JP2018106368A - Information processor, information processor control method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a mechanism capable of proposing an index to improve accuracy of determination when a company that handles products/services in various price zones conducts an attribution analysis.SOLUTION: An information processor manages the number of transitions indicating how many times a user transits to a specific landing page until a conversion by the user occurs and identification information which allows identification of whether a transition source to the specific landing page is an advertisement concerning a specific product. The information processor determines a weight for each transition source by using the number of transitions. The information processor calculates an evaluation value of the advertisement concerning a specific product identified by the identification information by using a weight for the transition source which is the advertisement and price information indicating the price of the specific product.SELECTED DRAWING: Figure 7

Description

  The present invention relates to an information processing apparatus, a control method for the information processing apparatus, and a program, and more particularly, to improve the accuracy of judgment when an enterprise that handles products and services in various price ranges performs attribution analysis. It relates to a mechanism that can propose indicators.

  Conventionally, there is a method called “attribution analysis” as a technique for measuring the effect of a digital advertisement displayed to a user on the Internet. In this method, when a user contacts (displays or clicks) a digital advertisement and conversion is performed later, the previous advertisement contact is evaluated as an “indirect effect on conversion”. Patent Document 1 discloses the mechanism of a system that realizes this technique.

Japanese Patent Laying-Open No. 2015-64782

  However, in Patent Document 1, when an advertiser handling products / services of various price ranges uses this mechanism, there is a possibility that the evaluation of each advertisement may be mistaken due to a difference in sales tendency due to a difference in price range. . For example, if seasonal factors and trends are not taken into account, low-priced products and services tend to be purchased more than high-priced products. Simply evaluate advertisements based on the number of items purchased. In other words, advertisements that appeal for low-priced products and services will inevitably get higher ratings.

  An object of the present invention is to provide a mechanism capable of proposing an index for improving the accuracy of judgment when a company handling goods / services in various price ranges performs attribution analysis.

  The present invention specifies the number of transitions indicating the number of times the user has transitioned to a predetermined landing page before conversion by the user and whether the transition source to the predetermined landing page is an advertisement related to a predetermined product Management means for managing possible specific information, determination means for determining a weight for each transition source to the predetermined landing page using the number of transitions managed by the management means, and among the transition sources, Using the weight determined by the determination unit for the transition source that is an advertisement related to the predetermined product specified by the specific information managed by the management unit, and the price information indicating the price of the predetermined product, And a calculating means for calculating an evaluation value of the advertisement.

  Further, according to the present invention, the number of transitions indicating the number of times the user has transitioned to a predetermined landing page before the conversion by the user occurs, and whether the transition source to the predetermined landing page is an advertisement related to a predetermined product A control method for an information processing apparatus comprising management means for managing specific information that can identify a predetermined landing using the number of transitions managed by the management means by the determination means of the information processing apparatus. The determination step of determining the weight for each transition source to the page and the calculation means of the information processing apparatus are advertisements related to a predetermined product specified by the specific information managed by the management means among the transition sources. The evaluation value of the advertisement is calculated using the weight determined in the determination step with respect to the transition source and the price information indicating the price of the predetermined product. Characterized in that it comprises a calculation step.

  Further, according to the present invention, the number of transitions indicating the number of times the user has transitioned to a predetermined landing page before the conversion by the user occurs, and whether the transition source to the predetermined landing page is an advertisement related to a predetermined product A program that can be read and executed by an information processing apparatus that includes a management unit that manages specific information that can be specified, and uses the number of transitions managed by the management unit to perform the predetermined landing A determining unit that determines a weight for each transition source to a page, and a transition unit that is an advertisement related to a predetermined product specified by the specific information managed by the management unit among the transition sources by the determining unit As a calculation means for calculating the evaluation value of the advertisement using the determined weight and the price information indicating the price of the predetermined product Characterized in that to ability.

  According to the present invention, it is possible to provide a mechanism capable of proposing an index for improving the accuracy of judgment when a company handling goods / services in various price ranges performs attribution analysis.

1 illustrates a system configuration diagram as an example of the present embodiment. 2 is a diagram illustrating an example of a hardware configuration of an information processing apparatus applicable to a management server 101 and a client terminal 102. FIG. It is a figure showing the access log data table assumed to be obtained with an access analysis tool etc. Represents the member registration product table that is required when the conversion is "member registration". It is a figure showing the product master which manages the sales amount for every product. It is a figure showing the advertisement delivery performance table which manages advertisement related data. It is a figure showing the algorithm of this embodiment. It is a figure showing the operation example of the algorithm of this embodiment. It is a figure showing the operation example of the algorithm of this embodiment. It is a figure showing the operation example of the algorithm of this embodiment. It is a figure showing the operation example of the algorithm of this embodiment. It is a figure showing the operation example of the algorithm of this embodiment. It is a figure showing the operation example of the algorithm of this embodiment. It is a figure showing the operation example of the algorithm of this embodiment. It is a figure showing the example of an output of this embodiment.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The embodiment described below shows an example when the present invention is specifically implemented, and is one of the specific embodiments having the configurations described in the claims.

  In addition, the following is a description of an embodiment mainly for digital advertising, but this analysis target may be another candidate such as an e-mail magazine or website content, and a plurality of analyzes depending on the analysis requirements. You may evaluate a target relatively.

  FIG. 1 is a system configuration diagram illustrating an example of the present embodiment. In the present embodiment, it is assumed that all data necessary for analysis is managed by the external memory 211 of the management server 101, the data extracted and processed from the management server 101 is output as advertisement evaluation data, and visualized by a data visualization tool. To do. Evaluators of measures including advertisers can judge whether measures are good or bad based on the visualized results.

  In this embodiment, the data (table) managed by the management server 101 includes “access log data table (FIG. 3)”, “member registration product table (FIG. 4)”, and “product master (FIG. 5)”. , “Advertisement delivery result table (FIG. 6)” exists.

  In the “access log data table”, an access log to each user's site obtained by analysis using an access analysis tool included in an external server is managed.

  In the “member registration product table”, information on products and services purchased by members of companies using the system is managed.

  The “product master” is a master in which an average selling price is recorded for each product handled by a company using this system.

  “Advertisement delivery result table” is a table that stores data obtained from an advertisement delivery tool of an external server. Data that is not stored in the access log table of FIG. Assume that it is stored.

  In this system, access information and purchase information (including product registration data for members to use various services and Web questionnaire data for purchasers) are used for purchases at actual stores as well as EC (electronic commerce) sites. Attribution analysis is also performed on products that have been analyzed. Specifically, it is as follows.

  (1) A list of persons to be analyzed is acquired from the table storing purchase information using the products / services, brand names, or product category types to be analyzed as extraction conditions. At this time, it is assumed that a cookie value or a user agent can be acquired as a unique ID for each person to be analyzed. However, if the site to be analyzed requires login in principle, the login ID may be substituted.

  (2) With respect to the list of analysis subjects in (1), using the unique ID (Cookie value or user agent) as a key, the behavior history in the site of the analysis subject (including inflow history such as advertisement inflow in addition to browsing history) To get. At this time, if the purpose is to measure the effect of the advertisement on the conversion, the acquired data may be only the action history before the CV date and time as in the general attribution analysis. When defining conversions using member registration information, note that the analyst has purchased the product / service (conversion has been achieved) before the date when the information was registered in the system. The action history of the analysis target person on the registered date needs to be dealt with such as being excluded from the target of attribution analysis. However, if the purchase date / time of a product / service can be acquired for each person to be analyzed using a receipt, questionnaire data, POS data, or the like, the purchase date / time may be used. In the present embodiment, “inflow” is also referred to as “transition”.

  (3) An attribution analysis score is calculated based on the behavior history of the analysis target person. At this time, as with general attribution analysis, the target of evaluation is a medium for attracting customers, but depending on the analysis requirements, the contact history of the advertisement (including the history of only displaying the advertisement in the browser in addition to the click of the advertisement) Or browsing history of web pages. Here, the “meeting medium for customers” is a general term for the trigger of inflow to advertisements, e-mail magazines, search engines and other sites. At this time, the score distribution method may be changed according to the characteristics and purpose of the advertisement to be analyzed. For example, in the case of an advertisement for the purpose of acquiring recognition, which is the first approach to the user, the evaluation is performed by a model in which the distribution ratio of the analysis subject's behavior history at the first time is increased. In addition, if the target advertisement is a target advertisement, such as a campaign announcement or a price appeal advertisement, which is an approach immediately before the purchase by the user, the evaluation is performed by a model in which the distribution ratio of the analysis target person immediately before the conversion is increased.

  (4) For each access log for which the score is calculated in (3), the sales price of the product / service purchased by the corresponding analysis target person is given as information, and the log is obtained by multiplying the score by the sales price. Calculate the sales amount at. For example, when the access log with a score of 0.1 is an access log of an analysis target person who purchased a product of 50,000 yen, the amount that the access log can contribute to sales is 0.1 × 50000 = 5000 It becomes.

  (5) The contribution amount for each access log calculated in (4) is accumulated for each advertisement. For example, if the advertisement A for cognitive purposes is the target of analysis, a single analyst is assigned a score of 0.9 if he / she clicks on the ad for the first time, and the analyst has purchased a product of 10,000 yen. Further, it is assumed that another analysis target person is assigned a score of 0.01 if the advertisement A is clicked immediately before the conversion, and the analysis target person purchases a product of 50,000 yen. In this case, the advertisement A for recognition purpose is evaluated to have a contribution amount of 0.9 × 10000 + 0.01 × 50000 = 9500.

(6) Visualize the result of (5). At this time, instead of visualizing only the contribution amount for each advertisement, an arrangement is made to reduce the risk of misjudgment by arranging the placement amount, clicks, bounce rate, etc. as the delivery result of the advertisement. In addition, it is possible to easily switch from a view with a large granularity such as a distribution destination medium and a distribution method (display advertisement, search-linked advertisement, etc) to a view with a fine granularity such as a target segment or a banner creative.

In this system, as the purchase information, “product registration data for use of various services by members and Web questionnaire data for purchasers” is taken as an example, but it is sufficient if the user can specify that the product has been purchased. As another embodiment, for example, when a user who has purchased a printer must always download software related to the printer from a predetermined site, the user who downloaded the software by accessing the predetermined site Attribution analysis may be performed using the access information. For example, when a user who purchased certain software installs the software on a PC and forcibly transitions to a predetermined web page, Subject to the transition to the web page, It may be carried out the attribution analysis using the seat of the access information.
This is the end of the description of FIG.

  Next, an example of the hardware configuration of the information processing apparatus applicable to the management server 101 and the client terminal 102 illustrated in FIG. 1 will be described with reference to FIG.

  In FIG. 2, reference numeral 201 denotes a CPU that comprehensively controls each device and controller connected to the system bus 204. In the ROM 202 or the external memory 211, a BIOS (Basic Input / Output System), an operating system program (hereinafter referred to as OS), which is a control program of the CPU 201, and various functions described later that are necessary for realizing the functions executed by the PC. Programs and so on are stored.

  A RAM 203 functions as a main memory, work area, and the like for the CPU 201. The CPU 201 implements various operations by loading a program necessary for execution of processing from the ROM 202 or the external memory 212 into the RAM 203 and executing the loaded program.

  An input controller 205 controls input from a pointing device such as a keyboard (KB) 209. A video controller 206 controls display on a display device such as a CRT display (CRT) 210.

  In FIG. 2, although described as CRT 210, the display device is not limited to the CRT, but may be another display device such as a liquid crystal display.

  A memory controller 207 is provided in an external storage device (hard disk (HD)), a flexible disk (FD), or a PCMCIA card slot for storing a boot program, various applications, font data, user files, editing files, various data, and the like. Controls access to an external memory 211 such as a compact flash (registered trademark) memory connected via an adapter.

  A communication I / F controller 208 connects and communicates with an external device via a network, and executes communication control processing on the network. For example, communication using TCP / IP is possible.

  Note that the CPU 201 enables display on the CRT 210 by executing outline font rasterization processing on a display information area in the RAM 203, for example. In addition, the CPU 201 enables a user instruction with a mouse cursor (not shown) on the CRT 210.

  Various programs to be described later for realizing the present invention are recorded in the external memory 211 and executed by the CPU 201 by being loaded into the RAM 203 as necessary. Further, a setting file used when executing the program is also stored in the external memory 211, and detailed description thereof will be described later.

  Now, an access log data table (FIG. 3), a member registration product table (FIG. 4), a product master (FIG. 5), and an advertisement distribution result table (FIG. 6) managed by the management server 101 of FIG. 1 will be described. .

  FIG. 3 is an example of an access log data table stored in the management server 101 in this embodiment. The first to tenth rows in the access log data table represent access logs by the same member (member identification ID: 12345678), and even for the same member, the device varies depending on the date and time, and is unique for each browser. This represents a situation where Cookie values are different.

  The browsing time 301 represents the time when the user accessed the website. The cookie value 302 represents the value of the cookie written in the user's browser, and is used to track the access log of the user who does not have the member identification ID 304.

  The device 303 represents a device used when the user accesses, and can take values such as a PC, a smartphone, and a tablet.

  The member identification ID 304 is a unique value for each user assigned when the user logs in to the member site, and the same value is stored if the same user is logged in even if the device used is different. Assuming

  A page URL 305 represents the URL of the Web page accessed by the user. The access order 306 represents the order of pages accessed within the same session. If the value is 1, the web page that is accessed first when a transition is made from an advertisement or mail magazine (called a landing page, abbreviated as LP). If the value is the largest in the same session, it is a leaving page.

  The advertisement ID 307 represents a URL parameter given to the URL at the time of transition from the advertisement when the access of the corresponding session is an inflow from the advertisement.

  These data are assumed to be data obtained with an access analysis tool. The 11th and 12th lines represent access logs by users who are not members, and when this user accesses the site later using another device or browser, it is difficult to make them the same person.

  The size of the access log data table can be very large depending on the target site, but in that case, it may take a long time to extract and process the data for the access log data table.

  In that case, it is only necessary to prepare a calculation table in which access logs after the date and time of conversion for each member are omitted by combining with a member registration product table described later in advance.

  FIG. 4 shows an example of a member registration product table in which products / services purchased by members are registered in a company member registration system. The example of FIG. 4 represents a situation in which two members register a total of three products in the system.

  The member identification ID 401 means the same as the member identification ID 304 in the access log data table of FIG. 3, and table join and data extraction are possible using this as a key.

  The registered product name 402 represents a product name registered in association with the user indicated by the member identification ID 401. The registration date 403 represents the date and time when the product was registered to the user.

  For example, when analyzing the member who registered the product aaa, the member identification ID: 12345678 is extracted from the member registration product table, and the log of the member can be extracted from the access log data table of FIG. 3 using the member identification ID 401 as a key. This is the end of the description of FIG. 4. Next, FIG. 5 will be described.

  FIG. 5 is an example of a product master in which the average selling price is recorded for each product. The product name 501 represents the name of a product handled by a company using this system, and the registered product name 402 in the member registered product table of FIG.

  The average selling price 502 represents the average selling price in the market for each product name 501, and it is assumed that the weekly average selling price corresponding to the week number 503 described later is stored.

  The week number 503 is a number assigned a serial number with “1W” as a week, and the product / service when the customer purchases using the week number 503 of the week including the purchase date acquired from the customer. Assume that the price of can be estimated. However, if the price does not fluctuate very much on a weekly basis, it may be on a monthly basis, or if the price fluctuates significantly, it may be on a daily basis. This is the end of the description of FIG. 5. Next, FIG. 6 will be described.

  FIG. 6 is a table storing data obtained from an advertisement distribution tool or the like, and it is assumed that data not stored in the access log table of FIG. 3 or data difficult to acquire with the access analysis tool is stored.

  The advertisement ID 601 means the same as the advertisement ID 307 in the access log data table in FIG. 3, and enables table combination and data extraction using this as a key.

  The responsible advertisement agency 602 places the corresponding advertisement using an advertisement distribution tool and represents the name of the advertisement agency to which the advertiser pays the advertisement cost. If there is only one advertising agency, there is no problem even if it is omitted.

The distribution media 603 represents the name of the site where the advertisement is actually displayed and the advertisement distribution tool itself. A distribution method 604 represents an advertisement distribution method, and may include a moving image advertisement displayed at the start of reproduction of a moving image in addition to the banner advertisement and the listing advertisement of FIG.
The targeting condition 605 represents the condition when the corresponding advertisement is displayed only to a limited user.

  The advertising device 606 represents the name of a device used as a condition for displaying the corresponding advertisement. When no device is used as a condition, it is assumed that NULL or ALL is stored. Further, it is assumed that the advertising device 606 does not necessarily match the device 303 in the access log data table of FIG.

  The display count 607 represents the number of times the corresponding advertisement is displayed. The number of clicks 608 represents the number of clicks on the corresponding advertisement. The cost 609 represents the amount paid as the expense of the corresponding advertisement.

  Since these data include data that is difficult to obtain only from the advertising distribution tool, prepare an environment where the advertiser can acquire these data by using an advertising agency or by using a third-party distribution tool. It will be necessary. The description of FIG. 6 has been completed, and the flowchart of the algorithm of the present embodiment will be described next with reference to FIG.

  FIG. 7 shows a flowchart of the algorithm of this embodiment, and FIG. 8 shows an example of its operation. In this example, a company that owns a member service sends sales data that is difficult to analyze linked to WEB access data generated at another company's EC site or other company's retail store to the customer's member site. It is assumed that analysis will be possible using the registered data.

  FIG. 8A represents an example of the operation of an algorithm when bbb is an analysis target among two representative products aaa and bbb handled by this company.

  In step S701, the management server 101 manages an access log data table (FIG. 3), a member registration product table (FIG. 4), a product master (FIG. 5), and an advertisement distribution result table (FIG. 5) managed by the external memory 211 of the management server 101. 6) is acquired.

  Step S701 is an advertisement related to a predetermined product in which the number of transitions indicating the number of times the user has transitioned to a predetermined landing page and the transition source to the predetermined landing page before the conversion by the user occurs in the present invention. It is an example of the management means which manages the specific information which can specify whether there exists.

  In step S702, the management server 101 extracts the member identification ID 401 from the member registration product table of FIG. 4 under the extraction condition “registered product name is XX”. At this time, if the period to be analyzed is limited, the condition “registration date is XXX / XXX to XX / XX” may be added to the extraction condition.

  In the example of FIG. 8A, the member identification ID 401 and the registration date 403 of two users whose member identification ID 401 is “12345678” and “1357911” are acquired based on the extraction condition “registered product name is bbb”.

  In step S703, the management server 101 uses the member identification ID 401 acquired in step S702 as a key, and displays the access data of the user who registered the product to be analyzed (hereinafter “product registrant”) as the access log data table in FIG. Extract from

  The access log data table before extraction is the upper diagram in FIG. 8B, and the extracted result is the lower diagram in FIG. 8B.

  At this time, in FIG. 8B (the same applies to FIGS. 8C to 8F), an intermediate table is prepared by adding the registration date 801 to the access log data table in order to simplify the processing in step S704 described later. The registration date 801 does not need to be added to the access log data table as long as it is a method of referring to the member registration product table of FIG. 4 each time.

  In the example of FIG. 8B (the same applies to FIGS. 8C to 8F), only the user with the member identification ID 304 “12345678” (hereinafter “bbb purchaser”) is shown for simplification, and the member identification ID 304 is “1357911”. It is assumed that no access log appears for the user “”.

  In step S704, the management server 101 uses the registration date 403 of “product registrant” from the registration date 801 in the access log data table in the upper part of FIG. 8B of “product registrant” acquired in step S703 as a condition. Access log data of “product registrant” dated before 403 is acquired. The purpose of this analysis is to measure the effectiveness of digital advertising, which is thought to have contributed to the conversion of the measure, and to optimize the cost allocation of the advertisement using the result, and the access log after the conversion is not necessary for the analysis.

  In the access log data table in the upper part of FIG. 8C (the same as the access log data table in the lower part of FIG. 8B), the data below the sixth line in the access log data table acquired in step S703 is “product registrant”. Since it is data after “2016/10/19” which is the registration date 403 of “bbb purchaser”, it is excluded by filtering. The result of exclusion by filtering is the access log data table in the lower part of FIG. 8C.

  In step S <b> 705, the management server 101 determines the landing page based on the condition that “the access order 306 is 1” from the access log data acquired in step S <b> 704 before the registration date 801 (registration date 403). Get the access log data. This is because, in this analysis, the evaluation target is a medium for attracting customers including digital advertisements, so access logs other than landing pages are not necessary for the analysis.

  In the example of the access log data table in the upper part of FIG. 8D (the same as the access log data table in the lower part of FIG. 8C), the fourth line “the access order 306 is not 1” among the five lines of data acquired in step S704. And the access log data on the fifth line are excluded by filtering. The result of exclusion by filtering is the access log data table in the lower part of FIG. 8D.

  In step S706, the management server 101 counts the number of inflows for each “product registrant” with respect to the inflow data of the access log data before the registration date 801 (registration date 403) of “product registrant” acquired in step S705. The attribution analysis score using (the number of rows in the access log data table in the lower part of FIG. 8D) is calculated.

  Step S706 is an example of a determination unit that determines the weight for each transition source to the predetermined landing page using the number of transitions managed by the management unit in the present invention.

  In the example of the access log data table in FIG. 8E (the inflow count 802 and the score 803 added to the lower access log data table in FIG. 8D), the inflow count 802 of “bbb purchaser” is 3, so each access The log score 803 (evaluation when the contribution degree of each access log is calculated by equal distribution) is 1/3. The above is an evaluation when the contribution degree of each access log is calculated by equal distribution without weighting according to the order of inflow, etc., but the score calculation method may be changed depending on the characteristics and purpose of the advertisement. For example, if you want to evaluate an advertisement whose main purpose is recognition acquisition, you can increase the score closer to the first inflow.

  In step S707, the management server 101 calculates the estimated value of the sales price that contributed to each access log in this analysis by multiplying the score 803 for each access log data calculated in step S706 by the sales price of the product / service. To do.

  The sales price is extracted by referring to the product master table of FIG. 5 and using the product name 501 as a key. At this time, if a product / service with a large price fluctuation range is handled, the week number (month or The estimated value of the average selling price at the date and time when the product / service to be analyzed is purchased may be used.

  In step S707, the weight determined by the determining unit with respect to the transition source that is an advertisement related to the predetermined product specified by the specific information managed by the management unit among the transition sources in the present invention, It is an example of a calculation unit that calculates an evaluation value of the advertisement using price information indicating a price of a predetermined product.

  In the example of the access log data table in FIG. 8F (in which the week number 804, the sales price 805, and the score × sales price 806 are added to the access log data table in FIG. 8E), the date portion of the registration date 801 is “2016/10”. / 19 ”is converted to week number 804“ 60W ”, and“ 3500 ”of average selling price 502 is extracted from the product master table using the week number 804 as a key (average selling price of week number 503 that matches the week number 804) 502 is extracted) and added to the selling price 805.

  After that, the “score” “0.33” given to the three rows of the access log data of “bbb purchaser” is multiplied by “3500” of the selling price 805 (average selling price 502). Score × sales price 806 “1155” is calculated.

  In step S708, the management server 101 extracts the access log data that is an inflow from the advertisement out of the score × sales price 806 calculated in step S707 and the corresponding access log data by referring to the advertisement ID 307, The advertisement ID 307 is used as a key to link with the advertisement distribution log table of FIG. 6, and the score × sales price 806 and the advertisement distribution result are combined to generate advertisement evaluation data. FIG. 8G shows the result of combining the score × sales price 806 and the actual result of advertisement distribution.

  The distribution medium 807 in FIG. 8G corresponds to the distribution medium 603 in FIG. 6, the advertisement ID 808 corresponds to the advertisement ID 307 and the advertisement ID 601, and the score × sales price 809 corresponds to the score × sales price 806.

  In addition, by assigning the advertising cost (cost 609) (the result of the grant is cost 810), an index of score × sales price / cost 811 is calculated. With this index, it is possible to express how efficiently the sales amount of the advertisement can be obtained.

  Note that the provision of the cost 609 is not essential in the present invention, but if the cost 609 is not given, the sales will increase as the advertising cost is increased. In particular, there is a problem that it is difficult to use as an index for evaluating efficiency. Therefore, it is more preferable to consider the cost 609 as an index for evaluating the efficiency.

  As for the score × sales price 809 and the score × sales price 806 for the advertisement ID 808 other than the advertisement ID 808 of “ad_1”, the result of applying the algorithm shown in FIGS. 8A to 8F to other advertisement IDs 808 is registered. .

  Finally, the client terminal 102 captures the advertisement evaluation data into a data visualization tool, and creates a dashboard for analysis. The use of data visualization tools is not required, but assume that you have a dashboard that allows you to make better decisions while looking at advertisements at various granularities.

  In the example of FIG. 8, as shown in “* image”, the result with the fine granularity of advertisement ID 808 (upper figure of FIG. 8G) or the result with the granularity of distribution medium 807 (lower figure of FIG. 8G) It represents a dashboard that can easily do that.

  FIG. 9 is an example when the output result by the above-described algorithm is visualized by the data visualization tool of the client terminal 102.

  In the example of FIG. 9, the advertiser has requested advertisements to the two responsible advertising agencies 901 “Company A” and “Company B”, and the advertiser verifies the effectiveness of the advertisement after the end of the advertisement distribution period. Assume that you are trying.

  FIG. 9 shows three patterns of screen transitions in the data visualization tool, with the top level indicating the finest granularity state and the bottom level indicating the coarsest granularity state. The advertiser determines how best to change the advertising agency and advertisement distribution conditions in order to maximize the cost effectiveness while appropriately changing the data granularity of the three patterns.

  In FIG. 9, for the sake of simplification, the advertising agency 901, the distribution medium 902, the distribution method 903, and the cost 904 are shown as the distribution results of the advertisement, and the score 905, the score × the selling price 906, and the score as the result of the attribution analysis. X Sales price / cost 907 is displayed.

  These items may be added or deleted as appropriate according to the analysis requirements. For example, as the delivery data of advertisements, the name of the product to be promoted, targeting conditions, delivery time, delivery device, banner creative, impressions, clicks, bounce rate, new rate, conversions (directly connected to purchase) Conversion rate (candidate conversions not directly connected to purchase), and attribution analysis results in score / impressions, score / clicks, sales price, etc. Etc.

  As described above, according to the present invention, it is possible to provide a mechanism capable of proposing an index for improving the accuracy of judgment when a company handling goods / services in various price ranges performs attribution analysis.

  In other words, in the present invention, by multiplying the sales of a user whose advertisement exists in the log by the score in the attribution analysis of the advertisement, it is possible to propose an index related to sales in consideration of the efficiency of the advertisement.

  In addition, in the present invention, by using registered information of a member held by a company or information (ex. Questionnaire) as an alternative to the registered information, even a product purchased at an actual store has its purchase date (receipt). The method of using the sales price closer to the actual sales price for the analysis, assuming that it is possible to acquire the name of the store or the purchased shop name etc. Can also be proposed.

  The present invention can be implemented as a system, apparatus, method, program, storage medium, or the like, and can be applied to a system including a plurality of devices. You may apply to the apparatus which consists of one apparatus.

  Note that the present invention includes a software program that implements the functions of the above-described embodiments directly or remotely from a system or apparatus. The present invention also includes a case where the system or the computer of the apparatus is achieved by reading and executing the supplied program code.

  Accordingly, since the functions of the present invention are implemented by computer, the program code installed in the computer also implements the present invention. In other words, the present invention includes a computer program itself for realizing the functional processing of the present invention.

  In that case, as long as it has the function of a program, it may be in the form of object code, a program executed by an interpreter, script data supplied to the OS, and the like.

  Examples of the recording medium for supplying the program include a flexible disk, hard disk, optical disk, magneto-optical disk, MO, CD-ROM, CD-R, and CD-RW. In addition, there are magnetic tape, nonvolatile memory card, ROM, DVD (DVD-ROM, DVD-R), and the like.

  As another program supply method, a browser on a client computer is used to connect to an Internet home page. The computer program itself of the present invention or a compressed file including an automatic installation function can be downloaded from the homepage by downloading it to a recording medium such as a hard disk.

  It can also be realized by dividing the program code constituting the program of the present invention into a plurality of files and downloading each file from a different homepage. That is, a WWW server that allows a plurality of users to download a program file for realizing the functional processing of the present invention on a computer is also included in the present invention.

  In addition, the program of the present invention is encrypted, stored in a storage medium such as a CD-ROM, distributed to users, and key information for decryption is downloaded from a homepage via the Internet to users who have cleared predetermined conditions. Let It is also possible to execute the encrypted program by using the downloaded key information and install the program on a computer.

  Further, the functions of the above-described embodiments are realized by the computer executing the read program. In addition, based on the instructions of the program, an OS or the like running on the computer performs part or all of the actual processing, and the functions of the above-described embodiments can also be realized by the processing.

  Further, the program read from the recording medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer. Thereafter, the CPU of the function expansion board or function expansion unit performs part or all of the actual processing based on the instructions of the program, and the functions of the above-described embodiments are realized by the processing.

  The above-described embodiments are merely examples of implementation in carrying out the present invention, and the technical scope of the present invention should not be construed as being limited thereto. That is, the present invention can be implemented in various forms without departing from the technical idea or the main features thereof.

101 Management server 102 Client terminal

Claims (6)

Specific information that can specify the number of transitions that indicate the number of times the user has transitioned to a predetermined landing page before conversion by the user and whether the transition source to the predetermined landing page is an advertisement related to a predetermined product Management means for managing
Determining means for determining a weight for each transition source to the predetermined landing page using the number of transitions managed by the management means;
Among the transition sources, a weight that is determined by the determination unit with respect to the transition source that is an advertisement related to the predetermined product specified by the specific information managed by the management unit, and a price that indicates the price of the predetermined product An information processing apparatus comprising: calculation means for calculating an evaluation value of the advertisement using information.   The calculation means includes a weight determined by the determination means for a transition source that is an advertisement related to the predetermined product, price information indicating a price of the predetermined product, and an advertisement cost required for the advertisement. The information processing apparatus according to claim 1, wherein an evaluation value of the advertisement is calculated using the. The management means manages the order of transition to the predetermined landing page of the transition source,
The determining unit further determines a weight for each transition source to the predetermined landing page using an order of the transition source managed by the management unit and the transition to the predetermined landing page. The information processing apparatus according to claim 1 or 2.   4. The determination unit according to claim 3, wherein the determination unit determines to increase a weight of a transition source having the earliest order of transition to the predetermined landing page among the transition sources managed by the management unit. Information processing device. Specific information that can specify the number of transitions that indicate the number of times the user has transitioned to a predetermined landing page before conversion by the user and whether the transition source to the predetermined landing page is an advertisement related to a predetermined product A method of controlling an information processing apparatus comprising a management means for managing
A determination step in which the determination unit of the information processing apparatus determines a weight for each transition source to the predetermined landing page, using the number of transitions managed by the management unit;
The weight determined in the determination step for the transition source, which is an advertisement related to the predetermined product specified by the specific information managed by the management unit, among the transition sources, by the calculation unit of the information processing apparatus And a calculation step of calculating an evaluation value of the advertisement using price information indicating a price of the predetermined product. Specific information that can specify the number of transitions that indicate the number of times the user has transitioned to a predetermined landing page before conversion by the user and whether the transition source to the predetermined landing page is an advertisement related to a predetermined product A program that can be read and executed by an information processing apparatus including a management means for managing
The information processing apparatus;
Determining means for determining a weight for each transition source to the predetermined landing page using the number of transitions managed by the management means;
Among the transition sources, a weight that is determined by the determination unit with respect to the transition source that is an advertisement related to the predetermined product specified by the specific information managed by the management unit, and a price that indicates the price of the predetermined product A program that functions as calculation means for calculating an evaluation value of the advertisement using the information.

Images