Sales Support System

Abstract

To provide a business support system capable of supporting business activities by using Internet browsing information data as data management platform (DMP) information.SOLUTION: A business support system 1 comprises: a prospective customer extraction device 50 which extracts prospective customers being the target of business activities of commercial materials from among viewers 510 who have browsed web content 501 on the Internet 500; a preliminary business information device 100 which outputs preliminary business information to the prospective customers; and an optimal business guideline information output device 150 which determines guidelines of the business activities for the specific viewers 510.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to a sales support system. [Background technology]

[0002] Today, Internet users, as viewers, browse various web content on the Internet. When a user browses web content, the browsing history and information about the viewer are stored as browsing history data on a web server or the like using cookies or the like. Conventionally, data management platform operators (hereinafter referred to as "DMP operators") have collected browsing history data from multiple viewers, and the collected browsing history data has been used to deliver optimal advertisements to specific targeted viewers (for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2020-195125 Summary of the Invention [Problem to be solved by the invention]

[0004] DMP information, which is the browsing history data of web content held by DMP operators, etc., contains information about the issues and concerns that viewers have.As a result of the inventor's diligent research, it has become clear that DMP information can be used to discover customers in B2B sales and to derive sales guidelines such as "appropriate sales timing" and "sales methods."

[0005] Based on the above findings, the present disclosure aims to support sales activities using internet browsing information data as DMP information.

[0006] The present disclosure has been made to solve the above-mentioned problems, and aims to provide a sales support system that can support sales activities using Internet browsing information data as DMP information. [Means for solving the problem]

[0007] The sales support system according to the present disclosure includes a reserve customer extraction device that obtains reserve customer output data consisting of reserve customer access source information, which is access source information related to reserve customers extracted from one or more pieces of access source information, based on reserve customer input data consisting of access source information corresponding to one or more viewers, viewer interest information corresponding to the access source information, and reserve customer extraction information set for extracting reserve customers, in order to extract reserve customers who will be the target of sales activities for a product from viewers who have viewed web content on the Internet; a reserve sales information device that outputs reserve sales output data consisting of reserve sales information for reserve customers based on reserve sales input data consisting of the reserve customer access source information; and a sales guideline input data consisting of access source information related to a specific viewer and viewer interest information corresponding to the access source information related to the specific viewer. and an optimal sales guideline information output device that determines sales guideline output data consisting of optimal sales guideline information that indicates guidelines for sales activities for a specific viewer based on the data, and determines guidelines for sales activities for a specific viewer, wherein the access source information includes at least one of the name information of the corresponding viewer, the activity content information of the viewer, and the industry information to which the viewer belongs, the viewer interest information is information that represents the interests of the viewer obtained based on one or more web contents viewed by the viewer corresponding to the access source information, and the preliminary sales information is output in a form corresponding to at least one of the content of a programmatic advertisement for the viewer corresponding to the preliminary customer access source information, a message posted to an inquiry form, the text of an email, a message in a telephone contact, a message posted on an SNS service, and the text of a letter. [Effects of the Invention]

[0008] According to the sales support system of the present disclosure, sales activities can be supported using internet browsing information data as DMP information. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a schematic diagram showing a sales support system according to a first embodiment. [Figure 2] FIG. 2 is a diagram showing an example of DMP information recorded in the recording device of FIG. [Figure 3] FIG. 3 is a diagram showing an example of access source information according to the first embodiment. [Figure 4] FIG. 3 is a diagram showing an example of viewer interest information according to the first embodiment. [Figure 5] FIG. 2 is a schematic diagram showing the preliminary customer extraction device of FIG. 1. [Figure 6] FIG. 2 is a schematic diagram showing the preliminary sales information device of FIG. [Figure 7] FIG. 2 is a schematic diagram illustrating the machine learning device of FIG. 1. [Figure 8] FIG. 8 is a diagram showing the learning model and learning data of FIG. 7. [Figure 9] 8 is a flowchart showing a machine learning method executed by the machine learning device of FIG. 7. [Figure 10] 2 is a schematic diagram showing the optimum business guideline information output device of FIG. 1. FIG. [Figure 11] 11 is a schematic diagram showing functions of the optimum business guideline information output device of FIG. 10. FIG. [Figure 12] 11 is a flowchart showing an information processing method executed by the optimum sales guideline information output device of FIG. [Figure 13] FIG. 2 is a schematic diagram showing the business target identification device of FIG. 1. [Figure 14] 1 is a conceptual diagram showing the flow of information in a sales support system according to a first embodiment. [Figure 15] FIG. 2 is a hardware configuration diagram illustrating an example of a computer. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, embodiments for carrying out the present disclosure will be described with reference to the drawings. Below, the scope necessary for the explanation to achieve the object of the present disclosure will be schematically shown, and the scope necessary for explaining the relevant parts of the present disclosure will be mainly explained, and the parts that are omitted from the explanation will be based on publicly known techniques.

[0011] Embodiment 1 1 is a schematic diagram showing a sales support system 1 according to embodiment 1. The sales support system 1 outputs optimal sales guidelines targeted at viewers 510 who view various web contents 501 published on the Internet 500.

[0012] A user of the Internet 500 can view various web contents 501 published on the Internet 500. In the present disclosure, a person who views various web contents 501 using the Internet 500 is referred to as a viewer 510.

[0013] Each viewer 510 uses an information terminal 511, such as a PC or a smartphone, that can connect to the Internet 500 in order to view the web content 501. An IP address, which is a unique number, is assigned to the information terminal 511 connected to the Internet 500.

[0014] The information terminal 511 extracts a plurality of Web contents 501 based on the keywords entered into the information terminal 511 by the viewer 510, and displays an outline of the extracted Web contents 501 on the screen 511a of the information terminal 511.

[0015] The viewer 510 can select a desired web content 501 from the outlines of the displayed multiple web contents 501. The selected web content 501 is displayed on the screen 511a, and the viewer 510 can view the displayed web content 501.

[0016] The information terminal 511 records the web address of the web content 501 displayed on the screen 511a and the date and time of viewing as viewing history data in a terminal recording device (not shown) of the information terminal 511. Each time the viewer 510 views the web content 501, information corresponding to the web content 501 is added to the viewing history data and recorded in the terminal recording device.

[0017] Next, we will explain the sales support system 1. The sales support system 1 includes a browsing information processing device 20 having a recording device 21, a machine learning device 40, a preliminary customer extraction device 50, a preliminary sales information device 100, an optimal sales guideline information output device 150, and a sales target identification device 200.

[0018] The sales support system 1 is connected to the Internet 500. The machine learning device 40, the preliminary customer extraction device 50, the preliminary sales information device 100, the optimal sales guideline information output device 150, and the sales target identification device 200 are connected to each other via a network 570 so as to be able to communicate information with each other. Note that the Internet 500 may also serve as the network 570.

[0019] The browsing information processing device 20 can collect browsing history data recorded on multiple information terminals 511 via the Internet 500 using mechanisms such as cookies, and record DMP information consisting of multiple pieces of browsing history data in the recording device 21. The DMP information is owned by and managed by the DMP operator.

[0020] Note that the browsing history data may be collected by the browsing information processing device 20 by analyzing the access history recorded on the web server without using a mechanism such as a cookie, and may be recorded as DMP information in the recording device 21. Furthermore, the collection and recording of browsing history data as DMP information may be performed by a device other than the browsing information processing device 20.

[0021] Furthermore, the DMP information may be generated by a device other than the browsing information processing device 20 or recorded in a recording device other than the recording device 21. In such cases, the browsing information processing device 20 can appropriately use the DMP information generated by an arbitrary device other than the browsing information processing device 20 and the DMP information recorded in an arbitrary recording device other than the recording device 21. Furthermore, in order to use the DMP information generated by an arbitrary device and the DMP information recorded in an arbitrary recording device, the arbitrary device and the arbitrary recording device may be connected to the browsing information processing device 20 so as to be able to communicate information via the Internet 500 or the like.

[0022] Fig. 2 is a diagram showing an example of DMP information recorded in the recording device 21 of Fig. 1. Fig. 2 shows DMP information consisting of 12 pieces of browsing history data associated with two IP addresses.

[0023] The DMP information is associated with the IP address of the information terminal 511 that recorded each piece of browsing history data and is recorded in the recording device 21. The IP address, the web address of the browsed web content 501, and the date and time of browsing are recorded as one piece of browsing information data.

[0024] In this way, the DMP information is made up of multiple browsing history data of multiple viewers 510 connected to the Internet 500. Note that the corresponding numbers shown in Figure 2 are numbers assigned for the convenience of explaining the present disclosure.

[0025] The browsing information processing device 20 can generate access source information about each viewer 510 who uses each information terminal 511 to which each of the multiple IP addresses recorded as DMP information is assigned. The access source information is about the viewer 510 who viewed the web content 501 on the Internet 500. The browsing information processing device 20 can record the generated access source information in the recording device 21.

[0026] Fig. 3 is a diagram showing an example of access source information according to embodiment 1. A piece of access source information relates to a viewer 510 using an information terminal 511 to which a corresponding IP address has been assigned. Fig. 3 shows access source information relating to a viewer 510 using an information terminal 511 to which the IP address XXX.△△△.XXX.01 in Fig. 2 has been assigned.

[0027] In the first embodiment, as described above, access source information is generated for a viewer 510 who uses an information terminal 511 to which a specific global IP address is assigned. However, this is not limited to this. The viewer 510 corresponding to the access source information may be a single individual viewer 510, a group of one or more viewers 510 belonging to an organization, or the organization to which the viewer 510 belongs may be the viewer 510 itself.

[0028] The viewing information processing device 20 can regard the group or group as a new viewer 510 based on the access source information of each viewer 510 belonging to the group or group, and generate access source information corresponding to the new viewer 510.

[0029] Specifically, the access source information includes at least one of name information, activity information, and industry information of a specific viewer 510. Name information indicates a company name, organization name, etc., which is a proper name of the viewer 510. The viewer 510 may be an individual, an organization such as a corporation, or an individual belonging to an organization.

[0030] The activity content information indicates the content of the social activities of the viewer 510 when the viewer 510 is engaged in social activities such as business activities, charitable activities, etc. The industry information indicates the industry to which the viewer 510 belongs.

[0031] FIG. 3 shows, for example, that a specific viewer 510 is using an information terminal 511 managed by XX Co., Ltd., which is engaged in the business of selling electrical equipment and is in the retail industry.

[0032] The name information, activity information, and industry information can be legally identified from information that the viewer 510 has made public on the Internet 500, information that the viewer 510 has registered with an Internet service provider in order to use the Internet 500, and information obtained from the Internet 500 based on the viewer 510's IP address.

[0033] The browsing information processing device 20 can appropriately acquire name information, activity content information, and industry information corresponding to the IP address of the browsing history data from public information on the Internet 500, and record them in the recording device 21. Note that the name information, activity content information, and industry information are not limited to information published on the Internet 500, and can be identified from various information sources. For example, name information, activity content information, and industry information identified by a human survey may be input to the browsing information processing device 20.

[0034] 4 is a diagram showing an example of viewer interest information according to Embodiment 1. The viewer interest information is based on one or more web contents 501 that a specific viewer 510 has viewed.

[0035] The five pieces of viewer interest information shown in Fig. 4 were obtained based on the browsing history data of the information terminal 511 assigned the IP address XXX.△△△.XXX.01 in Fig. 2. In Fig. 4, the corresponding numbers assigned to each piece of viewer interest information were obtained from the browsing history data of the same corresponding number in Fig. 2.

[0036] The viewer interest information is information that indicates the interests of the viewer 510, and is acquired based on one or more web contents 501 that the viewer 510 corresponding to the access source information has viewed. The viewer interest information is acquired based on the browsing history data of a specific viewer 510.

[0037] The browsing information processing device 20 searches for the web content 501 indicated by the web address recorded in each browsing history data of a specific viewer 510, acquires and generates viewer interest information based on the information described in the searched web content 501, and records it in the recording device 21.

[0038] The number of pieces of viewer interest information corresponds to the number of web content 501 viewed by a particular viewer 510. Since a viewer 510 usually views multiple pieces of web content 501, viewer interest information is acquired and generated for each piece of web content 501 viewed.

[0039] Each piece of viewer interest information includes at least one of title information, meta information, and keyword information, and also includes one of viewing order information, viewing count information, and viewing time information.

[0040] 4, for the sake of explanation, in addition to title information, meta information, and keyword information, view order information, view count information, and view time information are shown. Title information indicates the title given to the web content 501. Meta information is obtained from HTML meta tags such as the title and description of the web content 501.

[0041] The keyword information is a keyword extracted based on at least one of the title given to the web content 501 and the meta tag of the web content 501. An appropriately set extraction method can be used to extract the keyword information.

[0042] For example, a plurality of combinations of words predicted to be used in the title, words predicted to be written in the meta tag, and keywords associated therewith are prepared and recorded in advance in the recording device 21.

[0043] The browsing information processing device 20 may extract one combination from the recorded combinations based on the title given to the browsed web content 501 and the information described in the meta tag of the web content 501, and may adopt the keyword in that combination as keyword information.

[0044] The viewing order information indicates the order in which the web content 501 viewed by a specific viewer 510 was viewed by the viewer 510. In other words, it indicates the order in which the web content 501 viewed by the specific viewer 510 was viewed within a predetermined period.

[0045] The browsing information processing device 20 calculates the order in which each piece of WEB content 501 was viewed within a predetermined period of time as viewing order information based on the WEB addresses and date and time information in the browsing history data, and records this in the recording device 21. Note that if a specific viewer 510 is defined as a group of one or more viewers 510 belonging to the organization to which the specific viewer 510 belongs, the viewing order information indicates the order in which the WEB content 501 viewed by one or more viewers 510 belonging to the organization to which the specific viewer 510 belongs was viewed by each viewer 510.

[0046] For example, in Figure 2, the browsing history data for corresponding number 2 is the oldest during the specified period from September 12, 2022 to September 14, 2022, and then becomes gradually newer as it moves from corresponding number 3 to corresponding number 6.

[0047] That is, since the web content 501 having the web address with the corresponding number 2 was viewed the earliest, the viewed information processing device 20 assigns 1 as the viewed order information for the corresponding number 2, as shown in Fig. 4. Since the web content was subsequently viewed in the order of the corresponding numbers 3 to 6, the viewed information processing device 20 assigns 2 to 5 as the viewed order information for the corresponding numbers 3 to 6, respectively.

[0048] The viewing date and time of the web content 501 corresponding to the correspondence number 1 is outside the above-mentioned predetermined period, so it is not extracted from the viewer interest information. The viewing order information is assigned in order from the oldest viewing date and time, but it is not limited to this, and the order may be assigned in order from the newest viewing date and time.

[0049] The view count information is the number of times that the web content 501 has been viewed by the viewer 510 within a predetermined period. In other words, the view count information indicates how many times the viewer 510 has viewed the same web content 501 within a predetermined period.

[0050] The viewing information processing device 20 counts the number of times each WEB content 501 has been viewed within a predetermined period based on the viewing information data, and calculates viewing count information. Note that if a specific viewer 510 is a set of one or more viewers 510 belonging to the organization to which the specific viewer 510 belongs, the viewing count information is the number of times the WEB content 501 viewed by one or more viewers 510 belonging to the organization to which the specific viewer 510 belongs has been viewed within a predetermined period.

[0051] For example, in Figure 2, it can be seen that the same web content 501 was viewed twice for corresponding numbers 4 and 6 during the specified period from September 12, 2022 to September 14, 2022, and that different web content 501 was viewed for the other corresponding numbers 2, 3, and 5. Therefore, as shown in Figure 6, the viewing information processing device 20 assigns 2 as the viewing count information for corresponding numbers 4 and 6, and assigns 1 to the other viewing count information.

[0052] The viewing time information is the total time that the web content 501 viewed by the viewer 510 was viewed within a predetermined period of time. In other words, the viewing time information indicates, for example, how many minutes the viewer 510 viewed the same web content 501 within a predetermined period of time.

[0053] The viewing information processing device 20 calculates viewing time information by adding up the viewing times of each piece of WEB content 501 viewed within a predetermined period based on the viewing information data. Note that if a specific viewer 510 is a group of one or more viewers 510 who belong to the organization to which the specific viewer 510 belongs, the viewing time information is the total amount of time that the WEB content 501 viewed by one or more viewers 510 who belong to the organization to which the specific viewer 510 belongs was viewed within a predetermined period.

[0054] For example, the browsing information processing device 20 can calculate the browsing time of each piece of web content 501 from the browsing information. Therefore, the browsing time information can be calculated by adding up the browsing times of each piece of web content 501. As shown in Fig. 4, each piece of web content 501 is associated with the browsing time information of that web content 501.

[0055] The browsing information processing device 20 can process each piece of browsing history data that constitutes the DMP information to generate learning data 46 to be used for machine learning and record it in the recording device 21. The learning data 46 and the detailed functions of the browsing information processing device 20 will be described later.

[0056] 5 is a schematic diagram showing the reserve customer extraction device 50 of FIG. 1. The reserve customer extraction device 50 can extract reserve customers who are viewers 510 who are the targets of a first sales activity for a product. Specifically, the reserve customer extraction device 50 extracts reserve customer access source information, which is access source information corresponding to the reserve customers, from the access source information organized based on the DMP information as the reserve customers. The first sales activity is a sales activity carried out for the reserve customers, and will be explained later.

[0057] The spare customer extraction device 50 includes a spare customer extraction device control unit 51, a spare customer extraction device recording unit 52, a spare customer extraction device communication unit 53, and an input / output device (not shown).

[0058] The reserve customer extraction device control unit 51 can execute various processes. The reserve customer extraction device communication unit 53 is connected to the browsing information processing device 20, the machine learning device 40, the reserve sales information device 100, the optimal sales guideline information output device 150, and the sales target identification device 200 via a network 570, and functions as a communication interface for transmitting and receiving various types of data.

[0059] The backup customer extraction device recording unit 52 can record various information as needed. The backup customer extraction device control unit 51 can record necessary information in the backup customer extraction device recording unit 52 and read out the recorded information from the backup customer extraction device recording unit 52 as needed.

[0060] The following describes the processing executed by the reserve customer extraction device control unit 51. First, the reserve customer extraction device control unit 51 executes an information acquisition processing to acquire, as reserve customer input data, the access source information recorded in the recording device 21, the viewer interest information corresponding to the access source information, reserve customer extraction information, and sales target information.

[0061] The preliminary customer extraction information is used to extract viewers 510 who will be the target of the first sales activity for the product from the DMP information. The preliminary customer extraction information is set in order to extract preliminary customers. Examples of preliminary customer extraction information include keywords related to the category to which the product is related and URLs of related web pages. The operator can input the preliminary customer extraction information using an input / output device.

[0062] The sales target information is information that can identify a specific viewer 510, but since it is information that is output by sales target identification device 200, it will be explained later.

[0063] Next, the reserve customer extraction device control unit 51 executes a reserve customer extraction process for extracting access source information related to the browser 510 who will become a reserve customer from the reserve customer input data. The reserve customer extraction device control unit 51 extracts the access source information of the browser 510 who will become a reserve customer from the reserve customer input data based on the reserve customer extraction information input to the reserve customer extraction device 50. In other words, the reserve customer extraction information serves as a keyword for extracting reserve customers.

[0064] The backup customer extraction device control unit 51 outputs the extracted access source information as backup customer access source information. In this way, the backup customer extraction device 50 can output backup customer output data, which is backup customer access source information.

[0065] The extraction of potential customers will now be explained. Here, an example will be explained in which compliance-related products are used as commercial products. First, the worker infers from past knowledge that viewers 510 who access web pages on information sites that contain content such as compliance-related articles and descriptions of compliance-related products could be potential customers.

[0066] In such a case, the operator sets up the preliminary customer extraction information as URLs that can encompass each web page of the information site and keywords related to compliance. The preliminary customer extraction information can also be input by the operator using an input / output device. However, the operator may also input information such as the name of the product and the category to which the product belongs to the preliminary customer extraction device 50 using the input / output device, so that the preliminary customer extraction device control unit 51 automatically generates the preliminary customer extraction information from information disclosed on the Internet 500.

[0067] In this case, for example, the preliminary customer extraction device control unit 51 may search and collect content and keywords related to the merchandise from the Internet, and generate preliminary customer extraction information.

[0068] Next, the reserve customer extraction device control unit 51 extracts the viewer interest information corresponding to the reserve customer extraction information, and can extract the access source information corresponding to the extracted viewer interest information. The extracted access source information corresponds to the viewer 510 who is a reserve customer, and the extracted access source information is set as reserve customer access source information.

[0069] The potential customer extraction information may also include the country or region, which makes it possible to extract potential customers in the country or region where the product is sold.

[0070] Furthermore, the reserve customer extraction device control unit 51 can also extract access source information corresponding to the sales target information. Specifically, the reserve customer extraction device control unit 51 can extract access source information and viewer interest information based on the sales target information itself, and information related to the viewer 510 identified by the sales target information searched from the recording device 21 and the Internet 500.

[0071] Information related to the viewer 510 identified by the sales target information includes the industry association to which the viewer 510 belongs, information related to the businesses in which the viewer 510 participates, affiliated companies, trading companies, competitors, company size, location area, and area of ​​activity.

[0072] It should be noted that if the sales target information cannot be acquired, i.e., if the sales target information is not output by the sales target identification device 200, the sales target information does not need to be included as input data for backup customers in the backup customer extraction device 50. The sales target identification device 200 and the sales target information will be described later.

[0073] In this way, the reserve customer extraction device 50 can extract viewers 510 who will become reserve customers from multiple access source information obtained based on DMP information and viewer interest information corresponding to the access source information, based on the reserve customer extraction information and sales target information, and output reserve customer access source information related to the reserve customers.

[0074] That is, the reserve customer extraction device 50 outputs reserve customer output data consisting of reserve customer access source information regarding reserve customers who are viewers 510 who are the targets of the first sales activity, based on reserve customer input data consisting of access source information, viewer interest information, reserve customer extraction information, and sales target information.

[0075] The spare customer extraction device control unit 51 accesses the spare customer extraction device recording unit 52 as necessary in the above processing to record and read information. The spare customer extraction device recording unit 52 may be substituted by a recording device of an external computer. Examples of the external computer include a server-type computer and a cloud-type computer. In this case, the spare customer extraction device control unit 51 can access the external computer.

[0076] Figure 6 is a schematic diagram showing the preliminary sales information device 100 of Figure 1. The preliminary sales information device 100 can output preliminary sales output data consisting of preliminary sales information based on preliminary sales input data consisting of preliminary customer access source information. The preliminary sales information will be explained later.

[0077] The preliminary sales information device 100 includes a preliminary sales information device control unit 101, a preliminary sales information device recording unit 102, a preliminary sales information device communication unit 103, and an input / output device (not shown).

[0078] The preliminary sales information device control unit 101 executes various processes. The preliminary sales information device communication unit 103 is connected to the browsing information processing device 20, the machine learning device 40, the preliminary customer extraction device 50, the optimal sales guideline information output device 150, and the sales target identification device 200 via the network 570, and functions as a communication interface for transmitting and receiving various data.

[0079] The preliminary sales information device recording unit 102 can record various information as needed. The preliminary sales information device control unit 101 can record necessary information in the preliminary sales information device recording unit 102 and can read out the information recorded in the preliminary sales information device recording unit 102 as needed.

[0080] The preliminary sales information device control unit 101 can execute a preliminary customer access source information acquisition process to acquire preliminary customer access source information as preliminary sales input data via the preliminary sales information device communication unit 103. The preliminary customer access source information input to the preliminary sales information device 100 as preliminary sales input data is output by the preliminary customer extraction device 50 described above.

[0081] Next, the preliminary sales information device control unit 101 executes preliminary sales information output processing to create preliminary sales information for the viewer 510 corresponding to the preliminary customer access source information in the preliminary sales input data and output it as preliminary sales output data.

[0082] Preliminary sales information is content intended to arouse potential customers' interest in a product. The preliminary sales information is output in a form that corresponds to various sales methods aimed at potential customers. Sales methods aimed at potential customers include presenting programmatic advertising, posting product information on an inquiry form set up by the potential customer, sending product information by email, sending product information by telephone, posting product information on a social networking service set up by the potential customer, and sending product information via paper media such as mail.

[0083] The preliminary sales information is content in a format corresponding to various sales methods for the above-mentioned potential customers. That is, the preliminary sales information is output in a format corresponding to at least one of programmatic advertising content for viewers corresponding to the potential customer access source information, a message posted to an inquiry form, email text, a phone call message, a message posted on a social networking service, and a letter text.

[0084] In the preliminary sales information output process, the preliminary sales information is generated, for example, by using a generation AI in the preliminary sales information device control unit 101. In this case, the preliminary sales information device control unit 101 can use a generation AI that can be accessed via the Internet 500.

[0085] Further, for example, the preliminary sales information may be created using content that has been created in advance and recorded in the preliminary sales information device recording unit 102 .

[0086] Furthermore, product information for guiding potential customers to the product-related information can be included in the preliminary sales input data. The product information includes product page information indicating a website related to the product and contact information indicating the contact point for inquiries about the product.

[0087] Specifically, product information may include, for example, the URL of the web page on which the product is posted, the URL of the web page where the product can be purchased, and contact information for inquiries about the product, and at least one of these may be used as product information.

[0088] The contact information for inquiries about the product may be a URL of a web page where inquiries about the product can be made, an SNS address, an email address, a telephone number, etc. The preliminary sales information device control unit 101 can output preliminary sales information including product information as preliminary sales output data.

[0089] In this way, the preliminary sales information device control unit 101 can output preliminary sales information based on preliminary sales input data, which is preliminary customer access source information, as preliminary sales output data. Note that the product information may be input by an operator using an input / output device.

[0090] The output preliminary sales information is transmitted to the potential customer by a corresponding sales method, either automatically or manually, thereby completing the first sales activity for the viewer 510 who is the potential customer.

[0091] The first sales activity is a sales activity carried out for potential customers, and its content is to convey preliminary sales information to potential customers.

[0092] A viewer 510 who is a potential customer for whom the first sales activity has been performed may take an action regarding the product. Actions that a potential customer for whom the first sales activity has been performed may take regarding the product include viewing a page related to the product, purchasing the product, and making an inquiry about the product.

[0093] Furthermore, the viewer 510 who comes into contact with the product information is more likely to take the action.

[0094] Next, the machine learning device 40 will be described. FIG. 7 is a schematic diagram showing the machine learning device 40 of FIG. 1. The machine learning device 40 operates as a main component in the learning phase of machine learning. The machine learning device 40 includes a machine learning control unit 41, a machine learning communication unit 42, a learning data storage unit 43, and a machine learning model storage unit 44.

[0095] The machine learning control unit 41 functions as a learning data acquisition unit 41a and a machine learning unit 41b. The machine learning communication unit 42 is connected to the optimal sales guideline information output device 150 and the browsing information processing device 20 via the network 570, and functions as a communication interface for transmitting and receiving various types of information.

[0096] The learning data acquisition unit 41a acquires learning data 46 from the recording device 21 via the machine learning communication unit 42 and the network 570. One set of learning data 46 is composed of input data and output data. Details of the input data and output data will be described later.

[0097] The learning data 46 acquired by the learning data acquisition unit 41a is used as training data, verification data, and test data in supervised learning in machine learning. In addition, output data of the acquired learning data 46 is used as a correct answer label in supervised learning.

[0098] The learning data storage unit 43 is a database that stores one or more sets of learning data 46 acquired by the learning data acquisition unit 41 a. The specific configuration of the database that constitutes the learning data storage unit 43 is designed as appropriate.

[0099] The machine learning unit 41b can perform machine learning using multiple sets of learning data 46 stored in the learning data storage unit 43. Specifically, the machine learning unit 41b inputs multiple sets of learning data 46 to the learning model 45 and causes the learning model 45 to learn the correlation between the input data and the output data included in the learning data 46. In this way, a trained learning model 45 can be generated.

[0100] The machine learning model storage unit 44 is a database that stores a trained learning model 45 generated by the machine learning unit 41b. The trained learning model 45 reflects an adjusted weight parameter group. The trained learning model 45 and the weight parameter group will be described later.

[0101] The trained learning model 45 stored in the machine learning model storage unit 44 is provided to the optimum sales guideline information output device 150 via the network 570 or a recording medium. Note that although the learning data storage unit 43 and the machine learning model storage unit 44 are shown as separate storage units in FIG. 7, they may be configured as a single storage unit.

[0102] Fig. 8 is a diagram showing the learning model 45 and learning data 46 of Fig. 7. For example, a neural network structure is adopted for the learning model 45. The learning model 45 includes an input layer 45a, an intermediate layer 45b, and an output layer 45c. A plurality of synapses are established between the input layer 45a, the intermediate layer 45b, and the output layer 45c, respectively, connecting a plurality of neurons.

[0103] Each synapse is associated with a weight. In machine learning, a group of weight parameters consisting of the weights of each synapse is adjusted, and the group of weight parameters is reflected in a learning model 45.

[0104] The input layer 45a has neurons whose number corresponds to the number of input data, and the output layer 45c has neurons whose number corresponds to the number of output data. Input data is input to each neuron in the input layer 45a of the learning model 45, passes through the intermediate layer 45b, and output data corresponding to the input data is output as an inference result from each neuron in the output layer 45c.

[0105] The machine learning unit 41b compares the value of the output data output as the inference result with the output data of the learning data 46 as the correct label, and adjusts the weight of each synapse based on the result of the comparison.

[0106] When the learning model 45 is configured as a regression model, the output data is output as a numerical value normalized to a predetermined range (for example, 0 to 1). When the learning model 45 is configured as a classification model, the output data is output as a score (accuracy) for each class as a numerical value normalized to a predetermined range (for example, 0 to 1).

[0107] The learning data 46 is data used for machine learning of the learning model 45. In the present embodiment 1, the input data of the learning data 46 is composed of data consisting of access source information and viewer interest information, and the output data of the learning data 46 is composed of data consisting of optimal sales guideline information.

[0108] The access source information and viewer interest information that make up the input data are generated based on the DMP information as described above.

[0109] The optimal sales guideline information constituting the output data indicates a guideline for a second sales activity for a specific viewer 510. The optimal sales guideline information includes at least one of a sales recommendation level and a recommended sales method. The second sales activity is a sales activity that is carried out for a specific viewer 510 in accordance with the optimal sales guideline information.

[0110] The sales recommendation level indicates the degree to which it is recommended to carry out a second sales activity toward the specific viewer 510. The sales recommendation level may be indicated as a percentage between 0% and 100%. For example, when the sales recommendation level is 90%, it is recommended to carry out a very aggressive second sales activity toward the viewer 510. Note that, when the specific viewer is an organization to which the specific viewer 510 belongs, the sales recommendation level indicates the degree to which it is recommended to carry out a second sales activity toward the organization to which the specific viewer belongs.

[0111] The recommended sales methods of telecalling viewer 510, posting sales information on viewer 510's inquiry form, sending sales e-mail to viewer 510, sending direct mail to viewer 510, and displaying advertisements on the web browser of viewer 510's information terminal 511 are, in this order, the most aggressive sales methods. In other words, telecalling viewer 511, recommended sales method 0, is a more aggressive sales method than sending direct mail to viewer 510.

[0112] The sales recommendation level and the recommended sales method may be output independently of each other, or the recommended sales method may be selected according to the sales recommendation level. For example, when the sales recommendation level is 70% to 100%, a telecall to the viewer 510 is the recommended sales method. When the sales recommendation level is 40% to 69%, a sales-related post to an inquiry form or the like held by the viewer 510, sending a sales email to the viewer 510, or sending a direct mail to the viewer 510 is the recommended sales method. When the sales recommendation level is 0% to 39%, an advertisement is displayed on the web browser of the information terminal 511 used by the viewer 510.

[0113] It is desirable to use sales guideline input data previously input to the optimum sales guideline information output device 150 and sales guideline output data output based on that sales guideline input data as the learning data 46. This is because such sales guideline output data is data that has been actually used since then, and therefore has a certain degree of validity, such as customer satisfaction.

[0114] In addition, the sales guideline input data that has already been used and the sales guideline output data corresponding to that sales guideline input data are recorded in a recording device 21 or the like, and are ready to be used as needed.

[0115] If there is no sales guideline output data output from the optimum sales guideline information output device 150 based on the sales guideline input data, sales guideline output data corresponding to the sales guideline input data can be created based on the knowledge of the operator, and the sales guideline input data and sales guideline output data can be used. Details of the optimum sales guideline information output device 150, the sales guideline input data, and the sales guideline output data will be explained later.

[0116] 9 is a flowchart showing a machine learning method executed by the machine learning device 40 of FIG. 7. In the machine learning method, the process of step S100 is first performed. In step S100, the learning data acquisition unit 41a acquires multiple pieces of learning data 46 as preparation for starting machine learning, and stores the acquired learning data 46 in the learning data storage unit 43. The number of pieces of learning data acquired for preparation may be set in consideration of the inference accuracy required for the ultimately obtained learning model 45.

[0117] Next, the process of step S110 is performed. In step S110, machine learning unit 41b prepares pre-learning learning model 45 in order to start machine learning. Learning model 45 is configured by a neural network model, and the weight of each synapse is set to an initial value.

[0118] Next, the process of step S120 is performed. In step S120, the machine learning unit 41b acquires, for example, one set of training data 46 at random from the multiple sets of training data 46 stored in the training data storage unit 43.

[0119] Next, the process of step S130 is performed. In step S130, the machine learning unit 41b inputs the access source information and the viewer interest information, which are input data included in the set of learning data 46, to the input layer 45a of the prepared learning model 45 before learning or during learning. When the input data is input to the input layer 45a, the output layer 45c of the learning model 45 outputs optimal sales guideline information, which is output data, as an inference result.

[0120] The output data output as an inference result is data generated by the learning model 45 before or during learning, and therefore may show values ​​different from the optimal sales guideline information, which is the correct label contained in the learning data 46.

[0121] Next, the process of step S140 is performed. In step S140, the machine learning unit 41b compares the optimal sales guideline information, which is the correct label included in the set of learning data 46 acquired in step S120, with the optimal sales guideline information, which is the output data output as the inference result from the output layer 45c in step S130.

[0122] The machine learning unit 41b performs machine learning by adjusting the weight of each synapse based on the comparison result between the correct label and the output data, i.e., by performing backpropagation, thereby causing the learning model 45 to learn the correlation between the access source information, the viewer interest information, and the optimal sales guideline information.

[0123] Next, the process of step S150 is performed. In step S150, the machine learning unit 41b determines whether the learning termination condition is met or not. For example, the machine learning unit 41b determines whether the learning termination condition is met based on at least one of the evaluation value of an error function based on the correct label and the output data and the remaining number of unlearned learning data 46 stored in the learning data storage unit 43.

[0124] If the learning termination condition is not met in step S150, the machine learning unit 41b performs the processes of steps S120 to S150 again on the currently trained learning model 45 using untrained learning data 46. On the other hand, if the learning termination condition is met in step S150, the machine learning unit 41b stores the generated trained learning model 45 (adjusted weight parameter group) in the machine learning model storage unit 44 in step S160, and the machine learning method ends.

[0125] In the machine learning method, step S100 corresponds to a learning data storage step, steps S110 to S150 correspond to a machine learning step, and step S160 corresponds to a trained model storage step.

[0126] Fig. 10 is a schematic diagram showing the optimum sales guideline information output device 150 of Fig. 1. The optimum sales guideline information output device 150 includes an output device control unit 151, an output device recording unit 152, and an output device communication unit 153.

[0127] The output device control unit 151 functions as an information acquisition unit 151a, an inference unit 151b, and an output processing unit 151c. The output device communication unit 153 is connected to the browsing information processing device 20, the machine learning device 40, the preliminary customer extraction device 50, the preliminary sales information device 100, and the sales target identification device 200 via a network 570, and functions as a communication interface for transmitting and receiving various data.

[0128] The information acquisition unit 151a is connected to the viewing information processing device 20, the machine learning device 40, the preliminary customer extraction device 50, and the preliminary sales information device 100 via the output device communication unit 153 and the network 570. The information acquisition unit 151a executes an information acquisition process to acquire the access source information recorded in the recording device 21 as input data for a sales guideline, and to acquire viewer interest information corresponding to the access source information as input data for a sales guideline.

[0129] The inference unit 151b inputs the access source information and the viewer interest information acquired by the information acquisition unit 151a as sales guideline input data to the learning model 45. The inference unit 151b executes inference processing using the learning model 45, which has learned the correlation between the sales guideline input data and the sales guideline output data recorded in the output device recording unit 152 by machine learning.

[0130] The output device recording unit 152 is a database that stores trained learning models 45 used in the inference unit 151b. The number of training models 45 recorded in the output device recording unit 152 is not limited to one, and multiple trained models with different conditions, such as different machine learning techniques used to generate the training models 45, are recorded and can be selectively used.

[0131] The output device recording unit 152 may be replaced by a storage unit of an external computer, in which case the inference unit 151b may access the external computer. Examples of the external computer include a server computer and a cloud computer.

[0132] The output processing unit 151c executes an output process of outputting sales guideline output data including the optimum sales guideline information inferred by the inference unit 151b to the recording device 21 for recording.

[0133] In this way, the output device control unit 151 can obtain sales guideline output data consisting of optimal sales guideline information based on preliminary customer input data consisting of access source information and viewer interest information.

[0134] Fig. 11 is a schematic diagram showing the functions of the optimum sales guideline information output device 150 of Fig. 10. In the optimum sales guideline information output device 150, the information acquisition unit 151a acquires access source information and viewer interest information based on DMP information as input data for sales guideline, and inputs them to the inference unit 151b. The inference unit 151b inputs the access source information and viewer interest information to the learning model 45, and generates optimum sales guideline information as an inference result by the learning model 45.

[0135] FIG. 12 is a flowchart showing an information processing method executed by the optimum sales guideline information output device 150 of FIG.

[0136] First, in step S200, the sales guideline input data acquisition step is executed. The information acquisition unit 151a acquires access source information and viewer interest information based on DMP information from the recording device 21 as sales guideline input data.

[0137] Next, in step S210, an inference process is carried out. The inference unit 151b inputs the access source information and the viewer interest information, which are acquired by the information acquisition unit 151a as input data for the sales guideline, into the learning model 45. The inference unit 151b executes an inference process using the learning model 45 recorded in the output device recording unit 152, and obtains optimal sales guideline information as sales guideline output data.

[0138] Next, in step S220, an output processing step is carried out. The output processing unit 151c executes output processing to output sales guideline output data including the optimum sales guideline information inferred by the inference unit 151b to the recording device 21. This completes the information processing method.

[0139] The optimum sales guideline information recorded in the recording device 21 can be used as appropriate, such as by being provided by the administrator of the sales support system 1 to those who need the optimum sales guideline information. The sales representative, who is the worker, can carry out a second sales activity for the target viewer 51 in accordance with the optimum sales guideline information. Note that whether or not the second sales activity will be carried out is determined by the worker, and the sales support system 1 has no binding power regarding the implementation of the second sales activity.

[0140] Fig. 13 is a schematic diagram showing the sales target identification device 200 of Fig. 1. The sales target identification device 200 can output sales target output data consisting of sales target information, based on sales target input data consisting of access source information of a specific viewer 510 and optimal sales guideline information.

[0141] The sales target person identification device 200 includes a sales target person identification device control unit 201, a sales target person identification device recording unit 202, a sales target person identification device communication unit 203, and an input / output device (not shown).

[0142] The sales target identification device control unit 201 executes various processes. The sales target identification device communication unit 203 is connected to the browsing information processing device 20, the machine learning device 40, the preliminary customer extraction device 50, the preliminary sales information device 100, and the optimal sales guideline information output device 150 via the network 570, and functions as a communication interface for transmitting and receiving various types of data.

[0143] Sales target identification device recording unit 202 can record various information as needed. Sales target identification device control unit 201 can record necessary information in sales target identification device recording unit 202, and can also read out recorded information from sales target identification device recording unit 202 as needed.

[0144] The processing executed by the sales target identification device control unit 201 will be explained. First, the sales target identification device control unit 201 executes a specific viewer information acquisition process to acquire access source information of the specific viewer 510 and optimal sales guideline information as input data for the sales target via the sales target identification device communication unit 203. At this time, the optimal sales guideline information includes a sales recommendation degree. The access source information input to the sales target identification device 200 as input data for the sales target is the same as the access source information of the specific viewer 510, which is the input data for the sales target of the optimal sales guideline information output device 150 described above.

[0145] Next, the sales target identification device control unit 201 executes sales target output processing to generate sales target information based on the sales target input data and output it as sales target output data.

[0146] The sales target information is information that can identify a specific viewer 510 or a viewer 510 extracted from the specific viewers 510. Specifically, the sales target information is information that can identify the viewer 510, such as access source information of the corresponding viewer 510 or an IP address corresponding to the access source information.

[0147] In the sales target output process, the sales target identification device control unit 201 generates sales target information based on the access source information of the specific viewer 510. At this time, the sales target identification device control unit 201 may extract the access source information from the access source information of the specific viewer 510 based on the sales recommendation degree included in the optimal sales guideline information, and generate sales target information that can identify the viewer 510 corresponding to this access source information.

[0148] That is, sales target information can be generated based on the sales recommendation level. Specifically, a threshold value for the sales recommendation level may be set, and access source information may be extracted based on the sales recommendation level included in the optimal sales guideline information from the access source information of a specific viewer 510 based on the threshold value.

[0149] The method for generating sales target information can be appropriately selected from rule-based methods, machine learning methods, and other well-known methods.

[0150] Next, the sales target identification device control unit 201 outputs the sales target information to the potential customer extraction device 50 via the sales target identification device communication unit 203.

[0151] Furthermore, sales target identification device control unit 201 may appropriately record sales target information in sales target identification device recording unit 202. This completes the series of processes by sales target identification device 200.

[0152] Although the sales target information is output based on the sales recommendation level here, the sales target information may also be output based on the recommended sales technique. In this case, a recommendation level equivalent to the sales recommendation level may be set for each of the various sales techniques indicated in the recommended sales technique, and the sales target information may be output based on the recommendation level.

[0153] In the sales support system 1, the above-mentioned preliminary customer extraction device 50, preliminary sales information device 100, optimal sales guideline information output device 150, and sales target identification device 200 can be used repeatedly in this order. Fig. 14 is a conceptual diagram showing the flow of information in the sales support system 1 according to the first embodiment.

[0154] When the sales support system 1 is used for a certain product, the process is first executed using the reserve customer extraction device 50. The reserve customer extraction device 50 outputs reserve customer access source information based on reserve customer input data.

[0155] The preliminary customer access source information is input to the preliminary sales information device 100 as preliminary sales input data, and the preliminary sales information device 100 outputs preliminary sales information, which is preliminary sales output data, based on the preliminary sales input data. The output preliminary sales information is communicated to the preliminary customers automatically or by an operator. That is, a first sales activity utilizing the preliminary sales information is carried out.

[0156] For a viewer 510 who is a potential customer who has become interested in the product through the first sales activity and has taken action on the product, the access source information will be included in the input data for the sales guideline to the optimal sales guideline information output device 150 as access source information related to the specific viewer 510.

[0157] The optimum sales guideline information output device 150 outputs optimum sales guideline information based on the sales guideline input data, which is access source information related to specific viewers 510 including such viewers 510. The sales person, who is the worker, can carry out the second sales activity based on the optimum sales guideline information.

[0158] Furthermore, the optimum sales guideline information output by the optimum salesperson information output device 150 is input to the sales target determination device 200 as sales target input data. The sales target determination device 200 outputs sales target output data including sales target information based on the sales target input data including the optimum sales guideline information. The sales target information is recursively included in the preliminary customer input data of the preliminary customer extraction device 50 and input to the preliminary customer extraction device 50.

[0159] The backup customer extraction device 50 performs processing again using the backup customer input data containing the sales target information, and outputs backup customer output data based on the backup customer input data. That is, the sales target information contained in the sales target output data of the sales target identification device 200 can be used as backup customer input data for the backup customer extraction device 50, and backup customer access source information can be output.

[0160] In this way, the sales support system 1 starts with the preliminary customer extraction device 50, and then processes are performed by the preliminary sales information device 100, the optimal sales guideline information output device 150, and the sales target identification information 200, and then the process is executed again by the preliminary customer extraction device 50. That is, each device is used repeatedly in sequence, and the corresponding process is repeatedly executed in sequence. This makes it possible to extract preliminary customers who are thought to be related to the product from a wider range.

[0161] As described above, when the sales support system 1 is used for the first time for a product, the sales target information is not output and does not exist. Therefore, the preliminary customer input data input to the preliminary customer extraction device 50 does not include the sales target information.

[0162] As described above, the sales target information output by the sales target identification device 200 may be, for example, extracted from the optimal sales guideline information, a viewer 510 whose sales recommendation level is lower than a set threshold value, and the viewer 510 may be identified.

[0163] For viewers 510 who are determined to have a low degree of recommendation for carrying out the second sales activity, the sales representative may carry out the second sales activity using a relatively low-effort method, such as sending only direct mail, or may not carry out the second sales activity at all. The sales target identification device 200 outputs sales target information that can identify such viewers 510, and the backup customer extraction device 50 outputs backup customer access source information based on the sales target information. As a result, the access source information of viewers 510 who are determined to have a low degree of recommendation for carrying out the second sales activity is also included in the backup customer access source information, and they become targets of the first sales activity.

[0164] Furthermore, for example, the sales target information output by the sales target identification device 200 may be configured to extract viewers 510 whose sales recommendation level of the optimal sales guideline information is higher than a threshold value, and identify the viewers 510. This allows the spare customer extraction device 50 to output spare customer access source information, taking into account information on the industry to which the viewers 510 who have a high recommendation level for carrying out the second sales activity belong.

[0165] As described above, in outputting sales target information, in addition to the sales recommendation degree, a recommended sales technique can also be used.

[0166] 15 is a hardware configuration diagram showing an example of a computer 900. The browsing information processing device 20, the machine learning device 40, the preliminary customer extraction device 50, the preliminary sales information device 100, the optimal sales guideline information output device 150, and the sales target identification device 200 are configured by a general-purpose or dedicated computer 900.

[0167] 15, the computer 900 includes, as its main components, a bus 910, a processor 912, a memory 914, an input device 916, an output device 917, a display device 918, a storage device 920, a communication interface unit 922, an external device interface unit 924, an input / output device interface unit 926, and a media input / output unit 928. Note that the above components may be omitted as appropriate depending on the application of the computer 900.

[0168] The processor 912 is composed of one or more arithmetic processing devices (such as a central processing unit (CPU), a micro processing unit (MPU), a digital signal processor (DSP), or a graphics processing unit (GPU)), and operates as a control unit that controls the entire computer 900. The memory 914 stores various data and a program 930, and is composed of, for example, a volatile memory (such as a DRAM or SRAM) that functions as a main memory, a non-volatile memory (ROM), a flash memory, etc.

[0169] The input device 916 is configured, for example, by a keyboard, a mouse, a numeric keypad, an electronic pen, etc., and functions as an input unit. The output device 917 is configured, for example, by a sound (audio) output device, a vibration device, etc., and functions as an output unit. The display device 918 is configured, for example, by a liquid crystal display, an organic EL display, electronic paper, a projector, etc., and functions as an output unit. The input device 916 and the display device 918 may be configured integrally, such as a touch panel display. The storage device 920 is configured, for example, by an HDD, an SSD (Solid State Drive), etc., and functions as a storage unit. The storage device 920 stores various data necessary for executing the operating system and the program 930.

[0170] The communication interface unit 922 is connected by wire or wireless to a network 940 such as the Internet or an intranet (which may be the same as the network 570 in FIG. 1 ), and functions as a communication unit that transmits and receives data to and from other computers in accordance with a predetermined communication standard. The external device interface unit 924 is connected by wire or wireless to an external device 950 such as a camera, printer, scanner, or reader / writer, and functions as a communication unit that transmits and receives data to and from the external device 950 in accordance with a predetermined communication standard. The input / output device interface unit 926 is connected to input / output devices 960 such as various sensors and actuators, and functions as a communication unit that transmits and receives various signals and data, such as detection signals from sensors and control signals to actuators, to and from the input / output devices 960. The media input / output unit 928 is configured by a drive device such as a DVD drive or CD drive, and reads and writes data from and to media (non-transitory storage media) 970 such as DVDs and CDs.

[0171] In the computer 900 having the above configuration, the processor 912 loads a program 930 stored in the storage device 920 into the memory 914, executes the program, and controls each unit of the computer 900 via the bus 910. The program 930 may be stored in the memory 914 instead of the storage device 920. The program 930 may be recorded on the medium 970 in an installable file format or an executable file format and provided to the computer 900 via the media input / output unit 928. The program 930 may be provided to the computer 900 by being downloaded via the network 940 via the communication interface unit 922. Furthermore, the computer 900 may implement various functions realized by the processor 912 executing the program 930 using hardware such as an FPGA or an ASIC.

[0172] The computer 900 is, for example, a desktop computer or a portable computer, and is an electronic device of any type. The computer 900 may be a client computer, a server computer, or a cloud computer. The computer 900 may be applied to devices other than the browsing information processing device 20, the machine learning device 40, the preliminary customer extraction device 50, the preliminary sales information device 100, the optimal sales guideline information output device 150, and the sales target identification device 200.

[0173] The sales support system 1 in the first embodiment is provided with the sales target person identification device 50. However, this is not limited to this. For example, if the sales target person identification device 50 cannot be provided, access source information regarding the specific viewer 510, which is input data for the sales guideline of the optimal sales guideline output device 150, may be input as sales target information as input data for the backup customer to the backup customer extraction device 50. This allows the backup customer extraction device 50 to output backup customer access source information including the specific viewer 510.

[0174] According to the sales support system 1 of the first embodiment, the system includes a reserve customer extraction device 50 that, based on reserve customer input data including access source information corresponding to one or more viewers 510, viewer interest information corresponding to the access source information, and reserve customer extraction information set for extracting reserve customers, extracts reserve customers who will be the target of sales activities for a product from viewers 510 who have viewed web content 501 on the Internet 500. The system also includes a reserve sales information device 100 that, based on preliminary sales input data including the reserve customer access source information, outputs preliminary sales output data including preliminary sales information for the reserve customers. The system also includes an optimal sales guideline information output device 150 that determines a sales guideline for the specific viewer 510 by extracting sales guideline output data including optimal sales guideline information that indicates a guideline for sales activities for the specific viewer 510, based on sales guideline input data including access source information for the specific viewer 510 and viewer interest information corresponding to the access source information for the specific viewer 510. The access source information includes at least one of the name information of the corresponding viewer 510, the activity information of the viewer 510, and the industry information to which the viewer 510 belongs. The viewer interest information is information indicating the interests of the viewer 510, obtained based on one or more web contents 501 viewed by the viewer 510 corresponding to the access source information. The preliminary sales information is output in a form corresponding to at least one of the programmatic advertising content, the text of an inquiry form, the text of an email, a message in a telephone call, a message posted on a social networking service, and the text of a letter for the viewer 510 corresponding to the preliminary customer access source information. This makes it possible to support sales activities using internet browsing information data as DMP information. This also makes it possible to easily find customers from the browsing history data of the viewer 510 by extracting preliminary customers from multiple access source information and the viewer interest information corresponding to each access source information using preliminary customer extraction information.In addition, sales guidelines such as "appropriate sales timing" and "sales methods" can be easily derived from the browsing history data of a specific viewer 510. Therefore, sales activities can be supported using internet browsing information data as DMP information.

[0175] According to the sales support system 1 of the first embodiment, the optimal sales guideline information further includes at least one of a sales recommendation level and a recommended sales technique, where the sales recommendation level indicates the degree to which sales activities are recommended for the viewer 510, and the recommended sales technique indicates a sales technique recommended for the viewer. This makes it possible to easily derive sales guidelines such as "appropriate sales timing" and "sales method" based on the browsing history data of a specific viewer 510. This also makes it possible to obtain sales guidelines for the specific viewer 510 at the current time. Therefore, it is possible to carry out effective sales activities. Therefore, it is possible to further support sales activities using Internet browsing information data as DMP information.

[0176] The sales support system 1 according to the first embodiment further includes a sales target identification device 200 that identifies sales target information from among the specific viewers 510 based on the sales recommendation level, and the input data for the spare customer in the spare customer extraction device 50 further includes sales target information. As a result, by extracting spare customers based on the input data for the spare customers that includes information for identifying the specific viewers 510, when re-finding customers, it is possible to extract spare customers taking into account information about the specific viewers 510. Therefore, by performing recursive processing, it is possible to extract more appropriate spare customers. Furthermore, it is possible to repeatedly perform the recursive processing, making it possible to easily find customers. Therefore, it is possible to further support sales activities using internet browsing information data as DMP information.

[0177] According to the sales support system 1 of the first embodiment, the name information indicates the name of the viewer 510 or the organization to which the viewer 510 belongs, the activity content information indicates the content of the social activities carried out by the viewer 510 or the organization, and the industry information indicates the industry to which the viewer 510 or the organization belongs. This allows more detailed information about the environment to which the viewer 510 belongs to to be obtained. Therefore, it is possible to more easily find customers from the browsing history data of the viewer 510, and also to more easily derive sales guidelines such as "appropriate sales timing" and "sales methods" from the browsing history data of a specific viewer 510. Therefore, sales activities can be better supported using internet browsing information data as DMP information.

[0178] According to the sales support system 1 of the first embodiment, each viewer interest information includes at least one of title information, meta information, and keyword information. The title information, meta information, and keyword information are obtained from information on the web content 501 viewed by the viewer 510. The title information indicates the title of the web content 501, the meta information is obtained from the meta tag of the web content 501, and the keyword information is a keyword extracted based on at least one of the title and meta tag of the web content 501. This allows potential customers to be extracted taking into account the content of the web content 501 viewed by the viewer 510. Furthermore, the content of the web content 501 viewed by the viewer 510 can be inferred in more detail. Therefore, it is possible to more easily find customers from the browsing history data of the viewer 510, and to more easily derive sales guidelines such as "appropriate sales timing" and "sales methods" based on the browsing history data of a specific viewer 510. Therefore, sales activities can be more effectively supported using internet browsing information data as DMP information.

[0179] According to the sales support system 1 of the first embodiment, the potential customer extraction information includes related website information indicating the URL of the web content 501 related to the category to which the product belongs. This makes it easy to extract potential customers who are interested in the product, making it easier to find customers. Therefore, sales activities can be better supported by using the internet browsing information data as DMP information.

[0180] According to the sales support system 1 of the first embodiment, the preliminary sales input data in the preliminary sales information device further includes product information, which is information related to the product, and the product information includes at least one of product page information indicating a website 501 related to the product and contact information indicating the contact point for inquiries regarding the product. This allows the preliminary sales information device 100 to generate preliminary sales information that takes into account information related to the product information. Therefore, viewers 510 who come across the preliminary sales information that takes into account information related to the product information can be more easily guided to the product. Therefore, sales activities can be more effectively supported using Internet browsing information data as DMP information.

[0181] According to the sales support system 1 of the first embodiment, the preliminary sales information includes product information. This allows the preliminary sales information device 100 to include the product information itself in the preliminary sales information. Therefore, it is possible to more directly guide the viewer 510 who comes across the preliminary sales information to the product. Therefore, it is possible to further support sales activities by using the internet browsing information data as DMP information.

[0182] According to the sales support system 1 of the first embodiment, each viewer interest information further includes viewing order information, which indicates the order in which the viewer 510 viewed the web content 501. This makes it possible to infer the interests of a specific viewer 510 according to the time series. Therefore, it is possible to more easily derive sales guidelines such as "appropriate sales timing" and "sales methods" based on the viewing history data of the specific viewer 510. Therefore, sales activities can be better supported using internet viewing information data as DMP information.

[0183] According to the sales support system 1 of the first embodiment, each viewer interest information further includes view count information, which is the number of times the web content 501 was viewed by the viewer 510 within a predetermined period. This makes it possible to infer the viewer's 510 interests based on the number of views. Therefore, it is possible to more easily derive sales guidelines such as "appropriate sales timing" and "sales methods" based on the browsing history data of a specific viewer 510. Therefore, sales activities can be better supported using internet browsing information data as DMP information.

[0184] According to the sales support system 1 of the first embodiment, each viewer interest information further includes viewing time information, which is the total time that the web content 501 was viewed by the viewer 510 within a predetermined period. This makes it possible to infer the subject of interest of the viewer 510 based on the viewing time. Therefore, it is possible to more easily derive sales guidelines such as "appropriate sales timing" and "sales methods" based on the viewing history data of a specific viewer 510. Therefore, sales activities can be better supported using internet viewing information data as DMP information.

[0185] According to the sales support system 1 of the first embodiment, when preliminary customer input data is input, the optimal sales guideline information output device 150 determines optimal sales guideline information using a learning model 45 that has learned the correlation between the preliminary customer input data and the preliminary customer output data through machine learning, and outputs the determined optimal sales guideline information as preliminary customer output data. This makes it possible to output optimal sales guideline information using the learning model 45. Therefore, it is possible to more easily derive sales guidelines such as "appropriate sales timing" and "sales methods" based on the browsing history data of a specific viewer 510. Therefore, it is possible to better support sales activities using Internet browsing information data as DMP information.

[0186] The sales support system 1 according to the first embodiment includes a reserve customer extraction device 50 that, based on reserve customer input data including access source information corresponding to one or more viewers 501, viewer interest information corresponding to the access source information, and reserve customer extraction information set for extracting reserve customers, extracts reserve customer output data including reserve customer access source information that is access source information related to reserve customers extracted from one or more pieces of access source information, in order to extract reserve customers who will be targets of sales activities for a product from among viewers 510 who have viewed web content 501 on the Internet 500. The access source information includes at least one of name information of the corresponding viewer 510, activity information of the viewer 510, and information on the industry to which the viewer 510 belongs, and the viewer interest information is information indicating the interests of the viewer 510 obtained based on one or more web content 501 viewed by the viewer 510 corresponding to the access source information. This allows potential customers to be extracted from multiple pieces of access source information and viewer interest information corresponding to each piece of access source information using potential customer extraction information, making it possible to easily discover customers from the browsing history data of viewer 510. Therefore, sales activities can be further supported by using internet browsing information data as DMP information.

[0187] The sales support system 1 according to the first embodiment includes a preliminary sales information device 100 that outputs preliminary customer output data consisting of preliminary sales information for a preliminary customer based on preliminary customer input data consisting of preliminary customer access source information, which is access source information regarding preliminary customers who are potential customers among viewers 510 who have viewed web content 501 on the Internet 500 and are the target of sales activities for a product. The access source information includes at least one of the name information of the corresponding viewer 510, activity content information of the viewer 510, and industry information to which the viewer 510 belongs. The preliminary sales information is output in a format corresponding to at least one of programmatic advertising content, a message posted to an inquiry form, email text, a phone call message, a message posted on a social networking service, and a letter text for the viewer 510 corresponding to the preliminary customer access source information. This makes it easier to create preliminary sales information for potential customers. This reduces sales activity costs and resources. Therefore, sales activities can be better supported using Internet browsing information data as DMP information.

[0188] Embodiment 2 The optimal sales guideline information output device 150 of the second embodiment outputs optimal sales guideline information based on a rule base. The optimal sales guideline information output device 150 of the first embodiment uses the trained learning model 45 generated by the machine learning device 40 to output optimal sales guideline information, but the optimal sales guideline information output device 150 of the second embodiment differs from the optimal sales guideline information output device 150 of the first embodiment in that it outputs optimal sales guideline information based on a rule base.

[0189] The optimum sales guideline information output device 150 includes an output device control unit 151, an output device communication unit 153, and an output device recording unit 152. The optimum sales guideline information output device 150 can output optimum sales guideline information corresponding to the degree of interest of the viewer 510 based on the input data for sales guideline, which is the acquired access source information and viewer interest information.

[0190] In the second embodiment, the interest level of the viewer 510 is divided into four levels based on a marketing funnel model. Specifically, the four levels based on the marketing funnel model are "awareness," "interest / concern," "comparison / consideration," and "purchase."

[0191] To output the sales guideline input data as interest levels, first, the access source information and the sales guideline input data, which is viewer interest information, are converted using a predetermined function. The converted sales guideline input data is then classified into one of the hierarchies based on the marketing funnel model, according to predetermined classification rules.

[0192] Here, the predetermined function is a well-known function that vectorizes text information. The predetermined function and classification rules are recorded in advance in the output device recording unit 152.

[0193] Next, the optimum sales guideline information output device 150 determines and outputs optimum sales guideline information based on the interest level. The optimum sales guideline information includes at least one of a sales recommendation level and a recommended sales technique.

[0194] The sales recommendation level is the degree to which the second sales activity is recommended for a particular viewer 510. For example, the sales recommendation level is output from the optimum sales guideline information output device 150 at four levels: low, medium, high, and highest, corresponding to the four layers based on the marketing funnel model.

[0195] The recommended sales method is a sales method recommended to a specific viewer 510. For example, the recommended sales methods correspond to the following in order of decreasing interest level in four layers based on the marketing funnel model: displaying an advertisement on the web browser of the information terminal 511 used by the viewer 510, sending a sales email to the viewer 510, posting a sales message on an inquiry form or the like held by the viewer 510, and making a telephone call to the viewer 510.

[0196] In the second embodiment, the sales recommendation level and the recommended sales technique are calculated and output independently of each other, but the recommended sales technique may be set according to the output sales recommendation level.

[0197] Since machine learning is not used in the second embodiment, the configurations relating to the learning model 45, the machine learning device 40, and the inference device in the first embodiment are not used. The other configurations of the second embodiment are the same as those of the first embodiment, and therefore description thereof will be omitted.

[0198] According to the sales support system 1 of the second embodiment, when preliminary customer input data is input, the optimum sales guideline information output device 150 classifies the preliminary customer input data based on predetermined rules, determines optimum sales guideline information based on the classification, and outputs the determined optimum sales guideline information as preliminary customer output data. This makes it possible to output optimum sales guideline information in accordance with the rules. Therefore, it is possible to more easily derive sales guidelines such as "appropriate sales timing" and "sales methods" based on the browsing history data of a specific viewer 510. Therefore, sales activities can be better supported using Internet browsing information data as DMP information.

[0199] In the second embodiment, the interest level of the viewer 510 is classified into hierarchical levels based on the marketing funnel model, but other well-known classification methods may be used for classification.

[0200] Furthermore, as described above, in the first and second embodiments, the specific viewer 510 does not have to be a single individual viewer 510. That is, the specific viewer is at least one of the specific viewer 510 who is a single individual, a set of one or more viewers 510 who belong to an organization to which the specific viewer 510 belongs, and an organization to which the specific viewer 510 belongs.

[0201] (Other embodiments) The present disclosure is not limited to the above-described embodiment, and various modifications can be made without departing from the spirit and scope of the present disclosure, all of which are included in the technical concept of the present disclosure.

[0202] For example, the access source information and the viewer interest information may include other information as appropriate.

[0203] Furthermore, in the above-described first embodiment, a case has been described in which a neural network is employed as learning model 45 that realizes machine learning by machine learning unit 41b, but other machine learning models may also be employed. Examples of other machine learning models include tree-type models such as decision trees and regression trees, ensemble learning such as bagging and boosting, neural network-type models (including deep learning) such as recurrent neural networks, convolutional neural networks, and LSTM (Long Short Term Memory), clustering-type models such as hierarchical clustering, non-hierarchical clustering, k-nearest neighbors, and k-means, multivariate analyses such as principal component analysis, factor analysis, and logistic regression, and support vector machines.

[0204] Furthermore, in the above-described first and second embodiments, the preliminary customer extraction information may further include information acquired by the worker during sales activities related to the product. That is, the preliminary customer extraction information may include information acquired by the worker, i.e., a sales representative, through actual contact with customers, such as related new keywords and keywords related to the problem. The worker can input this information into the preliminary customer extraction device 50 using an input / output device.

[0205] Furthermore, in the above-described first and second embodiments, a machine learning method may be used as a method for outputting output data for each input data in the preliminary customer extraction device 50, the preliminary sales information device 100, and the sales target identification device 200. In this case, each output data may be output following the machine learning method and related processing implemented in the optimal sales guideline information output device 150.

[0206] That is, the processing by the viewed information processing device 20, the machine learning device 40, and the optimal sales guideline information output device 150, and the exchange of information between them, can be applied to the preliminary customer extraction device 50, the preliminary sales information device 100, and the sales target identification device 200. Specifically, in the preliminary customer extraction device 50 and the preliminary sales information device 100, learning models based on the respective input data and output data are prepared using a machine learning device, and the learning models can be used to output output data based on the input data.

[0207] In addition, in the above-mentioned first and second embodiments, any of the preliminary customer extraction device 50, preliminary sales information device 100, optimal sales guideline information output device 150, and sales target identification device 200 may be combined into one device. In that case, the combined device naturally satisfies the functions of the sales support system 1 described above.

[0208] The present disclosure can also be provided in the form of a program (machine learning program) that causes computer 900 to function as each part of machine learning device 40, or a program (machine learning program) that causes computer 900 to execute each step of a machine learning method.

[0209] The present disclosure can also be provided in the form of a program (optimal sales guideline information output program) that causes the computer 900 to function as each unit included in the optimal sales guideline information output device 150, or a program (optimal sales guideline information output program) that causes the computer 900 to execute each step included in the information processing method according to each of the above embodiments. The same applies to devices other than the optimal sales guideline information output device 150.

[0210] Furthermore, the present disclosure can be provided not only in the form of the optimum sales guideline information output device 150 (information processing method or information processing program) according to each of the above-described embodiments, but also in the form of an inference device (inference method or inference program) used to infer optimum sales guideline information. In this case, the inference device (inference method or inference program) can include a memory 914 and a processor 912, and the processor 912 can execute a series of processes.

[0211] The series of processes includes an information acquisition process (information acquisition step) for acquiring access source information and viewer interest information, and an inference process (inference step) for inferring optimal sales guideline information using the learning model 45 stored in the memory 914. When each output data is output by inference in a device other than the optimal sales guideline information output device 150, the same applies to the device other than the optimal sales guideline information output device 150.

[0212] By providing it in the form of an inference device (inference method or inference program), it can be easily applied to various devices. It is naturally understandable to those skilled in the art that when the inference device (inference method or inference program) infers optimal sales guideline information, the inference method implemented by the inference unit 151b may be applied using the machine learning device 40 according to the first embodiment and the trained learning model 45 generated by the machine learning method.

[0213] Although the preferred embodiments have been described in detail above, the present invention is not limited to the above-described embodiments, and various modifications and substitutions can be made to the above-described embodiments without departing from the scope of the claims.

[0214] Various aspects of the present disclosure are summarized below as appendices.

[0215] (Appendix 1) a reserve customer extraction device for extracting reserve customers who will be the target of sales activities for a product from among viewers who have viewed web content on the Internet, based on reserve customer input data consisting of access source information corresponding to one or more of the viewers, viewer interest information corresponding to the access source information, and reserve customer extraction information set for extracting the reserve customers, and for obtaining reserve customer output data consisting of reserve customer access source information, which is the access source information related to the reserve customers extracted from one or more of the access source information; a preliminary sales information device that outputs preliminary sales output data comprising preliminary sales information to the preliminary customers based on preliminary sales input data comprising the preliminary customer access source information; an optimum sales guideline information output device for determining sales guideline output data comprising optimum sales guideline information indicating a guideline for sales activities for the specific viewer, based on sales guideline input data comprising the access source information for the specific viewer and the viewer interest information corresponding to the access source information for the specific viewer, and for determining a guideline for sales activities for the specific viewer; Equipped with The access source information includes at least one of name information of the corresponding viewer, activity content information of the viewer, and industry information to which the viewer belongs, The viewer interest information is information representing the viewer's interests acquired based on one or more of the web contents viewed by the viewer corresponding to the access source information, The preliminary sales information is output in a form corresponding to at least one of the following: content of a programmatic advertisement for the viewer corresponding to the preliminary customer access source information, a message posted to an inquiry form, the text of an e-mail, a message in a telephone call, a message posted on a social networking service, and the text of a letter. Sales support system. (Appendix 2) The optimal sales guideline information further includes at least one of a sales recommendation level and a recommended sales technique, The sales recommendation level indicates a degree to which the sales activity is recommended to the viewer, The recommended sales method indicates a sales method recommended to the viewer. A sales support system as described in Appendix 1. (Appendix 3) A sales target specifying device is further provided which specifies sales target information from among the specific viewers based on the sales recommendation degree, The preliminary customer input data in the preliminary customer extraction device further includes the sales target information. A sales support system as described in Appendix 2. (Appendix 4) The name information indicates the name of the viewer or the name of an organization to which the viewer belongs, The activity content information indicates the content of social activities being carried out by the viewer or the organization, The industry information indicates an industry to which the viewer or the organization belongs, A sales support system according to any one of Supplementary Note 1 to Supplementary Note 3. (Appendix 5) Each of the viewer interest information includes at least one of title information, meta information, and keyword information; the title information, the meta information, and the keyword information are acquired from information of the web content viewed by the viewer; The title information indicates the title of the web content, The meta information is obtained from meta tags of the web content, The keyword information is a keyword extracted based on at least one of the title and the meta tag of the web content. A sales support system according to any one of Supplementary Note 1 to Supplementary Note 4. (Appendix 6) The preliminary customer extraction information includes related website information indicating URLs of web content related to the category to which the product belongs. A sales support system according to any one of Supplementary Note 1 to Supplementary Note 5. (Appendix 7) the preliminary sales input data in the preliminary sales information device further includes product information that is information about the product; The product information includes at least one of product page information indicating a website related to the product and contact information indicating a contact point for inquiries regarding the product. A sales support system according to any one of Supplementary Notes 1 to 6. (Appendix 8) The preliminary sales information includes the product information. A sales support system as described in Appendix 7. (Appendix 9) Each of the viewer interest information further includes viewing order information; The viewing order information indicates the order in which the viewers viewed the web content. A sales support system according to any one of Supplementary Notes 1 to 8. (Appendix 10) Each of the viewer interest information further includes view count information; The view count information is the number of times the web content has been viewed by the viewer within a predetermined period of time. A sales support system according to any one of Supplementary Notes 1 to 9. (Appendix 11) Each of the viewer interest information further includes viewing time information; The viewing time information is a total time that the web content was viewed by the viewer within a predetermined period. A sales support system according to any one of Supplementary Notes 1 to 10. (Appendix 12) When the sales guideline input data is input, the optimum sales guideline information output device determines the optimum sales guideline information using a learning model in which a correlation between the sales guideline input data and the sales guideline output data is learned by machine learning, and outputs the determined optimum sales guideline information as the sales guideline output data. A sales support system according to any one of Supplementary Note 1 to Supplementary Note 11. (Appendix 13) When the sales guideline input data is input, the optimum sales guideline information output device classifies the sales guideline input data based on predetermined rules, determines the optimum sales guideline information based on the classification, and outputs the determined optimum sales guideline information as the sales guideline output data. A sales support system according to any one of Supplementary Note 1 to Supplementary Note 11. (Appendix 14) a reserve customer extraction device for extracting reserve customers who will be the target of sales activities for a product from among viewers who have viewed web content on the Internet, the reserve customer extraction device obtaining reserve customer output data comprising reserve customer access source information, which is the access source information relating to the reserve customers extracted from one or more pieces of access source information, based on reserve customer input data comprising access source information corresponding to one or more of the viewers, viewer interest information corresponding to the access source information, and reserve customer extraction information set for extracting the reserve customers; The access source information includes at least one of name information of the corresponding viewer, activity content information of the viewer, and industry information to which the viewer belongs, The viewer interest information is information representing the viewer's interests acquired based on one or more of the web contents viewed by the viewer corresponding to the access source information. Sales support system. (Appendix 15) a preliminary sales information device that outputs preliminary sales output data that includes preliminary sales information for the preliminary customers based on preliminary sales input data that includes preliminary customer access source information that is access source information related to the preliminary customers who are the targets of sales activities for the merchandise among viewers who have viewed the web content on the Internet; The access source information includes at least one of name information of the corresponding viewer, activity content information of the viewer, and industry information to which the viewer belongs, The preliminary sales information is output in a form corresponding to at least one of the following: content of a programmatic advertisement for the viewer corresponding to the preliminary customer access source information, a message posted to an inquiry form, the text of an e-mail, a message in a telephone call, a message posted on a social networking service, and the text of a letter. Sales support system. [Explanation of symbols]

[0216] 1 Sales support system, 20 Viewing information processing device, 21 Recording device, 40 Machine learning device, 41 Machine learning control unit, 41a Learning data acquisition unit, 41b Machine learning unit, 42 Machine learning communication unit, 43 Learning data storage unit, 44 Machine learning model storage unit, 45 Learning model, 45a Input layer, 45b Intermediate layer, 45c Output layer, 46 Learning data, 50 Reserve customer extraction device, 51 Reserve customer extraction device control unit, 52 Reserve customer extraction device recording unit, 53 Reserve customer extraction device communication unit, 100 Reserve sales information device, 101 Reserve sales information device control unit, 102 Reserve sales information device recording unit, 103 Reserve sales information device communication unit, 150 Optimal sales guideline information output device, 151 Output device control unit, 151a Information acquisition unit, 151b Inference unit, 151c Output processing unit, 152 Output device recording unit, 153 Output device communication unit, 200 Sales target identification device, 201 Sales target identification device control unit, 202 Sales target identification device recording unit, 203 Sales target identification device communication unit, 500 Internet, 501 Web content, 510 Viewer, 511 Information terminal, 511a Screen, 570 Network, 900 Computer, 910 Bus, 912 Processor, 914 Memory, 916 Input device, 917 Output device, 918 Display device, 920 Storage device, 922 Communication interface unit, 924 External device interface unit, 926 Input / output device interface unit, 928 Media input / output unit, 930 Program, 940 Network, 950 External device, 960 Input / output device, 970 Media (non-transitory storage medium)

Claims

1. a reserve customer extraction device for extracting reserve customer input data consisting of access source information corresponding to one or more viewers, viewer interest information indicating the interests of the viewers obtained based on one or more web contents viewed by the viewers corresponding to the access source information, and reserve customer extraction information set for extracting the reserve customers, in order to extract reserve customer who will be the target of sales activities for a product from viewers who have viewed web contents on the Internet, the reserve customer extraction device extracting the viewer interest information corresponding to the reserve customer extraction information, and determining reserve customer output data using the access source information corresponding to the extracted viewer interest information as reserve customer access source information, which is the access source information related to the reserve customers; a preliminary sales information device that generates preliminary sales information for the preliminary customers based on preliminary sales input data consisting of the preliminary customer access source information, and outputs preliminary sales information for the preliminary customers in a format corresponding to at least one of programmatic advertising content for the viewers corresponding to the preliminary customer access source information, a message posted to an inquiry form, a message in an email, a message in a telephone call, a message posted on an SNS service, and a message in a letter, and outputs preliminary sales output data consisting of the preliminary sales information; an optimum sales guideline information output device for determining sales guideline output data comprising optimum sales guideline information indicating a guideline for sales activities for the specific viewer, based on sales guideline input data comprising the access source information for the specific viewer and the viewer interest information corresponding to the access source information for the specific viewer; Equipped with The access source information includes at least one of name information of the corresponding viewer, activity content information of the viewer, and industry information to which the viewer belongs, The viewer interest information is information representing the viewer's interests, which is obtained from information on one or more of the web contents viewed by the viewer corresponding to the access source information, and is at least one of title information indicating the title of the web content, meta information obtained from meta tags of the web content, and keyword information extracted based on at least one of the title of the web content and the meta tags; The preliminary customer extraction information is a keyword related to a category to which the product is related or a URL of a web page related to the product, The preliminary sales information is output in a form corresponding to at least one of the content of a programmatic advertisement for the viewer corresponding to the preliminary customer access source information, a message posted to an inquiry form, the text of an e-mail, a message in a telephone call, a message posted on an SNS service, and the text of a letter, and the optimal sales guideline information further includes a sales recommendation level indicating the degree to which the implementation of the sales activity is recommended for the viewer, and a recommended sales method indicating one of the sales methods recommended for the viewer, namely, a telecall, a sales posting to an inquiry form, sending a sales e-mail, sending a direct mail, and displaying an advertisement on a web browser of an information terminal used by the viewer, the optimum sales guideline information output device stores a learning model in which a correlation between the sales guideline input data and the sales guideline output data is learned by machine learning, the sales guideline input data is input to the learning model, and the optimum sales guideline information generated by the learning model is output as the sales guideline output data; Sales support system.

2. a reserve customer extraction device for extracting reserve customer input data consisting of access source information corresponding to one or more viewers, viewer interest information indicating the interests of the viewers obtained based on one or more web contents viewed by the viewers corresponding to the access source information, and reserve customer extraction information set for extracting the reserve customers, in order to extract reserve customer who will be the target of sales activities for a product from viewers who have viewed web contents on the Internet, the reserve customer extraction device extracting the viewer interest information corresponding to the reserve customer extraction information, and determining reserve customer output data using the access source information corresponding to the extracted viewer interest information as reserve customer access source information, which is the access source information related to the reserve customers; a preliminary sales information device that generates preliminary sales information for the preliminary customers based on preliminary sales input data consisting of the preliminary customer access source information, and outputs preliminary sales information for the preliminary customers in a format corresponding to at least one of programmatic advertising content for the viewers corresponding to the preliminary customer access source information, a message posted to an inquiry form, a message in an email, a message in a telephone call, a message posted on an SNS service, and a message in a letter, and outputs preliminary sales output data consisting of the preliminary sales information; an optimum sales guideline information output device for determining sales guideline output data comprising optimum sales guideline information indicating a guideline for sales activities for the specific viewer, based on sales guideline input data comprising the access source information for the specific viewer and the viewer interest information corresponding to the access source information for the specific viewer; Equipped with The access source information includes at least one of name information of the corresponding viewer, activity content information of the viewer, and industry information to which the viewer belongs, The viewer interest information is information representing the viewer's interests, which is obtained from information on one or more of the web contents viewed by the viewer corresponding to the access source information, and is at least one of title information indicating the title of the web content, meta information obtained from meta tags of the web content, and keyword information extracted based on at least one of the title of the web content and the meta tags; The preliminary customer extraction information is a keyword related to a category to which the product is related or a URL of a web page related to the product, The preliminary sales information is output in a form corresponding to at least one of the content of a programmatic advertisement for the viewer corresponding to the preliminary customer access source information, a message posted to an inquiry form, a message in an email, a message in a telephone call, a message posted on an SNS service, and a message in a letter, The optimum sales guideline information further includes a sales recommendation level indicating the degree to which the implementation of the sales activity is recommended to the viewer, and a recommended sales method indicating one of the following sales methods recommended to the viewer: telecalling, posting sales information to an inquiry form, sending sales e-mails, sending direct mail, and displaying advertisements on a web browser of an information terminal used by the viewer; When the sales guideline input data is input, the optimum sales guideline information output device classifies the sales guideline input data into one of four hierarchies based on a marketing funnel based on a predetermined rule, and outputs the optimum sales guideline information based on the degree of interest corresponding to the classification as the sales guideline output data. Sales support system.

3. A sales target identification device is further provided which generates sales target information which is information capable of identifying the specific viewer corresponding to the access source information extracted from the access source information related to the specific viewer based on the sales recommendation degree, The preliminary customer input data in the preliminary customer extraction device further includes the sales target information.

3. The sales support system according to claim 1.

4. The name information indicates the name of the viewer or the name of an organization to which the viewer belongs, The activity content information indicates the content of social activities being carried out by the viewer or the organization, The industry information indicates the industry to which the viewer or the organization belongs.

3. The sales support system according to claim 1.

5. the preliminary sales input data in the preliminary sales information device further includes product information that is information about the product; The product information includes at least one of product page information indicating a website related to the product and contact information indicating contact information for inquiries regarding the product.

3. The sales support system according to claim 1.

6. The preliminary sales information includes the product information. The sales support system according to claim 5.

7. Each of the viewer interest information further includes viewing order information; The viewing order information indicates the order in which the viewer viewed the web content.

3. The sales support system according to claim 1.

8. Each of the viewer interest information further includes view count information; The information on the number of times of viewing is the number of times the web content has been viewed by the viewer within a predetermined period of time.

3. The sales support system according to claim 1.

9. Each of the viewer interest information further includes viewing time information; The viewing time information is a total time that the web content was viewed by the viewer within a predetermined period of time.

3. The sales support system according to claim 1.

10. a reserve customer extraction device for extracting reserve customer input data consisting of access source information corresponding to one or more of the viewers, viewer interest information indicating the interests of the viewers obtained based on one or more of the web contents viewed by the viewers corresponding to the access source information, and reserve customer extraction information set for extracting the reserve customers, in order to extract reserve customer who will be the target of sales activities for a product from viewers who have viewed web contents on the Internet, the device extracting the viewer interest information corresponding to the reserve customer extraction information from reserve customer input data consisting of access source information corresponding to one or more of the viewers, viewer interest information indicating the interests of the viewers obtained based on one or more web contents viewed by the viewers corresponding to the access source information, and obtaining reserve customer output data using the access source information corresponding to the extracted viewer interest information as reserve customer access source information which is the access source information related to the reserve customers; The access source information includes at least one of name information of the corresponding viewer, activity content information of the viewer, and industry information to which the viewer belongs, The viewer interest information is information representing the viewer's interests, which is obtained from information on one or more of the web contents viewed by the viewer corresponding to the access source information, and is at least one of title information indicating the title of the web content, meta information obtained from meta tags of the web content, and keyword information extracted based on at least one of the title of the web content and the meta tags. Sales support system.

Images