JP2022069602A - Sales activity support system, sales activity support method and sales activity support program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a sales activity support system, a sales activity support method and a sales activity support program that support sales activity more effectively.

SOLUTION: A sales activity support system includes a prediction model which has learnt using training data that is a set of data comprising successful/failed results in accomplishing a predetermined objective in user's sales activities, and multiple variables that may correlate with the successful/failed results, in association with each other. The prediction model is used for predicting at least one of the successful/failed results and success probability, for combinations of variables whose successful/failed results are unknown. The sales activity support system further includes a prediction unit 501 that predicts, on the basis of information on a partner candidate in the sales activity, at least one of the successful/failed results and success probability for the partner candidate.

SELECTED DRAWING: Figure 24

COPYRIGHT: (C)2022,JPO&INPIT

Description

The present invention relates to a sales activity support system, a sales activity support method, and a sales activity support program that support a user's sales activities.

In a mature domestic environment, it is foreseen that it will be difficult to secure human resources at the sales floor in the future. Even under such circumstances, the supervisor of sales activities not only maintains and improves business performance, but also meets labor standards in order to secure a standard amount of sales base in the future even if there is a shortage of human resources. It is desired to secure human resources and develop human resources.

Under these circumstances, high-performance people with high grades will become more and more busy, and the difference (difference in sales performance and working hours) with low-performance people who cannot achieve high grades will increase. .. Then, not only is it difficult for the high-performance group to secure their own business hours, but there are also problems such as dissatisfaction due to the concentration of work and the inability to take guidance time even if the low-performance group wants to pass on their know-how. Conceivable.

On the other hand, even low-performance people are dissatisfied with the fact that there is no target (potential customer) for sales, they do not know, their bosses are busy and they are not fully educated, and even if they spend time doing sales activities, no results are obtained. And anxiety may occur.

Therefore, there are various systems that use AI (artificial intelligence) technology represented by prediction models to perform customer management, sales forecasting, know-how analysis (data conversion), etc., and improve the efficiency of sales activities through them. Has been developed.

In relation to sales activity support using AI technology, for example, Patent Document 1 shows an example of a system for predicting the number of sales of products that have not yet been sold. Further, for example, Patent Document 2 describes a system for filtering, selecting, and presenting vendors so as to match customer needs with vendors who are expected to have higher sales success from a group of restricted vendors. Has been done. Further, for example, in Patent Document 3, a list of prospective customers is extracted from existing customers who can propose the purchase of a new product based on the nature of the product, the relationship between the products, the past purchase history, and the like. The system presented as is described.

Japanese Unexamined Patent Publication No. 2000-200260 Japanese Patent Publication No. 2014-521147 Japanese Unexamined Patent Publication No. 2002-334201

In the future, in order to maintain and improve sales performance while observing labor standards amid an increasing shortage of human resources, a sales activity support system that can reduce the burden on high-performance groups and improve the utilization rate of low-performance groups is desired. ..

In order to achieve these in a well-balanced manner and to lead to the sales results of the entire business establishment, simply improving the prediction accuracy is not enough. For example, ease of introduction and use of information provided. It is necessary to increase the utility value as a system, such as improving the ease and verifiability of the effect.

For example, if the information is too complicated when providing the analysis results, there may be a problem that an inexperienced sales person cannot process the information and can not connect to specific sales activities. On the other hand, if there is too little information, it is not possible to identify the partner of the sales activity and it cannot be connected to specific sales activities, or even if the partner of the sales activity can be identified, the basis for identification is unknown. There may be a problem that even if you do sales activities, your approach is weak and it does not lead to results.

In addition, for example, in order to perform marketing and analysis of prospective customers accurately, it is necessary to make full use of not only a lot of existing data such as customer information and sales results in business establishments but also knowledge databases in the world. It is difficult for system users alone to select, collect, and organize data suitable for machine analysis from a wide variety of existing data.

Therefore, an object of the present invention is to provide a sales activity support system, a sales activity support method, and a sales activity support program that can more effectively support a user's sales activities.

The sales activity support system according to the present invention is machine-learned using training data, which is a set of data in which the success or failure of a contract for a product or service provided by a user is associated with a plurality of variables that can correlate with the success or failure of the contract. In addition, the success rate of the contract in the candidate partner is based on the prediction model for predicting the success rate of the contract for the combination of variables whose success or failure of the contract is unknown and the information about the candidate partner of the user's sales activity. A forecasting unit that predicts The training data is generated based on the information including the customer contact information which is the information about the contact with the customer in the user, and the customer contact is provided. The information is characterized by including the date and time of the interview.

Further, the sales activity support method according to the present invention is a training in which an information processing apparatus is a set of data in which a plurality of variables that can correlate with the success or failure of a contract for a product or service provided by a user are associated with each other. Based on a prediction model for predicting the success rate of a contract for a combination of variables whose success or failure is unknown, which is machine-learned using data, and information on potential partners for the user's sales activities. Sales that predict the success probability of a contract in a candidate, obtain the contribution of each of the variables to the success probability, which is specified based on the prediction model, and identify the information about the candidate and the contribution. The information showing the basis of the priority of the activity is output in association with each other, and the training data is generated based on the information including the customer contact information which is the information about the contact with the customer in the user, and the customer contact information is the date and time of the interview. It is characterized by including.

In addition, the sales activity support program according to the present invention provides a computer with training data, which is a set of data in which the success or failure of a contract for a product or service provided by a user is associated with a plurality of variables that can correlate with the success or failure of the contract. Candidate partners based on a prediction model for predicting the success rate of a contract for a combination of variables whose success or failure is unknown, machine-learned using it, and information about potential partners in the user's sales activities. The process of predicting the success probability of the contract in, the process of acquiring the contribution of each of the variables to the success probability, which is specified based on the prediction model, the information about the candidate partner, and the specification based on the contribution. , Information indicating the basis of the priority of sales activities, and the process of outputting in association with each other are executed, and training data is generated based on information including customer contact information which is information about the contact with the customer in the user. , The customer contact information includes the date and time of the interview.

According to the present invention, sales activities can be supported more effectively.

It is a block diagram which shows the structural example of the sales activity support system of 1st Embodiment. It is explanatory drawing which shows the example of the data which the data storage part 11 stores. It is explanatory drawing which shows the example of the training data D1. It is explanatory drawing which shows the example of the trained model. It is a list of coefficients of each variable in the prediction formula of the trained model. It is a graph which shows the coefficient of each explanatory variable specified as a result of learning. It is explanatory drawing which shows the example of the prediction target data set D2. It is explanatory drawing which shows the example of the prediction result with respect to the prediction target data set D2. It is explanatory drawing which shows the example of the sort result of the prediction target data set D2 which attached the prediction result. It is explanatory drawing which shows the example of the partner candidate list D3. It is explanatory drawing which shows the other example of the other party candidate list D3. It is explanatory drawing which shows the display example of the destination candidate list D3. It is explanatory drawing which shows the other example of the other party candidate list D3. It is a flowchart which shows an example of the operation of the sales activity support system of 1st Embodiment. It is a block diagram which shows the structural example of the sales activity support system of 2nd Embodiment. It is explanatory drawing which shows the example of the data which the data storage part 11 stores. It is a block diagram which shows the structural example of the data verification processing part 16. It is explanatory drawing which shows the example of the counterparty candidate list D3 in which the result of a business activity is entered. It is explanatory drawing which shows the verification example of the effect of the other party candidate list D3. It is explanatory drawing which shows the verification example of the effect of the other party candidate list D3. It is explanatory drawing which shows the example of the new training data D1. It is a flowchart which shows an example of the operation of the sales activity support system of 2nd Embodiment. It is a schematic block diagram which shows the configuration example of the computer which concerns on each embodiment of this invention. It is a block diagram which shows the outline of the sales activity support system of this invention.

Embodiment 1.
Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing a configuration example of the sales activity support system of the first embodiment. The sales activity support system shown in FIG. 1 includes a data storage unit 11, a learning unit 12, a prediction unit 13, and an output unit 14.

The data storage unit 11 stores data used in this system. FIG. 2 is an explanatory diagram showing an example of data stored by the data storage unit 11 of the present embodiment. As shown in FIG. 2, the data storage unit 11 of the present embodiment stores at least the training data D1.

The training data D1 is a set of data in which the success or failure of a predetermined purpose in a user's business activity is associated with a plurality of variables that can correlate with the success or failure of the predetermined purpose. The success or failure of the above object is set as an objective variable in the prediction model described later, and a plurality of variables that can correlate with the success or failure of the above purpose are set as explanatory variables in the prediction model described later.

The predetermined purpose in the sales activity of the user in the training data D1 can be freely set by the user. Here, examples of the purpose include contracts for products or services provided by the user (including sales contracts, rental contracts, etc.), making promises for visits to customers, and having customers introduce other people. Will be.

FIG. 3 is an explanatory diagram showing an example of training data D1. The example shown in FIG. 3 is an example of training data D1 when the purchase of a specific product (hereinafter referred to as a target product) is set as the purpose, that is, the objective variable in the user's business activities. As shown in FIG. 3, the data storage unit 11 may store, as training data D1, a plurality of predetermined variables that can correlate with the presence / absence of the purchase in association with the presence / absence of the past purchase of the target product. ..

The training data D1 shown in FIG. 3 includes information indicating Y: "whether or not the target product has been purchased" and customer characteristics such as X1: "age", X2: "gender", X3: "address", X4 :. Information indicating "whether or not married", X5: "annual income", X6: "occupation", X7: "whether or not product A is purchased" and X8: "whether or not product B is purchased" is associated. In FIG. 3, “1” in the Y: “whether or not there is a contract for the target product” column indicates that there is a purchase, and “-1” indicates that there is no purchase. In addition, X2: "1" in the "gender" column represents a woman, and "0" represents a man. Here, the "product A" of X7 and the "product B" of X8 may be, for example, other products related to the target product or the target product. However, in the latter case, it is assumed that the individual is different from the "target product" represented by the explanatory variable. In this way, it is also possible to include the "presence or absence of purchase of the target product" before the purchase or non-purchase of the target product represented by the objective variable in the explanatory variable.

Such training data D1 is obtained in the past from information held by the user, for example, contract information which is information about past contracts, customer information which is information about customers, product information which is information about products, and the like. It can be created by extracting the characteristics of the customer who purchased the target product and the characteristics of the customer who did not purchase the target product. It should be noted that the variables associated with the purchase or absence of the target product can include not only the characteristics of the customer but also the situation at that time (sales representative, weather, time, presence or absence of campaign, etc.).

Although FIG. 1 shows an example in which the data storage unit 11 stores the training data D1, the training data D1 may not be stored in this system but may be stored in another system. In that case, the user or the other system may input the training data D1 as appropriate, or the learning unit 12 described later may acquire the training data D1 from the other system as needed.

Using the training data D1, the learning unit 12 learns a prediction model for predicting the success / failure and success rate of the target for the prediction target data set D2, which is a combination of objective variables whose success / failure of the target is unknown. .. For example, the learning unit 12 may predict only the success or failure of the above-mentioned purpose, may predict only the success probability of the above-mentioned purpose, or may predict both the success or failure of the above-mentioned purpose and the success probability.

The learning method performed by the learning unit 12 is not particularly limited, but various types such as supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning can be considered. An example of a machine learning algorithm is a neural network, which is one of general supervised learning. Further examples include support vector machines, deep learning, Gaussian processes, decision trees, random forests, and the like. Examples of predictive models include linear models, partitioned linear models, regression models, logistic regression models, multiple regression models, and multiple regression models with cases.

The learning unit 12 may learn the prediction model by using, for example, a learning device capable of specifying the contribution of each of the plurality of explanatory variables to the objective variable by machine learning using the training data D1. Further, the learning unit 12 may learn the prediction model by using at least one of sparsity and regularization as a constraint at that time. As an example, the learning unit 12 is one of the learning devices based on the multiple regression analysis with case classification, and uses heterogeneous mixed learning to solve nonlinear and sparse problems with high accuracy in a white box, and is a predictive model. You may study.

FIG. 4 is an explanatory diagram of an example of a trained model. FIG. 4 shows a predicted formula after normalization as an example of a learning model. Further, FIG. 5 is a list of coefficients of each variable in the prediction formula. Further, FIG. 6 is a graph showing the coefficients of each explanatory variable specified as a result of learning. As a result of learning, the learning unit 12 may specify the magnitude (absolute value) of the coefficient of each variable in the model formula as the contribution degree. At this time, the variable having zero contribution may be excluded from the explanatory variables.

When the information about the partner candidate of the sales activity is input, the prediction unit 13 predicts the success / failure or the success probability of the target in the input partner candidate based on the information and the learned prediction model. The prediction unit 13 is input by, for example, creating a prediction target data set D2 which is a combination of explanatory variables to be predicted from information on potential counterparties of sales activities and applying it to a trained prediction model. You may predict the success or failure or success probability of the purpose in the candidate partner.

FIG. 7 is an explanatory diagram showing an example of the prediction target data set D2. In the example shown in FIG. 7, the prediction target data set D2 is associated with the “customer ID” for identifying the destination candidate, and the description in the trained prediction model for the person or the like indicated by the “customer ID” is given. Each value of the variable is registered. More specifically, as the forecast target data set D2 of this example, "X1: age", "X2: gender", "X4: whether married or not", "X5: annual income" are associated with "customer ID". Values are shown for each of the five explanatory variables "X7: whether or not product A has been purchased". There may be a plurality of prediction target data sets D2.

For example, the prediction unit 13 applies a prediction model to each of such combinations of explanatory variables associated with the customer ID (prediction target data set D2), and the destination candidate indicated by the customer ID. Predict the success or failure or success rate of the purpose in.

For example, the prediction unit 13 may acquire information about a destination candidate from customer information or the like held by the user. In that case, the existing customer of the user is regarded as a candidate for the other party. Further, the destination candidate is not limited to the existing customer, and for example, the user can input information about the destination candidate each time a prediction is made.

FIG. 8 is an explanatory diagram showing an example of a prediction result for the prediction target data set D2 shown in FIG. 7. In the example shown in FIG. 8, as the prediction result, the score output from the prediction model when each of the prediction target data sets D2 is applied to the prediction model is shown. The score corresponds to the target success probability.

Further, the prediction unit 13 may predict the target success probability and acquire the contribution of each of the plurality of explanatory variables used for deriving the success probability. These contribution rates can be obtained from the learning unit 12. In that case, the learning unit 12 may specify and output the contribution rate based on the coefficient of each explanatory variable used in the prediction formula held as the model parameter.

Further, the prediction unit 13 is a case where the prediction model is a case-wise discriminant model (for example, a piecewise linear model, a case-classified multiple regression model, etc.) including a portal function for classifying explanatory variables according to their values. , The success probability may be predicted, and the case classification conditions used for deriving the success probability and the contribution of each of the plurality of explanatory variables may be obtained. The case classification condition and the contribution rate can be obtained from the learning unit 12. In that case, the learning unit 12 may output the case classification condition held as a model parameter, and specify and output the contribution rate based on the coefficient of each explanatory variable used in the prediction formula for each condition. ..

Based on the prediction result of the prediction unit 13, the output unit 14 outputs the information of the partner candidate to which the sales activity is prioritized or the information of the partner candidate including the priority of the sales activity.

For example, as shown in FIG. 9, the output unit 14 may sort the prediction target data set D2 based on the score and select a destination candidate (customer ID in this example) to be provided to the user. FIG. 9 is an explanatory diagram showing an example of the sort result of the prediction target data set D2 together with the prediction result. The output unit 14 may convert the score (success probability) of the partner candidate selected in this way into the priority of the sales activity to create the partner candidate list D3 as shown in FIG. FIG. 10 is an explanatory diagram showing an example of the destination candidate list D3. In addition, in FIG. 10, the "recommendation degree" for the sales staff as the priority of the sales activity is displayed together with the information on the partner candidate. The information about the destination candidate included in the destination candidate list D3 is not particularly limited as long as it is information that the receiving user or sales staff can identify the destination candidate. In the example shown in FIG. 10, "customer ID", "name", "age" and "gender" are included as the information regarding the candidate partner. In addition, the higher the number of black stars, the higher the degree of recommendation. In this example, after converting the success probability into five levels of recommendation, a partner candidate list D3 is created, which is presented in order from the customer with the highest success probability. The destination candidate list D3 does not necessarily have to be sorted in order of priority of sales activities. This is because if the destination candidate list D3 contains the priority information, the user can sort the information.

At this time, the output unit 14 may select a destination candidate whose predicted success probability satisfies a predetermined condition and create a destination candidate list D3.

Further, as shown in FIG. 11, the output unit 14 gives priority (presented at the top) to the partner candidate whose predicted success probability satisfies a predetermined condition, as the partner candidate has a higher success probability. You may create and output a partner candidate list D3 that includes information about the partner candidate and information showing the basis of ranking or priority of sales activities. At this time, the output unit 14 includes, as information indicating the basis of the above-mentioned order or priority, information about a variable having a large contribution to the success probability of the selected partner candidate for each of the selected partner candidates. The candidate list D3 may be created and output. In other words, the output unit 14 provides the user with a destination candidate list D3 containing information indicating the grounds for predicting that the other party is highly interested in the purpose (for example, a product) for each of the other party candidates. offer. At that time, the display mode of the information regarding these variables may be different according to a predetermined condition.

For example, when the contribution presented as the basis is a positive contribution, that is, an explanatory variable having a positive correlation with the objective variable, the output unit 14 indicates that the explanatory variable is a numerical variable and the value is the training data D1. It may be highlighted if it is larger than the average of or if it is a binary variable and its value is 1. On the other hand, in the case of an explanatory variable having a negative contribution to the objective variable, that is, the explanatory variable is a numerical variable and its value is smaller than the average of the training data D1, or it is a binary variable. It may be highlighted when the value is 0. For example, in FIG. 12, as an example of highlighting, the values of explanatory variables satisfying the above conditions are shaded.

Further, when the prediction model used for prediction is a multiple regression discrimination model with case classification, the output unit 14 ranks each case classification condition or grounds the priority of sales activities as shown in FIG. You may create and output a list that presents information indicating. When the contribution of the explanatory variables differs depending on the case classification conditions, it is easier for the viewer to understand if the information of the explanatory variables with a high contribution degree is classified and presented according to the case classification conditions.

Further, the output unit 14 can also create a destination candidate list D3 for each person (sales staff) who conducts sales activities. In that case, for example, each time the output unit 14 selects a higher-ranked partner candidate from the prediction result, the output unit 14 distributes the selected partner candidate to one of the sales staff members, thereby listing the partner candidate for each sales staff. May be created.

Alternatively, the characteristics of the sales staff are included in a plurality of variables of the training data D1 used for learning, and the success or failure or success of the purpose in the sales staff candidate based on the information about the sales staff in the prediction unit 13 and further. The probability may be predicted, and the output unit 14 may create a partner candidate list for each sales staff based on the result. If the sales staff have duplicate destination candidates, the output unit 14 may be adjusted so that it is included in the list of only one sales staff.

Further, as shown in FIG. 13, the output unit 14 may create and output a destination candidate list D3 including an entry field for inputting the result of the sales activity. At this time, the aggregation function may be added to the entry field in the destination candidate list D3. That is, the output unit 14 may create and output a destination candidate list D3 including an entry field and a tabulation function of the entry field. Therefore, the output unit 14 can also create a destination candidate list D3 in the format of spreadsheet software, for example. Further, the output unit 14 may output, for example, the destination candidate list D3 including the entry field to the screen of a terminal or the like possessed by a person who conducts sales activities. Then, the output unit 14 can accept the input to the entry field on the screen, perform the aggregation, and further output the aggregation result. The method of accepting input in the entry field and the method of outputting the aggregated result are not limited to the above.

In the list of potential destinations illustrated using FIG. 13, as an example, not only the "result" column showing the result of conducting sales activities using the forecast results, but also the impressions of the sales staff who conducted sales activities are shown. It shall include the "user impression" column to be shown. However, it is not limited to this configuration.

Next, the operation of this embodiment will be described. FIG. 14 is a flowchart showing an example of the operation of the sales activity support system of the present embodiment. In the example shown in FIG. 14, first, the learning unit 12 learns the prediction model using the training data D1 (step S11).

Next, the prediction unit 13 predicts the success probability of the purpose of the sales activity in the partner candidate based on the information about the partner candidate of the sales activity and the learned prediction model (step S12). As described above, the prediction unit 13 may create the prediction target data set D2 from the information regarding the partner candidate of the sales activity, and predict the success probability of the sales activity for the prediction target data set D2. The prediction unit 13 may predict the success or failure of the sales activity instead of the success probability of the sales activity.

Next, the output unit 14 outputs the destination candidate list D3 as the destination candidate information including the priority of the sales activity or the priority of the sales activity based on the result of the prediction by the prediction unit 13. (Step S13). The output unit 14 creates and outputs the destination candidate list D3 as described above based on the prediction result. The output unit 14 can also hold the created destination candidate list D3 and output the held destination candidate list D3 according to a download request from the user.

As described above, in the present embodiment, the success / failure or success probability of the purpose of the sales activity for the partner candidate is predicted by using the prediction model learned by using the training data D1, and the sales activity is based on the result. Outputs information about potential partners, including prioritized or sales activity priorities. Therefore, the sales staff can preferentially visit the other party with a high probability of success based on the information output by this system. As a result, not only the efficiency of sales activities can be improved, but also the amount of activities of the entire organization and the improvement of business performance can be expected along with the efficiency.

For example, according to the present embodiment, sales activities that have been personalized can be made more efficient by utilizing AI, so that the face-to-face time of sales staff can be increased, and the experience value can be improved accordingly. The effect is expected. As a result, it can be expected that inexperienced sales staff will be able to work immediately and improve their motivation.

Further, according to the present embodiment, since the information including the grounds for the prediction result is provided, the sales staff can use it for the examination of the sales policy.

In addition, by adding an entry field for inputting the results of sales activities to the information to be output, the burden on the user side for totaling the results of sales activities can be reduced, and the effect can be easily measured. Can be done.

Embodiment 2.
Next, a second embodiment of the present invention will be described. FIG. 15 is a block diagram showing a configuration example of the sales activity support system of the second embodiment. The sales activity support system shown in FIG. 15 is different from the first embodiment shown in FIG. 1 in that it includes a user-owned information acquisition unit 15 and a data verification processing unit 16.

The user-owned information acquisition unit 15 inputs (acquires) the user-owned information D0, which is the information possessed by the user. For example, the user-owned information acquisition unit 15 may input information about a contract for a product or service handled by the user, information about a customer, or information about a product or service as user-owned information D0. The user-owned information acquisition unit 15 may input specific information among these information. For example, the user-owned information acquisition unit 15 uses the user-owned information D0 as specific information among information related to contracts for products or services handled by the user, specific information among information about customers, and information related to products or services. You may enter specific information or a combination thereof.

An example of information about a contract for a product or service handled by a user is contract history information, which is a history of information about existing contract details, that is, contract information related to all products or services (for example, contract date, contractor (customer)). , Contracted goods or services, options, branch in charge at that time, sales representative, etc.). In addition, as an example of information about a customer, customer information which is basic information about a user's customer (for example, gender, age, family structure, branch office in charge, sales representative, place of employment, annual income, product usage information of other companies, etc.) can be mentioned. Be done. Further, as an example of information about a product or service, the content of the product or service handled by the user (for example, price, type, feature, option, etc.) can be mentioned.

In addition to the above, the user-owned information acquisition unit 15 may use the user-owned information D0 as customer contact information, which is information regarding the contact with the customer such as the date and time of the interview and the content of sales activities, and the attributes of the sales staff. You may enter the person in charge information indicating the above. Further, the user-owned information acquisition unit 15 displays the user-owned information on the partner candidate list D3 (including the partner candidate list D3 in which the sales person inputs the result of the sales activity in the entry field) output by the output unit 14. It may be input as D0.

The user-owned information acquisition unit 15 is not limited to directly inputting the above information from the user. The user-owned information acquisition unit 15 can also acquire, for example, the above-mentioned information about the user stored in another system. Even in such a case, the system treats the acquired information as user-owned information D0. That is, the user-owned information D0 may be any information that the user possesses or manages as his / her own information.

The data verification processing unit 16 verifies the information input by the user-owned information acquisition unit 15 and the information output by the output unit 14. At that time, the data verification processing unit 16 can store the information processed so that the system can be easily used in the data storage unit 11.

FIG. 16 is an explanatory diagram showing an example of data stored by the data storage unit 11 of the present embodiment. As shown in FIG. 16, the data storage unit 11 of the present embodiment stores at least the user-owned information D0 and the training data D1.

Further, FIG. 17 is a block diagram showing a configuration example of the data verification processing unit 16. As shown in FIG. 17, the data verification processing unit 16 may include a training data creation unit 161, a prediction target data set creation unit 162, and an effect verification unit 163. The data verification processing unit 16 does not have to include all of them, and may include, for example, any one of them.

The training data creation unit 161 creates training data D1 from the user-owned information D0. The training data creation unit 161 creates training data D1 by selecting or newly extracting a predetermined feature amount from the user-owned information D0, for example, based on a predetermined data structure of the training data D1. At this time, the training data creation unit 161 may construct one virtual database by concatenating the above information input as the user-owned information D0 based on the customer's identifier, the sales representative's identifier, and the like.

Here, the predetermined feature amount may be the value of the item (variable) included in the user-owned information D0 itself, or may be processed from the value of the item included in the user-owned information D0. .. In the former case, for example, the system administrator specifies the item in advance, so that the feature quantity is selected. In the latter case, for example, the system administrator specifies in advance the item to be processed and the processing method for that item (general statistical processing such as four-rule operation, average, variance, etc., conversion to the corresponding character string or value, etc.). By applying the specified processing method to the specified item, it is extracted as a new feature amount. It is also possible to use information obtained from the outside during processing.

Then, the training data creation unit 161 performs, for example, selection or new extraction of a predetermined feature amount as described above based on the information in the virtual database, and is related to the success or failure of the target and the success or failure. Create a set of data consisting of multiple variables. Here, the set of created data is used as the prototype of the training data D1. Then, the training data creation unit 161 adds items, complements data, processes data, and data based on the data structure of training data D1 for the created data set (prototype of training data D1). The final training data D1 may be created by at least one of invalidation and deletion of data.

An example of adding an item is adding a variable that indicates statistical information. Further, as an example of data complementation, data in which a value is not registered among items may be complemented based on the value of another item, information obtained from the outside, or the like. Further, as an example of data processing, conversion of character information into a numerical variable or a binary variable can be mentioned. Further, as an example of data invalidation, invalidation of information older than a certain level based on an update date or the like can be mentioned. Examples of data deletion include deleting a data set (a combination of variables related to the success or failure of a certain purpose) based on information older than a certain level based on the update date or the like.

The prediction target data set creation unit 162 creates the prediction target data set D2 from the user-owned information D0. For example, the prediction target data set creation unit 162 sets all existing customers as potential destinations, collects information corresponding to the trained explanatory variables of the prediction model for each customer from the user-owned information D0, and predictable data. Set D2 may be created.

For example, the effect verification unit 163 acquires the counterparty candidate list D3 in which the result of the sales activity is entered, and evaluates the counterparty candidate list D3 from the result of the sales activity. Further, the effect verification unit 163 creates and outputs the effect verification information D4 indicating the evaluation result.

FIG. 18 is an explanatory diagram showing an example of a partner candidate list D3 in which the results of sales activities are entered. As shown in FIG. 18, the effect verification unit 163 is a destination candidate list D3 including an entry field for inputting the result of the sales activity created by the output unit 14, and then the user fills the entry field. Even if the partner candidate list D3 in which the result of the activity is input is collected (acquired) and the effect of the partner candidate list D3 is verified based on the result of the sales activity entered in the partner candidate list D3. good. The method of acquiring the results of sales activities is not limited to the above. The result of the sales activity can be obtained from, for example, the destination candidate list D3 which is the user-owned information D0, the contract history information, or the customer contact information. Further, for example, when the output unit 14 has acquired the result of the sales activity for aggregation, it is possible to obtain the result of the sales activity from the output unit 14. The data storage unit 11 may store the result of the business activity thus obtained in association with at least one of the predicted success / failure of the purpose and the success probability. For example, the data storage unit 11 may store the destination candidate list D3 including the prediction result and the result of the sales activity.

At this time, the effect verification unit 163 may evaluate the partner candidate list D3 for each attribute of the person who has performed the sales activity based on the result of the sales activity and the information about the person who has performed the sales activity. 19 and 20 are explanatory views showing an example of verification of the effect of the destination candidate list D3 by the effect verification unit 163.

For example, as shown in FIG. 19, the effect verification unit 163 adds information on the sales staff (user) who has utilized the sales position candidate list D3 to the customer candidate list D3 including the results of sales activities. Then, the effect verification unit 163 aggregates and evaluates the results of the sales activities entered in the entry field of the partner candidate list D3 for each segment of user information (for example, years of joining the company). At this time, as shown in FIG. 20, the effect verification unit 163 compares the obtained aggregated results with the results of the sales activities of the sales staff who belong to the same segment and do not utilize the destination candidate list D3. Therefore, the effect of the destination candidate list D3 may be evaluated. The effect verification unit 163 may create and output the effect verification information D4 as shown in FIG. 20, for example.

According to the example shown in FIG. 20, the increase rate of the number of proposals and the number of contracts is higher in the sales staff who have been in the company for less than 5 years than the sales staff who have been in the company for 5 years or more, and the effect of utilizing the partner candidate list D3 is effective. You can see that it is big.

Further, the effect verification unit 163 not only verifies the effect of the partner candidate list D3 but also presents it in the partner candidate list D3 based on the information such as the result of the sales activity obtained after presenting the partner candidate list D3. The priority or priority of the partner candidate, the prediction result on which the priority is given, the prediction model derived from the prediction result, and the training data D1 used for the learning may be reviewed.

For example, the effect verification unit 163 may add a variable determined to have a high correlation with the success or failure of the target to the explanatory variable of the training data D1 based on the result of parsing the user's impression. In the example shown in FIG. 20, since it can be determined that "the number of days elapsed since the previous purchase" has a high correlation with the success or failure of the target, the effect verification unit 163 describes the "number of days elapsed since the previous purchase" as the training data D1. The decision to add to the variable or the change of the data structure of the training data D1 may be made.

When the effect verification unit 163 is determined or changed, the training data creation unit 161 creates new training data D1 according to the data structure of the new training data D1. Note that FIG. 21 is an explanatory diagram showing an example of new training data D1 created based on the determination or modification of the effect verification unit 163. In the example shown in FIG. 21, "X8: number of days elapsed since the previous purchase" is newly added as a variable that may be related to the success or failure of the target.

Even if the training data creation unit 161 does not make a decision or change in the effect verification unit 163, the training data creation unit 161 appropriately bases on newly acquired information such as the results of sales activities obtained after presenting the partner candidate list D3. It is preferable to add training data D1 to improve the accuracy of the predictive model.

The learning unit 12 may learn the prediction model at the timing when the data structure of the training data D1 is changed or a predetermined amount of new training data D1 is added. The learning timing of the prediction model is not limited to the above, and may be performed according to the instruction of the system administrator or may be performed periodically.

Next, the operation of this embodiment will be described. FIG. 22 is a flowchart showing an example of the operation of the sales activity support system of the present embodiment. In the example shown in FIG. 22, first, the user-owned information acquisition unit 15 acquires the user-owned information D0 (step S21).

Next, the training data creation unit 161 creates training data D1 from the user-owned information D0 (step S22).

Next, the learning unit 12 learns the prediction model using the training data D1 (step S23).

Next, the prediction target data set creation unit 162 creates the prediction target data set D2 based on the user-owned information D0 (step S24).

Next, the prediction unit 13 applies a trained prediction model to the prediction target data set D2 to predict the success probability of the sales activity of the destination candidate (customer) indicated by the prediction target data set D2 (). Step S25). Similar to the first embodiment, the prediction unit 13 may predict the success or failure of the sales activity instead of the success probability of the sales activity.

Next, the output unit 14 creates and outputs the destination candidate list D3 based on the result of the prediction by the prediction unit 13 (steps S26 and S27).

Next, the effect verification unit 163 acquires information indicating the effect (success or failure of sales activity) of the destination candidate list D3 output by the output unit 14, and verifies the effect (step S28). In step S28, the user-owned information acquisition unit 15 acquires the user-owned information after presenting the destination candidate list D3, so that the effect verification unit 163 determines the effect of the destination candidate list D3 (success or failure of sales activities). Information indicating that may be obtained.

Next, the effect verification unit 163 creates the effect verification information D4 showing the effect verification result (step S29). Further, the effect verification unit 163 reviews the data structure of the training data D1 (step S30). Then, the process returns to step S21, and a series of processes are repeated.

According to the present embodiment, in response to the data provided by such a user, a list of potential recipients is created and provided, and the results of actual sales activities based on the list are acquired to verify the effect. It can be fed back to the user at the time of information D4, the creation of the next list, the learning of the model, and the like. Therefore, it is possible not only to improve the prediction accuracy, but also to reduce the burden of data preparation on the user side and to support the measurement of the effect of introducing this system.

Further, FIG. 23 is a schematic block diagram showing a configuration example of a computer according to each embodiment of the present invention. The computer 1000 includes a CPU 1001, a main storage device 1002, an auxiliary storage device 1003, an interface 1004, a display device 1005, and an input device 1006.

The server and other devices included in the sales activity support system of each of the above-described embodiments may be mounted on the computer 1000. In that case, the operation of each device may be stored in the auxiliary storage device 1003 in the form of a program. The CPU 1001 reads a program from the auxiliary storage device 1003, deploys it to the main storage device 1002, and performs a predetermined process in each embodiment according to the program. The CPU 1001 is an example of an information processing unit that operates according to a program. In addition to the CPU (Central Processing Unit), for example, an MPU (Micro Processing Unit), an MCU (Memory Control Unit), a GPU (Graphics Processing Unit), etc. May be provided.

Auxiliary storage 1003 is an example of a non-temporary tangible medium. Other examples of non-temporary tangible media include magnetic disks, magneto-optical disks, CD-ROMs, DVD-ROMs, semiconductor memories, etc. connected via the interface 1004. Further, when this program is distributed to the computer 1000 by a communication line, the distributed computer may deploy the program to the main storage device 1002 and execute a predetermined process in each embodiment.

Further, the program may be for realizing a part of a predetermined process in each embodiment. Further, the program may be a difference program that realizes a predetermined process in each embodiment in combination with another program already stored in the auxiliary storage device 1003.

Interface 1004 sends and receives information to and from other devices. In addition, the display device 1005 presents information to the user. Further, the input device 1006 accepts the input of information from the user.

Further, depending on the processing content in the embodiment, some elements of the computer 1000 may be omitted. For example, if the computer 1000 does not present information to the user, the display device 1005 may be omitted. For example, if the computer 1000 does not accept information input from the user, the input device 1006 can be omitted.

In addition, some or all of the components of each of the above embodiments are implemented by a general-purpose or dedicated circuit (Circuitry), a processor, or a combination thereof. These may be composed of a single chip or may be composed of a plurality of chips connected via a bus. Further, a part or all of each component of each of the above-described embodiments may be realized by a combination of the above-mentioned circuit or the like and a program.

When a part or all of each component of each of the above embodiments is realized by a plurality of information processing devices, circuits, etc., the plurality of information processing devices, circuits, etc. may be centrally arranged or distributed. It may be arranged. For example, the information processing device, the circuit, and the like may be realized as a form in which each is connected via a communication network, such as a client-and-server system and a cloud computing system.

Next, the outline of the present invention will be described. FIG. 24 is a block diagram showing an outline of the sales activity support system of the present invention. The sales activity support system 500 shown in FIG. 24 includes a prediction unit 501.

The prediction unit 501 (for example, the prediction unit 13) learns using training data, which is a set of data in which the success or failure of a predetermined purpose in a user's business activity is associated with a plurality of variables that can correlate with the success or failure of the purpose. Based on a prediction model for predicting at least one of the success or failure of the target and the probability of success for a combination of variables whose success or failure is unknown, and information on potential partners for sales activities. Predict at least one of the success or failure of the objective and the probability of success in the candidate.

With such a configuration, for example, by conducting sales activities using the prediction results for potential counterparties, the efficiency of sales activities can be balanced, for example, the burden on the high performance layer can be reduced and the utilization rate of the low performance layer can be improved. Since both can be realized, more effective support can be provided.

It should be noted that each of the above embodiments can also be described as described in the following appendix.

(Appendix 1) The success or failure of the purpose is unknown, which was learned using training data, which is a set of data in which the success or failure of a predetermined purpose in the user's business activities is associated with a plurality of variables that can correlate with the success or failure of the purpose. Based on the prediction model for predicting at least one of the success / failure and success probability of the target for the combination of variables of, and the information about the potential partner of the sales activity, the success / failure and success probability of the target in the candidate partner. A sales activity support system characterized by having a prediction unit that predicts at least one of them.

(Appendix 2) The sales activity support system according to Appendix 1, which includes a training data storage unit for storing training data and a model learning unit for learning a prediction model using training data.

(Appendix 3) Addendum 1 or 2 provided with an output unit that outputs information on potential counterparties, including the priority of sales activities or the priority of sales activities, based on the result of prediction by the prediction unit. The listed sales activity support system.

(Appendix 4) A training data storage unit for storing training data, a model learning unit for learning a prediction model using training data, and a priority for sales activities based on the results of prediction by the prediction unit. The sales activity support system according to Appendix 1, which includes an output unit that outputs information on potential counterparties including the priority of the sales activity.

(Appendix 5) The model learning unit learns the prediction model using a learning device that can specify the contribution of each of the multiple variables to the success or failure of the target by machine learning, and the prediction unit is the partner of the sales activity. Based on the information about the candidate and the prediction model, the success probability of the target in the partner candidate is predicted, and the contribution of each of the plurality of variables used for deriving the success probability is acquired, and the output unit succeeds. A list of potential partners whose probability meets a predetermined condition, the higher the probability of success, the higher the priority, and the information about the candidate and the information showing the basis of the ranking or priority of the partner. The sales activity support system according to Appendix 4, which outputs a list associated with information about variables having a large contribution to the success probability of the previous candidate.

(Appendix 6) The prediction model is a discriminant model with case classification, and the prediction unit predicts the success probability of the target in the partner candidate based on the information about the partner candidate of the sales activity and the prediction model, and also The case classification condition used for deriving the success probability and the contribution of each of a plurality of variables are acquired, and the output unit is a list of potential partners whose success probability satisfies a predetermined condition, and the partner has a high success probability. Information about the other party candidate, which is prioritized as the first candidate, and information about a variable that has a large contribution to the success probability of the other party candidate as information showing the basis of the ranking or priority, depending on the case classification condition. The sales activity support system according to Appendix 4 or Appendix 5 that outputs a list associated with the classified information.

(Appendix 7) The model learning unit is the sales activity support system according to any one of Appendix 2, 4-6, which learns a predictive model by using at least one of sparsity and regularization as a constraint.

(Appendix 8) The output unit is a sales activity support system according to any one of Appendix 3 to Appendix 7 that creates and outputs a list for each person who conducts sales activities.

(Appendix 9) The plurality of variables of the training data include variables showing the characteristics of the person who has performed the sales activity for the purpose, and the prediction department performs the sales activity with the information about the potential partner of the sales activity. The sales activity support system according to Appendix 8, which predicts at least one of the success or failure of the purpose and the success probability of the target candidate for each person who conducts sales activities based on the information about the person and the prediction model.

(Supplementary Note 10) The sales activity support system according to any one of Supplementary note 1 to Supplementary note 9, further comprising a storage unit that stores the result of the sales activity in association with at least one of the predicted success / failure and success probability.

(Appendix 11) The sales activity support system according to Appendix 10, which includes an evaluation unit that verifies the effect of the list from the results of sales activities and outputs the verification results.

(Appendix 12) The sales activity described in Appendix 11 evaluates the effect of the list for each attribute of the person who conducted the sales activity based on the result of the sales activity and the information about the person who performed the sales activity. Support system.

(Appendix 13) A training data creation unit for creating training data is provided, and the training data creation department updates the training data based on the results of the sales activities. Support system.

(Appendix 14) A user-owned information acquisition unit that acquires information possessed by the user and a training data creation unit that creates training data from the input information are provided, and the training data creation unit is predetermined. The sales activity support system according to any one of Appendix 1 to Appendix 12 for creating training data by selecting or newly extracting a predetermined feature amount from the input information based on the data structure of the training data.

(Appendix 15) The user-owned information acquisition unit acquires at least information on contracts for products or services handled by the user, information on customers, and information on products or services as information held by the user, and training data. Based on the acquired information, the creation unit constructs a set of data consisting of multiple variables related to the success or failure of the target, adds items to the constructed data set, and complements the data. , The sales activity support system according to Appendix 14, which creates training data by processing data, invalidating data, and deleting data at least one of them.

(Appendix 16) The information processing apparatus has been trained using training data, which is a set of data in which the success or failure of a predetermined purpose in a user's business activity is associated with a plurality of variables that can correlate with the success or failure of the purpose. A purpose in a potential partner based on a prediction model for predicting at least one of the success or failure of the target and the probability of success for a combination of variables whose success or failure is unknown, and information about potential partners for sales activities. A sales activity support method characterized by predicting at least one of success or failure and success probability.

(Appendix 17) A purpose trained on a computer using training data, which is a set of data in which the success or failure of a predetermined purpose in a user's business activities is associated with a plurality of variables that can correlate with the success or failure of the purpose. A prediction model for predicting at least one of the success / failure and success probability of the target for a combination of variables whose success / failure is unknown, and the success / failure of the purpose in the partner candidate based on the information about the partner candidate of the sales activity. And a sales activity support program to execute the process of predicting at least one of the success probabilities.

Although the present invention has been described above with reference to the present embodiments and examples, the present invention is not limited to the above embodiments and examples. Various changes that can be understood by those skilled in the art can be made within the scope of the present invention in terms of the configuration and details of the present invention.

The present invention can be suitably applied to any type of business and purpose as long as it is a user who conducts business activities.

11 Data storage unit 12 Learning unit 13 Prediction unit 14 Output unit 15 User-owned information acquisition unit 16 Data verification processing unit 161 Training data creation unit 162 Prediction target data set creation unit 163 Effect verification unit 1000 Computer 1001 CPU
1002 Main storage device 1003 Auxiliary storage device 1004 Interface 1005 Display device 1006 Input device 500 Sales activity support system 501 Prediction unit

Claims (8)

The success or failure of the contract is unknown, which is machine-learned using training data that is a set of data in which the success or failure of the contract of the product or service provided by the user is associated with a plurality of variables that can correlate with the success or failure of the contract. Predict the success probability of the contract in the customer candidate based on the prediction model for predicting the success probability of the contract for the combination of the variables and the information about the partner candidate of the sales activity of the user. Prediction department and
An acquisition unit that acquires the contribution of each of the variables to the success probability, which is specified based on the prediction model.
It is provided with an output unit that outputs information related to the destination candidate and information indicating the basis of the priority of the sales activity, which is specified based on the contribution degree, in association with each other.
The training data is generated based on information including customer contact information, which is information about the contact of the user with the customer.
The customer contact information is a sales activity support system that includes the date and time of the interview. The sales activity support system according to claim 1, wherein the output unit outputs information indicating the basis of the priority in different display modes according to predetermined conditions. The sales activity support system according to claim 1 or 2, wherein the output unit outputs information about the other party candidate and information showing the grounds in association with each other for each person who performs the sales activity. The plurality of variables of the training data include variables indicating the characteristics of the person performing the sales activity.
Based on the information about the other party candidate, the information about the person who carries out the sales activity, and the prediction model, the prediction unit determines the success probability of the contract in the other party candidate for each person who carries out the sales activity. The sales activity support system according to any one of claims 1 to 3 to be predicted. A user-owned information acquisition unit that acquires user-owned information owned by the user, including the customer contact information, and a user-owned information acquisition unit.
It is provided with a training data generation unit that generates the training data based on the user-owned information.
The training data generation unit selects or newly extracts a predetermined feature amount from the user-owned information based on a predetermined training data data structure, and generates the training data from claim 1 to claim. The sales activity support system described in any one of 4. The business according to claim 5, wherein the user-owned information acquisition unit acquires at least information about a contract for a product or service handled by the user, information about a customer, and information about the product or service as the user-owned information. Activity support system. The computer
The success or failure of the contract is unknown, which is machine-learned using training data that is a set of data in which the success or failure of the contract of the product or service provided by the user is associated with a plurality of variables that can correlate with the success or failure of the contract. Based on the prediction model for predicting the success probability of the contract for the combination of the variables and the information about the partner candidate of the sales activity of the user, the success probability of the contract in the partner candidate is predicted. ,
Obtain the contribution of each of the variables to the success probability identified based on the prediction model.
Information about the destination candidate and information indicating the basis of the priority of the sales activity, which is specified based on the contribution, are output in association with each other.
The training data is generated based on information including customer contact information, which is information about the contact of the user with the customer.
The customer contact information is a sales activity support method including the date and time of the interview. On the computer
The success or failure of the contract is unknown, which is machine-learned using training data that is a set of data in which the success or failure of the contract of the product or service provided by the user is associated with a plurality of variables that can correlate with the success or failure of the contract. Predict the success probability of the contract in the customer candidate based on the prediction model for predicting the success probability of the contract for the combination of the variables and the information about the partner candidate of the sales activity of the user. Processing and
The process of acquiring the contribution of each of the variables to the success probability specified based on the prediction model, and
A process of associating and outputting information about the destination candidate and information indicating the basis of the priority of the sales activity, which is specified based on the contribution degree, is executed.
The training data is generated based on information including customer contact information, which is information about the contact of the user with the customer.
The customer contact information is a sales activity support program that includes the date and time of the interview.

Images