corresponding column of the activity simulation table 1015. In addition, the above registration date and time a0 is stored.

[0133] Furthermore, in step S140, the combination of the usage or prescription probability "after" p1, which is the maximum probability that the target product will be used or prescribed by the physician after the <optimized sales action calculation process> has been performed, and the value of x related to the activities to obtain it is calculated and recorded.

[0134] In step S160, the control unit 101 of the server 10 displays the combination of the usage or prescription probability "after" p1, which is the maximum probability that the target product will be used or prescribed to the physician after the <optimized sales action calculation process> has been performed, and the value of x related to the activities to obtain it, along with the name of the activity with the greatest contribution, on the monitor display via the output unit 1043.

[0135] According to the report, even if Company B's MR attempts to approach Dr. G, the currently planned activities—three web meetings, three email outreach programs, and two mailings of materials—they will not be able to promote the new drug A. The probability that L will be adopted and prescribed by Dr. G is only 38%, but if 22 web interviews, 17 email awareness campaigns, and 7 mailings of materials are conducted, the probability that the new drug AL will be adopted by Dr. G is 38%. It is shown that the probability of prescription increases to 89%, and that the three activities mentioned above contribute significantly to this. Meanwhile, for Dr. H, whom Company B's MR is also trying to approach, the currently planned activities include 9 in-person meetings, 13 email awareness campaigns, and Even after mailing materials nine times, the probability of the new drug AL being adopted and prescribed by Dr. D was only 29%. Therefore, to maximize the probability of success by increasing activities to 39 face-to-face meetings and email awareness campaigns, Even after 25 outreach calls and 9 mailings of materials, the probability of the new drug AL being adopted and prescribed by Dr. G only increases to 31%.

[0136] Furthermore, if Company B's medical representative (MR) searches for a physician who can provide an efficient approach on behalf of Dr. H, and if, based on the above results, has similar attributes to Dr. G and therefore has a high similarity score, and clicks a button on the screen of the medical sales support information processing device of the present invention to retrieve a similarity analysis list, the medical sales support information processing device of the present invention will retrieve this information, perform the <cosine similarity analysis> flowchart (Figure 10), and then display a list of physicians with a high similarity score to Dr. G. It can also be used to calculate recommended activities and usage or prescription probabilities for these highly similar physicians, similar to Dr. G.

[0137] Company B's medical representative (MR) will export the above information to an Excel file and immediately begin sales activities targeting Dr. G and several other doctors who are highly similar to Dr. G.

[0138] <Embodiment 3> Company Ding is a medical device manufacturing and sales company that developed and launched a new digital microscope five years ago, which combines the functions of a small camera with high image quality and 8K resolution with a microscope. The company sells this device to physicians and dentists (hereinafter collectively referred to as "physicians"), and although sales were strong at the time of launch, sales performance over the past year has been poor. However, the introduction of new products is still some time away, and the company aims to recover sales by narrowing its target market and improving its sales activities. Since a reasonable amount of data on Company Ding's activities and results regarding its digital microscope has been registered in the medical sales support information processing device of the present invention, the company will begin to use the present invention.

[0139] As described above, data on each hospital facility, the attributes of the doctors belonging to them, and the sales activities and their results (use or prescription) of Company D's digital microscope since its market launch have been registered in advance by the administrator of the medical sales support information processing device of the present invention. Whenever the information becomes available in the past, in step S100 of Figure 9, the control unit 104 of the server 10 of the medical sales support information processing device of the present invention acquires information for the doctor table 1012 and the product table 1013 from the management information processing terminal 15 and stores it in the respective columns of the doctor table 1012 and the product table 1013.

[0140] Company D's Medical Representative (MR) will compile, in Excel Form A, the attributes of each hospital facility and physician they intend to approach regarding Company D's digital microscope, as far as they know, along with the planned sales activities they intend to undertake.

[0141] In the medical sales support information processing device of the present invention, in step S110, the control unit 104 of the server 10 acquires information for the activity simulation table 1015 uploaded by the sales representative of Company D from the management information processing terminal and the server 10, and stores it in each column of the activity simulation table 1015 for performing the <optimized sales action calculation process>.

[0142] Specifically, this includes the facility physician code, facility name, physician's name, attributes (gender, age, affiliated academic societies, etc.), and planned activities from 1 to 13 (visiting interviews, web interviews, email awareness campaigns, newsletter distribution, etc.). The system obtains the planned sales activities from the source, the product name, product number, other affiliation information, and regression coefficients for logistic regression analysis that have been pre-calculated and appropriately pre-processed using a separate technology.

[0143] In step S120, the control unit 104 of the server 10 compares the information identifying the physician stored in the activity simulation table 1015 with explanatory variables regarding the physician's attributes and performs necessary updates based on the called application program 1011.

[0144] In step S140, the <Optimized Sales Action Calculation Process> is performed. Prior to this, the control unit 104 of the server 10 first reads the regression coefficients etc. corresponding to the aforementioned similar product numbers from the activity simulation table 1015, which is stored in the product table 1013. The explanatory variables corresponding to attributes 1 to 8 of the activity simulation table 1015, and the explanatory variables corresponding to activities 1 to 13, along with β01, β02, β03, β04, β05, β06, β07, β08, β09, β10, β11, β12, β13, β14, β15, β16, β17, β18, β19, β20, β21 stored in the product table 1013, are multiplied together for those with the same product number, and the usage or prescription probability "before" p0 is calculated using a logit function in the same manner as in Embodiment 1, and stored in the corresponding column of the activity simulation table 1015. In addition, the above registration date a0 is stored.

[0145] Furthermore, in step S140, the combination of the usage or prescription probability "after" p1, which is the maximum probability that the target product will be used by the physician after the <optimized sales action calculation process> is performed, and the value of x related to the activities to obtain it is calculated and recorded.

[0146] In step S160, the control unit 104 of the server 10 displays the combination of the usage or prescription probability "after" p1, which is the maximum probability that the target product will be used by the physician after the <optimized sales action calculation process> has been performed, the x value related to the activities to obtain it, and the names of the 7 activities with the greatest contribution (calculated in step 150) on the monitor display via the output unit 1043.

[0147] According to the report, even if the sales representative from Company D attempts to approach Dr. J, the currently planned activities—namely, three in-person meetings, three email outreach campaigns, and two mailings of materials—Company D The probability that our company's digital microscope will be adopted and prescribed by Dr. J is only 44%, but if we conduct 6 web interviews, 7 email awareness campaigns, and 6 mailings of materials, then Company D will be able to... The report indicates that the probability of digital microscopes being adopted and used by Dr. J increases to 66%, and that the three aforementioned activities contribute significantly to this goal.

[0148] On the other hand, regarding Dr. K, whom the sales representative from Company D is also trying to approach, even if the currently planned activities—11 web interviews, 15 email outreach programs, and 9 mailings of materials—are carried out, The probability of our company's digital microscope being adopted and prescribed by Dr. K is only 23%. To achieve the highest possible probability, we need to increase our activities further: 49 in-person consultations and 29 email awareness campaigns. After sending materials by mail 19 times, the probability of Company D's digital microscope being adopted by Dr. K only increases to 25%.

[0149] The sales manager of Company D collects the daily sales reports submitted by multiple sales representatives of Company D, and sends the sales report analysis to the customer information processing terminal 40 of the medical sales support information processing device of the present invention using a predetermined Excel FORM (not shown in the drawing). The medical sales support information processing device of the present invention then acquires this data and, after performing the steps described in the <Sales Report Analysis> chart, can display information such as a summary of the sales report and future improvement measures.

[0150] Company B's sales representatives and / or sales managers can export the above information to an Excel file and immediately implement focused sales activities targeting selected doctors, as well as new sales strategies devised based on the improvement suggestions.

[0151] <Effects and Actions> The present invention provides the following effects and benefits.

[0152] 1. Reduction of sales costs By eliminating unnecessary sales activities and focusing on effective activities, costs can be reduced. 2. Optimization of sales resources By developing optimal sales strategies for each physician, it becomes possible to efficiently allocate limited sales personnel. 3. Improving outcome prediction A data-driven, probabilistic approach improves the accuracy of sales performance predictions. 4. Strengthening relationships with doctors This allows for an approach tailored to the physician's needs, leading to the development of better relationships.

[0153] <Note> The details described in each of the above embodiments are noted below.

[0154] (Note 1) An acquisition unit that acquires data including the attributes of each physician, the sending of email newsletters to physicians, notifications of email newsletter opening, the history or schedule of sales promotion activities including web interviews or face-to-face interviews, or the results of sales promotion activities, A storage unit for storing programs and data, A calculation unit that retrieves programs and data, calculates the probability of use or prescription using statistical methods including logistic regression analysis, or calculates recommended sales activities using a logit function based on the probability of use or prescription, An output unit showing recommended sales activities calculated by the calculation unit, Medical sales support information processing device, including

[0155] (Note 2) The medical sales support information processing device described in Appendix 1, wherein the logistic regression analysis includes penaltyed logistic regression or multiclass logistic regression.

[0156] (Note 3) A medical sales support information processing device as described in Appendix 1 or 2, wherein the statistical methods include the use of machine learning models.

[0157] (Note 4) A medical sales support information processing device described in any of the appendices 1 to 3, which calculates recommended sales activities using a linear or nonlinear predictive model.

[0158] (Note 5) A medical sales support information processing device as described in any of Appendix 1 to 4, wherein the calculation unit further performs sales promotion activities for physicians and sales promotion activities based on the aforementioned data, using ROI analysis to quantify the relationship between investment amount and results, and calculate ROI by applying either a statistical method, a machine learning model, or a regression analysis method.

[0159] (Note 6) A medical sales support information processing device as described in any of Appendix 1 to 5, wherein the calculation unit further calculates the similarity between physicians using cosine similarity analysis for physicians with a desired range of usage or prescription probability based on the physician's attributes, classifies physicians based on the calculated similarity, and utilizes this for listing physician names within the desired similarity range.

[0160] (Note 7) A medical sales support information processing device as described in any of Appendix 1 to 6, wherein the calculation unit further analyzes the sales activity record documents using NLP and machine learning models, summarizes them using BERT, TF-IDF, LDA, or supervised learning algorithms, extracts specific information, or calculates a recommended strategy in association with the aforementioned data.

[0161] (Note 8) A medical sales support information processing device as described in any of Appendix 1 to 7, wherein the recommended sales activities include the calculation of the type and increase / decrease volume of sales activities.

[0162] (Note 9) A medical sales support information processing device according to any one of the appendices 1 to 8, wherein the output unit includes outputting or displaying electronic files on a screen.

[0163] (Note 10) A medical sales support information processing device as described in any of Appendix 1 to 9, wherein the output unit can further export or display an electronic file containing recommended tactics or actions for each sales activity.

[0164] (Note 11) A medical sales support information processing device as described in any of the appendices 1 to 10, wherein the medical sales refer to the sales of pharmaceuticals.

[0165] (Note 12) A medical sales support information processing device as described in any of the appendices 1 to 10, wherein the medical sales refer to the sales of medical devices.

[0166] (Note 13) A computer program that causes the acquisition unit, storage unit, calculation unit, or output unit described in any of the appendices 1 to 12 to perform its operation.

[0167] (Note 14) Steps to acquire data including the attributes of each physician, the history or schedule of sales promotion activities including sending email newsletters to physicians, notifications of email newsletter open rates, web interviews, or in-person interviews, or the results of sales promotion activities, A step of storing the program and data, The steps include: calling up programs and data, calculating the probability of use or prescription using statistical methods including logistic regression analysis, or calculating recommended sales activities using a logit function based on the probability of use or prescription; Steps to show recommended sales activities calculated by the calculation unit, Medical sales support methods including

[0168] (Note 15) The method described in Appendix 14, which includes calculating or determining as described in any of Appendix 2 to 8, or outputting to an electronic file or displaying on a screen as described in any of Appendix 9 to 10.

[0169] (Note 16) A medical sales support method as described in Appendix 14 or 15, wherein the medical sales refer to the sales of pharmaceuticals.

[0170] (Note 17) A medical sales support method as described in Appendix 14 or 15, wherein the medical sales refer to the sales of medical devices.

[0171] (Note 18) In a non-temporary computer-readable medium that stores computer programs A memory and a processor that executes the aforementioned computer program including computers, The processor is designed to support medical sales. The system stores data in memory including the attributes of each physician, the history or schedule of sales promotion activities including sending email newsletters to physicians, notifications of email newsletter openings, web interviews, or in-person interviews, or the results of sales promotion activities. The processor, after receiving the data, calls the program and data. A computer that calculates the probability of use or prescription using statistical methods, including logistic regression analysis, or calculates recommended sales activities using a logit function based on the probability of use or prescription, and outputs the calculated recommended sales activities.

[0172] (Note 19) The computer according to Appendix 18, characterized in that the logistic regression analysis includes penaltyed logistic regression or multiclass logistic regression.

[0173] (Note 20) The computer according to Appendix 18 or 19, characterized in that the statistical methods include the use of machine learning models.

[0174] (Note 21) A computer according to any one of the appendices 18 to 20, characterized in that it calculates recommended sales activities using a linear or nonlinear predictive model.

[0175] (Note 22) A computer according to any one of Appendix 18 to 21, characterized in that sales promotion activities targeting physicians and said sales promotion activities based on data are performed using ROI analysis, which quantifies the relationship between investment amount and results and calculates ROI by applying either a statistical method, a machine learning model, or a regression analysis method.

[0176] (Note 23) A computer according to any one of the appendices 18 to 22, characterized in that it calculates the similarity between physicians using cosine similarity analysis for physicians who have a desired range of usage or prescription probability based on the physician's attributes, classifies the physicians based on the calculated similarity, and utilizes this for listing physician names within the desired similarity range.

[0177] (Note 24) A computer according to any one of the appendices 18 to 23, characterized by analyzing sales activity records using NLP and machine learning models, summarizing them using BERT, TF-IDF, LDA, or supervised learning algorithms, extracting specific information, or calculating recommended strategies in association with the data.

[0178] (Note 25) A computer according to any one of the appendices 18 to 24, characterized in that the recommended sales activities include calculating the type and increase / decrease volume of sales activities.

[0179] (Note 26) A computer as described in any of Appendix 18 to 25, capable of exporting or displaying electronic files.

[0180] (Note 27) A computer as described in any of Appendix 18 to 26, capable of exporting or displaying electronic files containing recommended tactics or actions for each sales activity.

[0181] (Note 28) A computer described in any of the appendices 18 to 27, for which the sale of medical supplies is the sale of pharmaceuticals.

[0182] (Note 29) A computer described in any of the appendices 18 to 27, for which the medical sale is the sale of a medical device.

[0183] (Note 30) A computer used to support medical sales acquires data including the attributes of each physician, the history or schedule of sales promotion activities including sending email newsletters to physicians, notifications of email newsletter open status, web interviews, or in-person interviews, or the results of said sales promotion activities. Store the program and data, The program and data are retrieved, and the probability of use or prescription is calculated using statistical methods including logistic regression analysis, or the recommended sales activity is calculated using a logit function based on the said probability of use or prescription. A medical sales support method that includes outputting calculated recommended sales activities.

[0184] (Note 31) The method described in Appendix 30, which includes causing a computer for medical sales support to perform calculations or calculations as described in any of Appendix 19 to 25, or output to an electronic file or display on a screen as described in any of Appendix 26 to 27.

[0185] (Note 32) A medical sales support method as described in Appendix 30 or 31, wherein the medical sales are sales of pharmaceuticals.

[0186] (Note 33) A medical sales support method as described in Appendix 30 or 31, wherein the medical sales refer to the sales of medical devices.

[0187] (Note 34) In order to support medical sales, The memory stores data including the attributes of each physician, the history or schedule of sales promotion activities including sending email newsletters to the physician, notifications of email newsletter opening, web interviews, or face-to-face interviews, or the results of sales promotion activities. The processor, after receiving the data, calls the program and data. A non-temporarily readable computer medium that calculates the probability of use or prescription using statistical methods including logistic regression analysis, or calculates recommended sales activities using a logit function based on the probability of use or prescription, and outputs the calculated recommended sales activities.

[0188] As described above, this invention can support pharmaceutical companies in achieving efficient sales activities, thereby enabling reductions in sales costs and optimization of pharmaceutical costs, and contributing to the improvement of the social situation in which lives that could be saved are not saved.

[0189] While embodiments of the present invention have been disclosed above, the present invention is not limited thereto and can be modified as appropriate without departing from the technical spirit of the invention. [Industrial applicability]

[0190] This invention can be applied not only to sales activities in the pharmaceutical industry, but also to insurance sales, medical device sales, and other industries that require face-to-face sales, and can be used as a technology to support the formulation of data-driven optimal sales strategies. [Explanation of Symbols]

[0191] 1. Medical Sales Support Information Processing Device 10 servers 15. Management information processing terminal 20 Customer information processing terminals 30 Customer information processing terminals

Claims

1. A medical sales support information processing device comprising: an acquisition unit that acquires data including attributes of each physician, a history or schedule of sales promotion activities including sending email newsletters to the physician, notifications of opening of email newsletters, web interviews, or face-to-face interviews, or the results of the sales promotion activities; a storage unit that stores a program and the data; a calculation unit that retrieves the program and the data, calculates the probability of use or prescription using statistical methods including logistic regression analysis, or calculates recommended sales activities using a logit function with respect to the probability of use or prescription; and an output unit that displays the recommended sales activities calculated by the calculation unit.

2. The medical sales support information processing device according to claim 1, wherein the logistic regression analysis includes penaltyed logistic regression or multiclass logistic regression.

3. The medical sales support information processing device according to claim 1 or 2, wherein the statistical method includes the use of a machine learning model.

4. The medical sales support information processing device according to claim 1 or 2, wherein the calculation of the recommended sales activities is performed using a linear or nonlinear predictive model.

5. The medical sales support information processing device according to claim 4, wherein the calculation unit further performs ROI analysis on the sales promotion activities for physicians and the sales promotion activities based on the data, quantifying the relationship between investment amount and results, and calculating ROI by applying either a statistical method, a machine learning model, or a regression analysis method.

6. The medical sales support information processing device according to claim 1 or 2, wherein the calculation unit calculates the similarity between physicians using cosine similarity analysis for physicians who have a desired range of usage or prescription probability based on the physicians' attributes, classifies physicians based on the calculated similarity, and utilizes this for listing physician names within the desired similarity range.

7. The medical sales support information processing device according to claim 1 or 2, wherein the calculation unit analyzes the sales activity record documents using NLP and machine learning models, summarizes them using BERT, TF-IDF, LDA, or supervised learning algorithms, extracts specific information, or calculates a recommended strategy in association with the data.

8. The medical sales support information processing device according to claim 1 or 2, wherein the recommended sales activity is the calculation of the type and quantity of sales activity.

9. The medical sales support information processing device according to claim 1, wherein the output unit can write out or display an electronic file on a screen.

10. The medical sales support information processing device according to claim 7, wherein the output unit can further write out or display on a screen an electronic file containing recommended tactics or recommended actions for each sales activity.

11. The medical sales support information processing device according to claim 1 or 2, wherein the medical sales are sales of pharmaceuticals.

12. The medical sales support information processing device according to claim 1 or 2, wherein the medical sales are sales of medical devices.

13. A computer program that causes the acquisition unit, storage unit, calculation unit, or output unit described in Claim 1 or 2 to perform operations.

14. A medical sales support method comprising the steps of: acquiring data including attributes of each physician, a history or schedule of sales promotion activities including sending email newsletters to the physician, notifications of opening of email newsletters, web interviews, or face-to-face interviews, or the results of the sales promotion activities; storing a program and the data; retrieving the program and the data, calculating the probability of use or prescription using a statistical method including logistic regression analysis, or calculating recommended sales activities using a logit function with respect to the probability of use or prescription; and showing the recommended sales activities calculated by the calculation unit.

15. The method according to claim 14, comprising the calculation or determination described above, or outputting to an electronic file or displaying on a screen as described in claim 9.

16. The medical sales support method according to claim 14, wherein the medical sales are sales of pharmaceuticals.

17. The medical sales support method according to claim 14, wherein the medical sales are sales of medical devices.

18. A computer comprising a memory which is a non-temporary computer-readable medium for storing a computer program, and a processor which executes the computer program, wherein the processor stores in the memory data including attributes of each physician, a history or schedule of sales promotion activities including sending email newsletters to the physicians, notifications of email newsletter opening, web interviews, or face-to-face interviews, or the results of the sales promotion activities, for the purpose of supporting medical sales, and the processor, after inputting the data, retrieves the program and the data, calculates the probability of use or prescription using a statistical method including logistic regression analysis, or calculates recommended sales activities using a logit function with respect to the probability of use or prescription, and outputs the calculated recommended sales activities.

19. The computer according to claim 18, characterized in that the logistic regression analysis includes penaltyed logistic regression or multiclass logistic regression.

20. The computer according to claim 18 or 19, characterized in that the statistical method includes the use of a machine learning model.

21. The computer according to claim 18 or 19, characterized in that the calculation of the recommended sales activities is performed using a linear or nonlinear predictive model.

22. The computer according to claim 21, characterized in that the sales promotion activities for the physician and the sales promotion activities based on the data are performed using ROI analysis, which quantifies the relationship between investment and results and calculates ROI by applying a statistical method, a machine learning model, or a regression analysis method.

23. The computer according to claim 18 or 19, characterized in that, based on the attributes of the physicians, it calculates the similarity between physicians using cosine similarity analysis for physicians who have a desired range of usage or prescription probability, classifies the physicians based on the calculated similarity, and utilizes this for listing physician names within the desired similarity range.

24. The computer according to claim 18 or 19, characterized in that it analyzes the aforementioned sales activity record documents using NLP and machine learning models, summarizes them using BERT, TF-IDF, LDA, or supervised learning algorithms, extracts specific information, or calculates a recommended strategy in association with the aforementioned data.

25. The computer according to claim 18 or 19, characterized in that the recommended sales activity includes calculating the type and quantity of sales activity.

26. The computer according to claim 18, which can export or display electronic files on a screen.

27. The computer according to claim 24, which can export or display an electronic file containing recommended tactics or actions for each of the aforementioned sales activities.

28. The computer according to claim 18 or 19, wherein the medical sale is a sale of pharmaceuticals.

29. The computer according to claim 18 or 19, wherein the medical sale is a sale of medical devices.

30. A medical sales support method comprising: having a computer for medical sales support acquire data including the attributes of each physician, the history or schedule of sales promotion activities including sending email newsletters to the physicians, notifications of email newsletter opening, web interviews, or face-to-face interviews, or the results of the sales promotion activities; storing the program and the data; retrieving the program and the data; calculating the probability of use or prescription using statistical methods including logistic regression analysis; calculating recommended sales activities using a logit function based on the probability of use or prescription; and outputting the calculated recommended sales activities.

31. The method according to claim 30, comprising causing a computer for medical sales support to perform the calculation or determination, or output to an electronic file or display on a screen as described in claim 26.

32. The medical sales support method according to claim 30, wherein the medical sales are sales of pharmaceuticals.

33. The medical sales support method according to claim 30, wherein the medical sales are sales of medical devices.

34. A non-temporarily readable computer medium that stores data in memory, including the attributes of each physician, the history or schedule of sales promotion activities including sending email newsletters to the physicians, notifications of email newsletter opening, web interviews, or face-to-face interviews, or the results of the sales promotion activities, after the data has been input, and where the processor retrieves the program and the data, calculates the probability of use or prescription using statistical methods including logistic regression analysis, or calculates recommended sales activities using a logit function with respect to the probability of use or prescription, and outputs the calculated recommended sales activities.

Images