JP2020204956A - Information processing system, information processing method, and computer program - Google Patents

Abstract

To provide a novel technology related to prediction of a performance evaluation index.SOLUTION: With a method according to one aspect of the present disclosure, history data of business action performed by at least one person is acquired. Moreover, actual measurement data of a performance evaluation index related to at least one of a product intended for the business action and roles is acquired. Furthermore, a prediction model for calculating a predicted value related to the performance evaluation index is constructed from a plurality of parameters related to the business action based on the history data and the actual measurement data (370).SELECTED DRAWING: Figure 9

Description

The present disclosure relates to information processing systems, information processing methods, and computer programs.

Conventionally, a prediction system for predicting the number of products sold based on customer attributes, product characteristics, and past sales performance has been known (see, for example, Patent Document 1). A system for evaluating a call operator's conversation with a customer for improving corporate activities is also known (see, for example, Patent Document 2).

Japanese Unexamined Patent Publication No. 2000-2000260 Japanese Unexamined Patent Publication No. 2014-123831

By the way, the transaction volume of a product between a company and a customer is related not only to the characteristics of the product but also to the business behavior of the company to the customer. However, a technique for predicting performance evaluation indicators such as the transaction volume of commodities in consideration of business activities is not yet known. This also applies to services.

Therefore, according to one aspect of the present disclosure, it is desirable to be able to provide a new technique for forecasting performance evaluation indicators.

According to one aspect of the present disclosure, an information processing system for calculating a predicted value regarding a performance evaluation index is provided. The information processing system includes a first acquisition unit, a second acquisition unit, and a construction unit. The first acquisition unit is configured to acquire historical data regarding business activities by at least one actor.

The second acquisition department is configured to acquire actual measurement data of performance evaluation indicators for at least one of the goods and services that are the purpose of the business activity. The construction unit is configured to build a prediction model for calculating a prediction value related to a performance evaluation index from a plurality of variables related to business activities based on the acquired historical data and actual measurement data.

According to this information processing system, it is possible to predict the performance evaluation index of a product or service from the characteristics of business behavior by using a prediction model, and it is possible to improve business behavior based on the prediction result. Therefore, the above-mentioned information processing system is very effective in improving corporate activities.

According to one aspect of the disclosure, the performance indicator can be a transaction volume or an indicator of transaction volume between at least one provider of goods and services corresponding to the actor and the consumer.

According to one aspect of the disclosure, the information processing system may further include a planning unit that creates a business plan based on the constructed forecasting model. For example, a business plan may include information that presents the timing of the business activity and at least one of the other parties. An information processing system equipped with a planning department is very useful for improving corporate activities.

According to one aspect of the present disclosure, the information processing system determines the contribution of each of the above-mentioned plurality of variables explaining the performance evaluation index based on the constructed forecast model, and outputs information on the contribution. May be further provided. Information about contributions is very helpful for users to consider improving their business activities.

According to one aspect of the present disclosure, the plurality of variables are the first parameter regarding the attributes of the actor, the second parameter regarding the attributes of the business partner, the third parameter regarding the business method from the actor to the business partner, and , Can be defined by at least one of the fourth parameters relating to the frequency or number of executions of business activities from the actor to the business destination.

According to one aspect of the disclosure, the first and second parameters belong to the geographic attribute of the corresponding person, the demographic attribute of the corresponding person, the psychographic attribute of the corresponding person, and the corresponding person. It may be a parameter for at least one of the attributes of the organization.

According to one aspect of the present disclosure, the historical data may be data including time information at each execution of a business act together with identification information of an actor, a business destination, and a business method. According to one aspect of the present disclosure, the measured data may be data indicating a time change of the performance evaluation index, such as time series data of the performance evaluation index.

According to one aspect of the present disclosure, the above-mentioned actual measurement data is obtained by the provider and the organization of the goods or services corresponding to the actor for each combination of the organization corresponding to the business partner and the goods or services for the purpose of the business act. The data may include performance indicators for each period related to transactions with and from. The actual measurement data may further include time information at the time of the first transaction for each of the above combinations.

According to one aspect of this disclosure, the Construction Department shall include historical data on the first business activity of the first company, actual measurement data of the first performance evaluation index, and second business activity of the second company. And a forecast model for calculating the forecast value for the first performance indicator from the plurality of variables related to the first business activity as the forecast model based on the data regarding at least one of the performance indicator and the second performance indicator. May be configured to build.

The first business act referred to here means the business act of at least one of the above-mentioned goods and services provided by the first company, and the first performance evaluation index is the above-mentioned goods and services provided by the first company. Means a performance indicator for at least one of the above. The second business act is the business act of at least one of the related goods and services of the second company that provides at least one of the goods and services related to at least one of the goods and services provided by the first company. Means. The second performance indicator means a performance indicator for at least one of the related goods and services provided by the second entity.

According to one aspect of the disclosure, a business act may include a business negotiation between the actor and the business partner. The historical data may include feature data related to the conversation at the time of the negotiation extracted from the voice at the time of the negotiation.

According to one aspect of the present disclosure, a computer program for realizing the functions of the information processing system described above in a computer may be provided. As the first acquisition unit, the second acquisition unit, and the construction unit described above, a computer program for operating the computer may be provided.

According to one aspect of the present disclosure, an information processing method corresponding to the above-mentioned information processing system may be provided. According to one aspect of the present disclosure, an information processing method executed by a computer relating to acquisition of historical data of business activities by at least one actor and at least one of goods and services that are the purpose of the business activities. Information processing including acquisition of actual measurement data of performance evaluation index and construction of a prediction model for calculating predicted value of performance evaluation index from multiple variables related to business activities based on historical data and actual measurement data. Methods may be provided.

It is a block diagram which shows the schematic structure of the system which concerns on the Example Embodiment of this disclosure. It is a block diagram which shows the schematic structure of an analysis system. It is a flowchart which shows the history recording process which a processor executes. It is a figure which shows the schematic structure of the sales report data provided by a salesperson. It is a figure which shows the structure of the business history database. FIG. 6A is a diagram showing the structure of participation history data, and FIG. 6B is a diagram showing the structure of browsing history data. It is a flowchart which shows the transaction DB update process executed by a processor. It is a figure which shows the structure of the transaction database. It is a flowchart which shows the model construction process which a processor executes. FIG. 10A is a diagram showing the configuration of the salesperson attribute database, and FIG. 10B is a diagram showing the configuration of the customer attribute database. It is a figure explaining the construction method of the prediction model. It is a flowchart which shows the business plan creation process which a processor executes. It is a flowchart which shows the contribution output processing which a processor executes. It is a flowchart which shows the model construction process of the 1st modification. It is a figure explaining the method of creating the sample data group of the explanatory variable and the objective variable in the second modification. It is a flowchart which shows the model construction process of the 2nd modification. It is a figure explaining the construction method of the prediction model by the third deformation.

An exemplary embodiment of the present disclosure will be described below with reference to the drawings.
The sales support system 1 of the present embodiment shown in FIG. 1 is a system for supporting the sales activities of a medical representative of a pharmaceutical company, a so-called MR.

One of the jobs of medical representatives is to sell medicines, which are products sold by pharmaceutical companies. This business activity includes the act of encouraging a doctor to prescribe a drug by providing information about the drug to the doctor, and linking the drug to a transaction, that is, a sale. The sales support system 1 of the present embodiment is configured to provide information for supporting this business act to a pharmaceutical company.

In the following, pharmaceutical companies targeted for sales support are referred to as target companies. The medical representative is referred to as a salesperson, and the person in charge of sales by the salesperson, specifically a doctor, is referred to as a customer. The customer corresponds to the business partner. Furthermore, the organization to which the customer belongs is expressed as a customer organization or a business partner. Examples of customer organizations include hospitals, departments within hospitals (especially large facilities), and clinics.

As shown in FIG. 1, the sales support system 1 of the present embodiment includes an analysis system 10 which is an information processing system for data analysis, and a plurality of mobile terminals 30 possessed by each of the sales staff. It includes a mobile terminal 30. The analysis system 10 is configured to collect and analyze the sales report data DR, which is the report data related to the business activity provided from the mobile terminal 30 of each salesperson.

In order to analyze the relationship between the sales behavior to the customer and the drug sales to the customer organization, the analysis system 10 is further configured to acquire the drug sales data from the sales data management system 50 of the target company.

Further, the analysis system 10 is configured to acquire market research data on pharmaceutical products from the market data management system 60. The analysis system 10 is further configured to acquire doctor data from the doctor data management system 70.

As shown in FIG. 2, the analysis system 10 includes a processor 11, a memory 12, a storage 13, and a communication interface 19. The processor 11 is configured to execute a process according to a computer program recorded in the storage 13.

The memory 12 functions as a working memory when the processor 11 executes a process according to a computer program. The storage 13 is an auxiliary storage device, and is composed of, for example, a hard disk drive. The communication interface 19 is configured to be communicable with the mobile terminal 30, the sales data management system 50, the market data management system 60, and the doctor data management system 70.

The processor 11 repeatedly executes the history recording process shown in FIG. 3 according to the computer program, and operates so as to update the business history database 131 in the storage 13 based on the business report data DR received from the mobile terminal 30. ..

When the history recording process shown in FIG. 3 is started, the processor 11 waits until the business report data DR relating to the business activity of the salesperson is received from the mobile terminal 30 through the communication interface 19 (S110).

Each of the mobile terminals 30 is configured to create a sales report data DR and transmit it to the analysis system 10 based on the operation of the sales staff. The business report data DR is created for each business act and transmitted to the analysis system 10.

As shown in FIG. 4, the sales report data DR transmitted from the mobile terminal 30 includes salesperson information, customer information, customer organization information, business date and time information, sales means information, and sales content data. ..

The salesperson information included in the sales report data DR is the identification information of the salesperson who performed the business act. Customer information is identification information of a customer who has received a business act. The customer organization information is the identification information of the organization to which the customer who received the business activity belongs. Doctors often belong to multiple hospitals. This customer organization information indicates which organization the customer received a business act as a respondent.

The business date and time information indicates the date and time when the business act was performed. The business means information indicates the type of business means. Examples of business means include "visit", "telephone" and "email". “Visit” indicates that the salesperson visited the customer and conducted a business act. "Telephone" indicates that the salesperson has conducted a business act to the customer through the telephone. "Email" indicates that the salesperson has conducted a business act to the customer through e-mail.

The business content data includes record data regarding the content of business activities. When the sales means is "visit", the sales content data includes recorded data recording a conversation (that is, a business negotiation) between the salesperson and the customer when the salesperson visits the customer. When the business means is "telephone", the business content data includes recorded data recording the conversation between the salesperson and the customer by telephone. When the sales means is "email", the sales content data includes the data of the e-mail sent by the salesperson to the customer.

The business content data may include not only the recorded data of the conversation described above, but also supplementary data explaining the environment and / or situation of the business activity. Examples of supplementary data include the type of material used during the negotiation, the purpose of the visit, the phase of the visit, and the presence or absence of a companion. Examples of materials used during business negotiations include materials used to explain goods or services in business negotiations, and this material includes digital materials displayed through a salesperson's mobile terminal 30. The visit phase means the stage of visit in the process of closing a transaction.

When the processor 11 receives the business report data DR from the mobile terminal 30 (Yes in S110), the processor 11 analyzes the received sales report data DR (S120), and obtains the business history data 131A corresponding to the business report data DR in the business history. Register in the database 131 (S130).

As shown in FIG. 5, the business history data 131A includes the same salesperson information as the sales report data DR, customer information, customer organization information, business date and time information, and sales means information. Further, the business history data 131A includes topic information and sales evaluation information.

The topic information is information representing a conversation topic determined by the processor 11 from the business content data. Specifically, the topic information includes information that can identify the product mentioned in the conversation, in other words, the product that is the target of the business activity.

The sales evaluation information is information that indicates the evaluation of the sales staff's business activities by, for example, evaluation points. The evaluation point may be, for example, a numerical value of the estimated operating effect. The sales evaluation information may include evaluation information related to emotions such as speech speed at the time of business negotiations, and evaluation information related to customer reaction and / or degree of interest such as catch ball rate of conversation.

In S120, the processor 11 can analyze the sales content data, determine the conversation topic between the salesperson and the customer, and generate the topic information. Similarly, the processor 11 can analyze the business content data and generate sales evaluation information.

As described above, each time the processor 11 receives the sales report data DR, the processor 11 registers the corresponding sales history data 131A in the sales history database 131, and stores the history information regarding the individual business activities of the plurality of sales staff. It operates so as to accumulate in the business history database 131 in.

In the present embodiment, the storage 13 further stores the participation history data 133 representing the participation status of the customers in a meeting such as a product information session for a plurality of customers. As shown in FIG. 6A, the participation history data 133 is data showing the date and time of the corresponding meeting and the participation status of each customer for each meeting held by the target company. In FIG. 6A, participation / non-participation is represented by 1/0.

The storage 13 further stores browsing history data 134 showing the browsing status of web contents related to the products of the target company provided to the customer from the website. As shown in FIG. 6B, the browsing history data 134 has data representing the browsing status of each customer for each web content provided by the target company through the website for each period. Each customer's access to the web content can be determined by the login procedure on the website or by using cookie technology.

In addition, the processor 11 acquires sales data of the target company from the sales data management system 50 by periodically and repeatedly executing the transaction DB update process shown in FIG. 7, and sells the drug from the target company to the customer organization. It is configured to update the trading database 136 for analysis of. An example of the trading database 136 is shown in FIG. The transaction database 136 is a database representing transaction results and is stored in the storage 13.

When the transaction DB update process shown in FIG. 7 is started, the processor 11 acquires the latest sales data for a predetermined period from the sales data management system 50 through the communication interface 19 (S210). The sales data represents the sales volume (specifically, the number of sales and sales) of the product for each sales act from the target company to the customer in the corresponding period.

Further, the processor 11 acquires the market research data for the same period from the market data management system 60 (S220). The market research data shows the sales of pharmaceutical products in the same category as the products handled by the target company in the entire market.

After that, the processor 11 adds data representing the latest sales volume of each product handled by the target company from the target company to each business partner based on the sales data and market survey data acquired in S210 and S220 in the latest predetermined period. The transaction database 136 is updated so as to be performed (S230).

As shown in FIG. 8, the transaction database 136 has transaction data 136A for each business partner of the target company. The transaction data 136A of each business partner includes product transaction data 136B, which is transaction data of the corresponding product, for each product handled by the target company. The product transaction data 136B of each product includes period transaction data 136D, which is transaction data for each period.

The period transaction data 136D indicates the number of sales, sales, and market share of the corresponding product to the corresponding business partner in the corresponding period. Depending on the number of sales and sales for each period, the group of period transaction data 136D shows the time change of the transaction volume of the corresponding product.

Market share indicates the ratio of the sales of the corresponding product to the corresponding business partner to the sales of the entire market of the product category corresponding to the product. The processor 11 can calculate the market share based on the sales of the entire market specified from the market research data acquired in S220.

Each commodity transaction data 136B includes, in addition to the group of period transaction data 136D, initial transaction data 136C indicating the date when the corresponding commodity is first sold to the corresponding supplier. The initial transaction data 136C is used by the processor 11 to determine that there is no transaction of the corresponding product with the business partner before that date.

In the present embodiment, the processor 11 further executes the model construction process shown in FIG. 9 to obtain a prediction model for predicting the transaction volume Y of the product from the business activity based on the business history database 131 and the transaction database 136. Works to build.

When the model construction process shown in FIG. 9 is started, the processor 11 first selects the calculation target period of the transaction volume Y (S310). The length of the period corresponds to the length of the period handled by each of the period transaction data 136D in the transaction database 136. The length of the period can be, for example, one month.

After that, the processor 11 refers to a group of period transaction data 136D corresponding to the selected calculation target period, and calculates an actual value (that is, an actual measurement value) of the transaction amount Y in the calculation target period (S320). The example of the transaction volume Y referred to here includes sales Y1 as a total sales of a plurality of products to a plurality of business partners of the target company, or a share Y2 of the sales Y1 in the entire market.

After calculating the actual value of the transaction volume Y, the processor 11 reads out a group of business history data 131A during the period for explaining the transaction volume Y (S330). In the following, this period will be referred to as the business activity period. The business activity period for reading the group of business history data 131A is the same period as the calculation target period for the transaction volume Y, or the period before the time corresponding to the time lag until the business activity is reflected in the transaction volume Y. obtain.

After the processing in S330, the processor 11 is a variable related to the business activities of a plurality of sales staff of the target company from the group of the read business history data 131A, and is a plurality of explanatory variables X1, X2, ... The observed value during the business activity period is calculated for each of the above (S340).

The explanatory variables X1, X2, ... Can be, for example, variables representing the sales volume for each combination of the salesperson attribute, the customer attribute, and the business act attribute. Alternatively, the explanatory variables X1, X2, ... Can be variables representing the sales volume for each combination of the salesperson attribute, the customer attribute, the customer organization attribute, and the business act attribute.

The business volume referred to here may be a value obtained by quantifying the amount of business activities in the corresponding combination according to a predetermined definition. A simple example of business volume is the number of sales, that is, the number of executions of a business act. According to the present embodiment in which one business activity is recorded by one business history data 131A, the number of business operations can be specified by counting the business history data 131A. As another example, the business volume may be a value obtained by correcting the number of business operations according to a predetermined rule based on the business evaluation information possessed by the business history data 131A and taking into consideration the business effect.

The salesperson attribute is an attribute of the salesperson defined based on at least one of the salesperson's geographic attribute, demographic attribute, psychographic attribute, and social attribute. The salesperson's geographic attributes can be defined by at least one of the salesperson's work area, residence area, and origin. The demographic attributes of a salesperson can be defined by at least one of gender, age, position, occupation, career, family structure, income, and assets.

A salesperson's psychographic attributes can be defined by at least one of the salesperson's personality, habits, hobbies, thoughts, and life values. The social attributes of a salesperson are, for example, relatives of the salesperson, current and / or past friends of the salesperson, seniors, juniors, bosses, subordinates, colleagues, and affiliated factions in the current and / or past affiliated organization of the salesperson. It can be defined as an attribute related to the relationship between a salesperson (including a student), a teacher-apprentice relationship, and an authority that has a psychological or psychological effect on the salesperson.

The analysis system 10 can have a salesperson attribute database 138 in the storage 13 in order to determine the attributes of each salesperson. The salesperson attribute database 138 shown in FIG. 10A has geographic attributes, demographic attributes, psychographic attributes, and social attributes of the corresponding salespersons as salesperson attribute data representing the attributes of the corresponding salespersons for each salesperson. Has data that describes.

Similarly, the analysis system 10 can have a customer attribute database 139 in the storage 13 in order to determine the attributes of each customer. The customer attribute database 139 shown in FIG. 10B contains data describing the geographic attribute, demographic attribute, psychographic attribute, and social attribute of the corresponding customer as customer attribute data representing the attribute of the corresponding customer for each customer. Have. The attributes of these customers can be defined in the same way as the attributes of the salesperson described above. The customer attribute database 139 can be created in the storage 13 by the processor 11 based on the doctor data acquired from the doctor data management system 70.

That is, the customer attribute is a customer attribute defined based on at least one of the customer (doctor) geographic attribute, demographic attribute, psychographic attribute, and social attribute. Customer organization attributes can be defined by the type of customer organization (general hospital, practitioner, etc.), number of beds, number of doctors, location, and the like.

The business activity attribute can be defined by the attributes of the business means such as "visit", "telephone", and "email" described above. Business activity attributes are further determined by multiple attributes related to the business content, such as the attributes of the product that was the subject of the business activity, the attributes of the explanatory materials used in the sales activity, the evaluation points of the sales activity, and the attributes of the topic in the negotiation. It may be defined.

According to the present embodiment, in order to suppress the number of explanatory variables, for example, for each combination of the salesperson attribute, the customer attribute, and the business act attribute defined by a predetermined range, one sales amount is set as a value. Explanatory variables can be defined. As a result, a plurality of explanatory variables X1, X2, ... Can be defined.

The above-mentioned definitions of the explanatory variables X1, X2, ... Are defined by the first parameter regarding the attributes of the salesperson, the second parameter regarding the attributes of the customer, the third parameter regarding the sales method from the salesperson to the customer, and the salesperson. It includes the idea of defining at least a part of the explanatory variables X1, X2, ... By the fourth parameter regarding the frequency or number of times the business operation is executed to the customer.

The explanatory variables X1, X2, ... Above may further include an explanatory variable Xv regarding the number of times the meeting is attended for each customer or each customer organization in the corresponding period. Similarly, the explanatory variables X1, X2, ... May include the explanatory variables Xw corresponding to the number of times the content is viewed for each customer or each customer organization in the corresponding period. The processor 11 can calculate the observed values of the explanatory variable Xv regarding the number of times the meeting is attended and the explanatory variable Xw corresponding to the number of times the content is viewed by referring to the participation history data 133 and the browsing history data 134 stored in the storage 13.

When the processor 11 calculates the actual value of the transaction volume Y in the calculation target period and the observed values of the explanatory variables X1, X2, ... It is determined whether or not the actual value of the transaction volume Y and the observed values of the explanatory variables X1, X2, ... Have been calculated for the entire period of.

If the processor 11 makes a negative determination in S350, the processor 11 shifts to S310, changes the calculation target period, and further executes the processes of S320 to S340. In this way, the processor 11 calculates the actual value of the transaction volume Y corresponding to the objective variable and the observed value of the explanatory variables X1, X2, ... For each period.

If affirmative judgment is made in S350, the processor 11 samples the objective variable and the explanatory variable for each period to be used for the regression analysis based on the combination of the actual value of the transaction volume Y for each period and the observed value of the explanatory variables X1, X2, ... Generate data (S360).

For example, the processor 11 can convert the actual value of the transaction volume Y for each period into a moving average value, and set this moving average value as the sample value of the objective variable Y. Similarly, the processor 11 may convert the observed values of the explanatory variables X1, X2, ... For each period into moving average values, and set the moving average values as the sample values of the explanatory variables X1, X2, .... it can.

That is, the processor 11 converts the actual value of the transaction volume Y for each period and the observed values of the explanatory variables X1, X2, ... To the moving average value, and uses the corresponding period as sample data for the corresponding period for each period. It is possible to generate sample data consisting of a combination of the moving average value of the transaction volume Y in the above and the moving average value of the explanatory variables X1, X2, ... In the corresponding period.

As another example, the processor 11 does not convert the combination of the actual value of the transaction volume Y for each period calculated in S320 to S340 and the observed value of the explanatory variables X1, X2, ... To the moving average value, but as it is, the sample value. May be used to generate sample data.

After that, the processor 11 constructs a prediction model by regression analysis based on these sample data groups (S370). For example, the processor 11 calculates the appropriate values of the regression coefficients B1, B2, ... In the regression equation Y = f (X1, X2, ...) Based on the sample data group, thereby predicting the prediction model Y = f (X1, X2 ...). , ...) can be constructed. The processor 11 stores the constructed prediction model Y = f (X1, X2, ...) In the storage 13 (S380). After that, the model construction process shown in FIG. 9 is completed.

FIG. 11 conceptually shows a method for constructing a prediction model in S370. According to the example shown in FIG. 11, for each combination of the age group and gender of the sales staff, the age group and gender of the customer (doctor), and the sales means, the explanatory variables X1 and X2 indicating the number of sales in the combination. , ..., XN sample values are prepared, and further, sample values of the objective variable Y indicating the corresponding sales are prepared. Then, by constructing a forecast model from these sample values, a forecast model that can predict sales is constructed from a sales plan defined by a combination of sales staff, customers, and sales means.

Subsequently, the details of the sales plan creation process executed by the processor 11 based on the constructed prediction model will be described with reference to FIG. In this business plan creation process, a business plan of the target company is created based on the forecast model and presented to the target company.

When the sales plan creation process shown in FIG. 12 is started, the processor 11 first reads out the salesperson list and the customer list (S410, S420). The salesperson list is a list of salespersons who perform sales activities for the customers listed in the customer list.

After that, the processor 11 sets a constraint condition regarding the transaction volume Y (S430). The constraint condition is set in the conditional expression f (X1, X2, ...)> D, for example, by receiving the designation of the lower limit D of the transaction volume Y per period from the target company.

The lower limit D may be determined by the processor 11 according to a predetermined rule based on the actual value of the transaction volume Y. For example, the lower limit D may be set to a value that is a predetermined ratio higher than the actual value of the transaction volume Y in the previous month. This constraint condition is set to search for a business plan with the minimum operating cost within the range of business activities in which the transaction volume Y predicted from the prediction model f (X1, X2, ...) Is larger than the lower limit D.

When the processing in S430 is completed, the processor 11 reads out the costs C1, C2, ... Required for performing the business operation corresponding to each explanatory variable X1, X2, ... (S440). The cost Ci is the cost required to carry out the business operation corresponding to the explanatory variable Xi. The cost includes, for example, the monetary cost or the time cost consumed by the business operation per unit, or the cost of integrating them. The variable i takes an integer value from the value 1 to the value N corresponding to the number N of the explanatory variables X1, X2, ..., XN.

After finishing the processing in S440, the processor 11 determines the evaluation function J (X) defined as the sum of the products (Ci × Xi) of the cost Ci and the explanatory variable Xi for the range from the variable i = 1 to i = N. ) = Σ (Ci × Xi) is used to solve the constrained optimization problem to calculate the optimum values of the explanatory variables X1, X2, ... (S450). That is, the processor 11 optimizes the values of the explanatory variables X1, X2, ... That minimize the evaluation function J (X) within the range that satisfies the constraint condition set in S430. Search as a value.

After that, the processor 11 is based on the calculated optimum values of the explanatory variables X1, X2, ..., For each of the salespeople listed in the salesperson list, the corresponding salesperson should be in charge of the customer and the customer per period. A sales plan that proposes the number of sales (that is, business frequency) and a sales means is created (S460), and the created sales plan is output to the target company (S470). After the output, the processor 11 ends the business plan creation process shown in FIG.

The output of the business plan can be realized, for example, by transmitting digital data explaining the business plan from the analysis system 10 to the computer system of the target company. The digital data explaining the business plan can be transmitted to the computer system of the target company, for example, in the form of e-mail.

When the sales support service is provided as a web service, the sales plan creation process shown in FIG. 12 is executed based on web access from the target company's computer system, and even if it is provided as web data to the target company's computer system. Good.

The configuration of the analysis system 10 of the present embodiment has been described above, but according to this analysis system 10, it is possible to predict the transaction volume Y based on the business activity based on the relationship between the salesperson, the customer, and the sales means. .. Then, using this prediction model, it is possible to present a sales plan that can realize effective sales activities to the target company.

Subsequently, a modified example of the above-described embodiment will be described. The present disclosure is not limited to the embodiments described above, and various aspects may be adopted. For example, the model construction process shown in FIG. 9 may be executed for each business partner, for each product, or for each combination of the business partner and the product.

For example, the processor 11 can execute the model construction process shown in FIG. 9 for each business partner. In this case, in S320, the processor 11 can calculate the actual value of the transaction volume Y with the corresponding business partner as the objective variable Y based on the transaction data 136A of the corresponding business partner in the transaction database 136. ..

Further, the processor 11 reads out a group of business history data 131A for the business activity period explaining the transaction volume Y from the group of business history data 131A explaining the business activity to the customer of the corresponding business partner (S330). Can be done.

At this time, the processor 11 sets the time lag until the business activity is reflected in the transaction volume Y, the first transaction date indicated by the initial transaction data 136C of the corresponding business partner, and the start of the business activity to the business partner for the corresponding product. It can be estimated based on the correspondence with the time. Then, the business act period can be set to a period that goes back from the calculation target period of the transaction volume Y by the time corresponding to the estimated time lag.

Further, the processor 11 can calculate the observed values of the explanatory variables X1, X2, ... Regarding the business behavior to the corresponding business partner by the plurality of sales staff of the target company from the group of the read business history data 131A. it can.

Based on the actual values of the transaction volume Y and the observed values of the explanatory variables X1, X2, ..., The processor 11 makes a transaction between the target company and the specific business partner based on the characteristics of the business activities of the sales staff to the specific business partner. A prediction model for calculating the prediction value of the quantity Y can be constructed (S370).

Similarly, the processor 11 can execute the model construction process for each product. That is, the processor 11 calculates the actual value of the transaction volume Y of the corresponding product based on the group of the product transaction data 136B of the corresponding product (S320), and further, it is added to the group of the business history data 131A of the corresponding product. Based on this, it is possible to calculate the observed values of the explanatory variables X1, X2, ... Regarding the business activity of the corresponding product. Then, based on the actual value of the transaction volume Y and the observed values of the explanatory variables X1, X2, ..., The predicted value of the transaction volume Y for the specific product is calculated from the characteristics of the sales activity of the specific product by the sales staff. A predictive model can be constructed (S370).

In addition, the processor 11 executes the contribution output process shown in FIG. 13 in addition to or instead of the business plan creation process to contribute to the transaction volume Y of the explanatory variables X1, X2, ... Sales support data indicating B1, B2, ... May be provided to the target company.

In the contribution output process shown in FIG. 13, the processor 11 selects a business partner and executes a process (S510, S520) for constructing a prediction model of the corresponding business partner for each business partner.

The processor 11 can build a prediction model for each business partner by the above-mentioned method by executing a model building process (see FIG. 9) for each business partner. That is, for each business partner, the prediction model Y = for calculating the predicted value of the transaction volume Y with the business partner from the characteristics of the business behavior of the sales staff to the business partner customer (explanatory variables X1, X2, ..., XN). f (X1, X2, ..., XN) can be constructed.

When the processor 11 executes the model construction process individually for all the business partners and builds the prediction model Y = f (X1, X2, ..., XN) for each business partner (Yes in S530), the explanation is given for each business partner. The computer of the target company obtains the contributions B1, B2, ..., BN of the variables X1, X2, ..., XN to the transaction volume Y, and explains the contributions B1, B2, ..., BN for each business partner. It is transmitted to the system (S540).

With respect to the variables i = 1 to N, the contribution Bi of the explanatory variable Xi to the transaction volume Y is obtained by partially differentiating the prediction model f (X1, X2, ..., XN) of the corresponding business partner with the explanatory variable Xi. (Bi = ∂f (X1, X2, ..., XN) / ∂Xi). As another example, the calculation of the contribution degree Bi may be performed by using the SHAP (Shapley Adaptive exPlanations) or LIMIT (Local Interpretable Model-agnostic Explanations) technique, which is an estimation technique for the contribution degree. According to this technique, a trained machine learning model can be locally approximated by a simple model, and the coefficient of the approximated model can be calculated as a contribution.

The person in charge of the target company estimates the customer who leads to sales and the compatibility between the salesperson and the customer based on the contributions B1, B2, ..., BN for each business partner indicated by the sales support data received through the computer system. You can formulate a business plan based on it. Therefore, a sales support form that provides information on the degree of contribution is useful for improving the quality of corporate activities, as in the above-described embodiment that proposes a sales plan.

As yet another modification, the processor 11 may be configured to execute the model construction process of the modification shown in FIG. According to this model construction process, the processor 11 acquires the activity data of the competitors from the external data management system (S610), and based on the acquired activity data of the competitors, the explanatory variables X1, X2, ... A forecast model for predicting the transaction volume Y of the target company is constructed in the form of including the parameter Xc related to the sales activities of the competitor (S620). The processor 11 stores this prediction model in the storage 13 (S630).

A competitor is a company that provides products related to the products provided by the target company, specifically, pharmaceutical products of the same type as the products provided by the target company. The activity data is data representing at least one of the business activities and transaction volumes of the competitors related to the related drugs.

The parameter Xc, which is defined as one of the explanatory variables X1, X2, ..., Can be a value obtained by scoring the amount of business activity of the competitor in the corresponding period. The parameter Xc may be composed of a plurality of parameters that individually represent the amount of business activity of each competitor.

The processor 11 constructs a prediction model for predicting the transaction volume Y of the target company by including the transaction volume of the competitor, specifically the parameter Xd related to sales or market share, in the explanatory variables X1, X2, ... (S620), and this prediction model may be saved (S630). The parameter Xd, which is defined as one of the explanatory variables X1, X2, ..., Can be a value indicating the market share of each competitor in the corresponding period.

According to these examples, in S620, the predicted value of the transaction volume Y of the target company can be calculated from the explanatory variables related to the business activities of the target company and the explanatory variables related to the sales activity amount and / or the transaction volume of the competitor. The model is built. Therefore, it is possible to calculate the predicted value of the transaction volume (for example, sales) Y of the target company in consideration of the activities of the competing company. According to the sales plan creation process based on the prediction model constructed by this modification, it is possible to present the sales plan of the target company in consideration of the activities of the competitors, which is very useful for improving the sales activities of the target company.

In addition, the analysis system 10 described above may prepare a business history database and a transaction database of competitors in the same manner as the target company, and build a prediction model from a sample data group based on these databases.

However, it is not realistic to prepare a business history database and a transaction database at the same level as the target company for competitors. Therefore, a forecast model of the target company may be constructed in consideration of the activities of the competitors by using the survey panel data on the competitors.

Specifically, the analysis system 10 acquires survey panel data of a plurality of companies, and creates a sample data group for a prediction model based on the survey panel data and the business history database 131 and transaction database 136 of the target company. , Can be configured to build a predictive model.

The survey panel data can be activity data that can identify the characteristics of the business activities of a plurality of competing companies for each period and the amount of transactions with business partners as a plurality of companies. The survey panel data may include activity data of not only competitors but also target companies as a plurality of companies. The survey panel data may be prepared by the operator of the analysis system 10 and stored in the storage 13.

Specifically, the survey panel data includes explanatory variables X1, X2, ... Regarding business activities that can be calculated from the business history database 131 and transaction database 136 of the target company, and objective variables Y related to transactions, and similar explanatory variables V1, V2. ... And the sample value of the objective variable W can be calculated. The explanatory variables V1, V2, ... Can be variables that express the characteristics related to the business activity in a different aspect from the explanatory variables X1, X2, .... The objective variable W can be a variable that expresses the characteristics related to the transaction in a different aspect from the objective variable Y.

In this case, the processor 11 is a plurality of companies calculated from the sample values of the target company's explanatory variables X1, X2, ... And the objective variable Y calculated from the target company's business history database 131 and the transaction database 136, and the survey panel data. Based on the explanatory variables V1, V2, ... Of the above and the sample values of the objective variable W, it is possible to create a sample data group in which these are integrated.

When the survey panel data also includes the activity data of the target company, the explanatory variables X1, X2 ... And the objective variable Y, the explanatory variables V1, V2, ... And the purpose are used by using the data matching technology and the machine learning technology. The correspondence between the variable W and the variable W can be estimated.

Based on this correspondence, as shown in FIG. 15, the processor 11 uses the explanatory variables X1, X2, ... Based on the business history database 131 and the transaction database 136 of the target company, and the sample data group of the objective variable Y as new explanatory variables. It can be converted into a sample data group of X ^* 1, X ^* 2, ... And the objective variable Y ^* . Further, the sample data group of the explanatory variables V1, V2, ... And the objective variable W based on the survey panel data can be converted into the sample data group of the explanatory variables X ^* 1, X ^* 2, ... And the objective variable Y ^*. .. The explanatory variables X ^* 1, X ^* 2, ... And the objective variable Y ^* may be the same variables as the explanatory variables V1, V2, ... And the objective variable W.

In this way, the processor 11 uses the survey panel data to create a sample data group of explanatory variables X ^* 1, X ^* 2, ... Regarding the business activities of the target company and competitors, and the objective variable Y ^* regarding transactions. be able to.

Then, the processor 11 is based on the sample data group of the created explanatory variables X ^* 1, X ^* 2, ... And the objective variable Y ^* related to the transaction, and from the explanatory variables X ^* 1, X ^* 2, ... A prediction model for predicting Y ^* can be constructed.

That is, the processor 11 can execute the model construction process of the modified example shown in FIG. According to the model construction process shown in FIG. 16, the processor 11 uses the above-mentioned method to sample data of explanatory variables X ^* 1, X ^* 2, ... Regarding the business activities of the target company and competitors, and objective variable Y ^* related to transactions. Create a group (S710).

Based on the sample data group created in S710, the processor 11 constructs and stores a prediction model for predicting the objective variable Y ^* related to the transaction from the explanatory variables X ^* 1, X ^* 2, ... (S720, S730). .. This prediction model can be a model for predicting the transaction volume, specifically, sales, as the objective variable Y ^* from the explanatory variables X ^* 1, X ^* 2, ....

The processor 11 can execute, for example, the business plan creation process shown in FIG. 12 by using this prediction model stored in the storage 13.

As a further modification, the processor 11 operates to build a new prediction model based on the latest data, taking into account the information of the past prediction model, assuming that the prediction model is time-varying. It may be (S370, S520, S620, S720).

Specifically, the processor 11 can build a prediction model according to the example shown in FIG. According to FIG. 17, the prediction model f (X_t, φ_t) at time t is defined by the function f (X_t, φ_t) including the explanatory variable X_t and the parameter φ_t at time t as input variables.

The explanatory variable X_t used here means the above explanatory variable X = {X1, X2, ... XN} at time t. The parameter φ_t means the parameter φ at time t. The parameter φ_t uses the function g (X_t-1, φ_t-1) having the explanatory variable X_t-1 of the past time t-1 and the parameter φ_t-1 as input variables, and the equation φ_t = g (X_t-1, It is defined by φ_t-1) + w. w is a noise term that follows a normal distribution. The explanatory variable X_t-1 means the explanatory variable X at the time t-1 before the time t, and the parameter φ_t-1 means the parameter φ at the time t-1.

For example, the function g (X_t-1, φ_t-1) can be a function that follows the prediction model at time t-1. According to this example, the prediction model can be trained to minimize the weighted sum of the errors g () −Y of the prediction model at multiple time points using the function g () and the objective variable Y described above. More generally, the prediction model can be trained to minimize cost functions such as errors defined by g () and Y.

According to this modification, the objective variable Y_t at time t considers not only the explanatory variable X_t at time t but also the explanatory variable X_t_1 temporally earlier than that, using the prediction model f (X_t, φ_t). Calculated as a value. Therefore, according to this modification, it is possible to accurately calculate the predicted value regarding the transaction volume Y even in an environment where the predicted model changes over time.

In the exemplary embodiment of the present disclosure including the modified examples described above, the compatibility between the sales staff and the customer who receives the business, the frequency of the sales activities, the activities of the competitors, etc. are taken into consideration, and the sales activities, sales, etc. It builds a forecast model for forecasting the transaction volume Y and uses it for sales support. Therefore, the structure of the database, the explanatory variables, and the objective variables are not limited to the above-mentioned examples, and various aspects can be adopted as long as the technical ideas of the present disclosure are included.

For example, the technology of the present disclosure is not limited to application to the sales support of pharmaceutical companies. For example, the technology disclosed can be useful for sales support in various industries where customer visits are important, such as automobile sales, real estate sales, or financial services. In the above embodiment, an example of supporting the sales activity of the "product" provided by the company has been described, but the technology of the present disclosure may be used to support the sales activity of the "service" provided by the company. ..

Further, the objective variable is not limited to the transaction volume Y, and various performance evaluation indicators relating to at least one of the goods and services that are the objectives of the business activity can be adopted. The prescription amount may be adopted as a performance evaluation index for business activities related to drugs. The prescription amount is included in the transaction amount Y in a broad sense, but it is an amount linked to the transaction amount Y, and can be said to be an evaluation index related to the transaction amount Y according to the transaction amount Y.

In addition, various performance evaluation indicators may be adopted as objective variables according to the type of goods or services. Examples of performance indicators can include the number of visitors, the number of groups visiting, and the amount of inflow / induction to the website.

The performance evaluation index may be an index obtained by market research, such as the recognition rate of goods or services, the evaluation of consumers for goods or services, and the candidate rate for consideration at the time of purchase. As a further alternative, the performance evaluation index may be an index relating to intimacy with the visitor, and may be, for example, an index represented by the visit time or the visit probability.

The presentation of the business plan is not limited to the simple example described above. The business plan presented may include information that presents the timing of the business activity by the salesperson and at least one of the other parties. For example, the business plan may include information that presents the timing and partner of the corresponding salesperson's business activities for each of the plurality of salespeople. For example, the business plan may include information that presents an action schedule for business activities for each of the plurality of sales staff.

For example, the processor 11 may determine in detail when, where, and to whom a salesperson should sell, and present the sales plan to the target company. In this case, the optimal salesperson action schedule can be presented in consideration of the movement cost of the salesperson.

The processor 11 may create a business plan by obtaining the value of the explanatory variable X that optimizes the sum of the prediction models Y = f (X) at a plurality of time points. When the prediction model is time-varying, not only the optimization for the prediction model Y_t = f_t (X) at one point, but also the sum of the prediction models at multiple time points t, ..., T + T f_t (X) + ... + f_ {t + T} ( It is conceivable to create a business plan by finding the value of the explanatory variable X that optimizes X). The sum may be a weighted sum. That is, the processor 11 may create a business plan by obtaining the value of the explanatory variable X that optimizes the weighted sum of the prediction model Y = f (X) at a plurality of time points. For example, the processor 11 can set constraints on the sum and weight sums in S430.

In addition, some of the configurations of the various embodiments described above may be omitted. At least a part of the configuration of the above embodiment may be added or replaced with the configuration of the other above embodiment. The embodiments of the present disclosure are all aspects contained in the technical idea identified from the wording described in the claims.

1 ... Sales support system, 10 ... Analysis system, 11 ... Processor, 12 ... Memory, 13 ... Storage, 19 ... Communication interface, 30 ... Mobile terminal, 50 ... Sales data management system, 60 ... Market data management system, 70 ... Doctor Data management system, 131 ... Sales history database, 131A ... Sales history data, 133 ... Participation history data, 134 ... Browsing history data, 136 ... Transaction database, 136A ... Transaction data, 136B ... Commodity transaction data, 136C ... Initial transaction data, 136D ... Period transaction data, 138 ... Salesperson attribute database, 139 ... Customer attribute database, DR ... Sales report data.

Claims (13)

The first acquisition department that acquires historical data on business activities by at least one actor,
The second acquisition department that acquires the actual measurement data of the performance evaluation index for at least one of the goods and services that are the purpose of the business activity,
Based on the acquired historical data and the actual measurement data, a construction unit that builds a prediction model for calculating a prediction value related to the performance evaluation index from a plurality of variables related to the business activity, and a construction unit.
Information processing system equipped with. The information processing system according to claim 1.
The performance evaluation index is an information processing system that is an evaluation index related to the transaction volume between the consumer and at least one provider of the goods and services corresponding to the actor, or the transaction volume. The information processing system according to claim 1 or 2.
An information processing system further equipped with a planning unit that creates a sales plan based on the constructed forecast model. The information processing system according to claim 3.
The business plan is an information processing system that includes information that presents the timing of the business activity and at least one of the other parties. The information processing system according to any one of claims 1 to 4.
An information processing system further including an output unit that determines the contribution degree of each of the plurality of variables for explaining the performance evaluation index based on the constructed prediction model and outputs information on the contribution degree. The information processing system according to any one of claims 1 to 5.
The plurality of variables are a first parameter regarding the attributes of the actor, a second parameter regarding the attributes of the business partner, a third parameter regarding the business method from the actor to the business partner, and the business from the actor. An information processing system defined by at least one of the fourth parameters regarding the frequency or number of executions of previous business activities. The information processing system according to claim 6.
The plurality of variables are defined by at least the first and second parameters.
The first and second parameters relate to at least one of the geographic attributes of the corresponding person, the demographic attributes of the corresponding person, the psychographic attributes of the corresponding person, and the attributes of the organization to which the corresponding person belongs. Information processing system that is a parameter. The information processing system according to any one of claims 1 to 7.
The history data is data that includes time information at each execution of the business act together with identification information of the actor, the business destination, and the business method.
The actual measurement data is an information processing system showing a time change of the performance evaluation index. The information processing system according to any one of claims 1 to 8.
The actual measurement data is used as a performance evaluation index for each combination of the organization corresponding to the business partner and the product or service for the purpose of the business act, and the provider of the product or service corresponding to the actor. An information processing system that includes performance indicators for each period related to transactions with the organization and time information at the time of the first transaction. The information processing system according to any one of claims 1 to 9.
The construction unit has the historical data relating to the first business activity, which is at least one of the products and services provided by the first company, as the historical data, and the first performance evaluation index. Provide the measured data of the first performance evaluation index for at least one of the goods and services provided by the first company and at least one of the goods and services related to at least one of the goods and services provided by the first company. The second business act of the second company, which is the business act of at least one of the related goods and services, and the second performance of the second company with respect to at least one of the related goods and services provided by the second company. Information for constructing a prediction model for calculating a prediction value for the first performance evaluation index from the plurality of variables related to the first business activity as the prediction model based on data on at least one of the evaluation indexes. Processing system. The information processing system according to any one of claims 1 to 10.
The business act includes a business negotiation between the actor and the business partner, and the historical data includes information including characteristic data related to the conversation at the time of the business negotiation extracted from the voice at the time of the business negotiation. Processing system. A computer program for operating a computer as a first acquisition unit, a second acquisition unit, and a construction unit in the information processing system according to any one of claims 1 to 11. Information processing method executed by a computer
To obtain historical data of business activities by at least one actor,
Acquiring actual measurement data of performance evaluation indicators for at least one of the goods and services that are the purpose of the business activity,
Based on the historical data and the actual measurement data, a prediction model for calculating a prediction value regarding the performance evaluation index from a plurality of variables related to the business activity is constructed.
Information processing methods including.

Images