JP2018109865A - Information processor and information processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processor capable of distributing advertisements corresponding to user hierarchy, and an information processing method.SOLUTION: The information processor includes a conversion user log extraction part, a route extraction part, a setting part, a communication part, an estimation part, an advertisement determination part and a determined advertisement transmission part. The conversion user log extraction part extracts a conversion user log of each user who completed a conversion. The route extraction part extracts behaviors that each user performs until the conversion and a transition route of the behaviors on the basis of the conversion user log. The setting part sets a behavior rate of behaviors per hierarchy of a funnel structure on the basis of the behaviors and the transition route of the behaviors. When receiving an advertisement request from a user terminal, the estimation part estimates a user hierarchy of the user terminal on the basis of the behavior rate. The advertisement determination part determines an advertisement corresponding to the hierarchy. The determined advertisement transmission part transmits the advertisement.SELECTED DRAWING: Figure 1

Description

  Embodiments described herein relate generally to an information processing apparatus and an information processing method for estimating a user's funnel structure on the Internet or the like.

  The user has a predetermined intent regarding conversion of a predetermined advertisement distributed on the Web, and belongs to various hierarchies (cognition, interest / interest, examination, immediately before, etc.) based on the intent. The distribution of users in each hierarchy has a funnel structure. From the advertiser's perspective, it is important to correctly evaluate the value of the delivered advertisement and to optimize the composition of the advertisement, such as the content and quantity of the advertisement, and it is necessary to know the funnel structure as the premise. .

  Conventionally, however, an analog method such as a questionnaire is used to visualize the funnel structure. Analog methods such as questionnaires are expensive and it is difficult to obtain a sufficient amount of data. In addition, objective information is not always obtained, for example, a questionnaire includes an answer based on misperception or an answer that makes the person look good.

  Therefore, a technique for estimating the user hierarchy in the funnel structure from an access log on the Internet is required.

  The user needs different information depending on the hierarchy to which the user belongs. Therefore, a technology for distributing different advertisements for each hierarchy is required.

Special table 2014-512613 gazette

  In order to solve the above-described problems, an information processing apparatus and an information processing method capable of distributing an advertisement according to a user hierarchy are provided.

  According to the embodiment, the information processing apparatus includes a conversion user log extraction unit, a route extraction unit, a setting unit, a communication unit, an estimation unit, an advertisement determination unit, and a determined advertisement transmission unit. The conversion user log extraction unit extracts a conversion user log of a user who has completed the conversion. The route extraction unit extracts, based on the conversion user log, an action performed by the user who has completed the conversion until the conversion and a transition route of the action. The setting unit sets a behavior ratio of the behavior for each hierarchy of the funnel structure based on the behavior extracted by the route extraction unit and the transition route of the behavior. The communication unit transmits and receives data. When the estimation unit receives an advertisement request from the user terminal through the communication unit, the estimation unit estimates a user hierarchy of the user terminal based on the behavior ratio. The advertisement determining unit determines an advertisement corresponding to the hierarchy. The determined advertisement transmission unit transmits the advertisement through the communication unit.

  According to the embodiment, the information processing apparatus can model the funnel hierarchy (generate a hierarchy table and a transfer probability table) based on the action log of the user who has completed the conversion. Further, the information processing apparatus can estimate the hierarchy of users who have not completed conversion by modeling the funnel structure.

  That is, the information processing apparatus can estimate the number of users for each level and the transfer probability between levels. Therefore, the above estimation makes it possible to estimate the volume for each tier and which tier will expand or contract in the future.

  Further, the information processing apparatus can estimate the funnel structure of the user who has viewed the advertisement and the funnel structure of the user who has not viewed the advertisement. Therefore, the information processing apparatus can present the advertising effect as a difference between both funnel structures. For example, if the number of users at a specific level of the funnel structure of the user who viewed the advertisement increases and the level immediately above (for example, “recognition” if the specific level is “interest / interest”) decreases, Is estimated to have an effect of transitioning the user from the immediately higher hierarchy to the specific hierarchy.

  Further, the information processing apparatus estimates both funnel structures after the advertisement distribution. Both funnels are affected by factors other than advertising (for example, TV commercials), but it is assumed that there is no difference (or the difference is sufficiently small) in the degree of influence that both funnels are receiving. Can do. Therefore, the difference between both funnels is not affected by factors other than advertising. Therefore, it can be determined that the difference between the two funnels is caused by browsing the advertisement. As a result, the effect of the advertisement can be grasped more clearly.

  In addition, the information processing apparatus can distribute a plurality of advertisements at random and measure the effect of each hierarchy. As a result, the information processing apparatus can determine an effective advertisement for each hierarchy.

  In addition, when the information processing apparatus receives an advertisement request from the user terminal, the information processing apparatus estimates the user hierarchy of the user terminal. The information processing device delivers an advertisement corresponding to the estimated hierarchy to the user terminal. As a result, the information processing apparatus can distribute an optimal advertisement to the user.

FIG. 1 is a diagram illustrating a configuration example of a funnel structure according to the embodiment. FIG. 2 is a block diagram illustrating a configuration example of the information processing apparatus according to the embodiment. FIG. 3 is a diagram illustrating an example of category transition according to the embodiment. FIG. 4 is a diagram illustrating an example of category transition according to the embodiment. FIG. 5 is a hierarchy table according to the embodiment. FIG. 6 is a transfer probability table according to the embodiment. FIG. 7 shows a transition example of the funnel structure according to the embodiment. FIG. 8 is a flowchart illustrating an operation example of the information processing apparatus according to the embodiment. FIG. 9 is a flowchart illustrating an operation example of the information processing apparatus according to the embodiment. FIG. 10 is a flowchart illustrating an operation example of the information processing apparatus according to the embodiment. FIG. 11 is a flowchart illustrating an operation example of the information processing apparatus according to the embodiment. FIG. 12 is a flowchart illustrating an operation example of the information processing apparatus according to the embodiment.

Hereinafter, embodiments will be described with reference to the drawings.
First, the funnel structure will be described.
FIG. 1 shows a configuration example of the funnel structure 1.

The funnel structure 1 indicates the number of users for each hierarchy related to conversion of a predetermined advertisement.
A conversion is the final result of an advertisement run by an advertiser. For example, the conversion is purchase of a predetermined article, request for data, browsing a predetermined site, or visiting a predetermined store. The content of the conversion is not limited to a specific configuration.
The advertisement is presented to the user through the user terminal.

  As shown in FIG. 1, the funnel structure 1 includes layers 2 to 6 and the like. Levels 2 to 6 are, for example, “recognition”, “interest / interest”, “examination”, “immediately before”, and “conversion”. In the example illustrated in FIG. 1, the larger the hierarchy area, the greater the number of users. The funnel structure 1 may not include “conversion” as a hierarchy.

  “Recognition” is a hierarchy that recognizes matters related to results. For example, when the conversion is a purchase of a predetermined product, “recognition” is a hierarchy that recognizes the product as a matter related to the result. Further, when the conversion is browsing of an event notification site, “recognition” is a hierarchy that recognizes the event or the like as a matter related to the result.

  “Interest / interest” is a level in which the person is interested in matters related to the results. In other words, “interest / interest” is a level that has a certain interest / interest in matters related to the results, although it is not just about considering conversion.

  “Review” is a hierarchy in which conversion is being considered. In other words, “examination” is a hierarchy in which it is considered to perform conversion beyond mere interest.

  “Just before” is a hierarchy immediately before conversion. That is, “immediately before” is a hierarchy in which the consideration of conversion is finished and it is determined to perform conversion.

  “Conversion” is a hierarchy in which a conversion is completed.

  In the example shown in FIG. 1, the number of users decreases as the hierarchy increases from “recognition”, “interest / interest”, “examination”, “immediately before”, and “conversion”.

  Note that the funnel structure may further include other layers. Further, the funnel structure may not include the above-described hierarchy. Also, the number of funnel structure layers is not limited to a specific number. The configuration of the funnel structure is not limited to a specific configuration.

Next, the information processing apparatus according to the embodiment will be described.
FIG. 2 is a block diagram illustrating a configuration example of the information processing apparatus 10.
In the configuration example illustrated in FIG. 2, the information processing apparatus 10 includes a CPU 11, a ROM 12, a RAM 13, an NVM 14, a communication unit 15, an operation unit 16, a display unit 17, and the like as basic configurations. These units are connected to each other via a data bus. Note that the information processing apparatus 10 may include a configuration as necessary in addition to the configuration illustrated in FIG. 2 or may exclude a specific configuration.

  The CPU 11 has a function of controlling the overall operation of the information processing apparatus 10. The CPU 11 may include an internal cache and various interfaces. The CPU 11 implements various processes by executing programs stored in advance in the internal memory, the ROM 12 or the NVM 14.

  Note that some of the various functions realized by the CPU 11 executing the program may be realized by a hardware circuit. In this case, the CPU 11 controls functions executed by the hardware circuit.

  The ROM 12 is a non-volatile memory in which a control program and control data are stored in advance. The control program and control data stored in the ROM 12 are incorporated in advance according to the specifications of the information processing apparatus 10. The ROM 12 stores, for example, a program (for example, BIOS) that controls the circuit board of the information processing apparatus 10.

  The RAM 13 is a volatile memory. The RAM 13 temporarily stores data being processed by the CPU 11. The RAM 13 stores various application programs based on instructions from the CPU 11. The RAM 13 may store data necessary for executing the application program, an execution result of the application program, and the like.

  The NVM 14 is a nonvolatile memory capable of writing and rewriting data. The NVM 14 is configured by, for example, a hard disk, SSD, EEPROM (registered trademark), flash memory, or the like. The NVM 14 stores a control program, an application, and various data according to the operational use of the information processing apparatus 10.

  In addition, the NVM 14 includes a storage area 14a for storing an action log that is a record of a user browsing the site, and a storage area 14b for storing an effect log indicating the effect of the advertisement. The action log and the effect log will be described later.

  The communication unit 15 is an interface for transmitting and receiving data to and from an external device through a communication network such as the Internet. The communication unit 15 is an interface that supports LAN connection, for example.

  The communication unit 15 transmits and receives data to and from the user terminal 20 through a communication network. The user terminal 20 is a terminal used by the user. For example, the user terminal 20 is a desktop PC, a notebook PC, a tablet PC, a smartphone, or the like. The user terminal 20 requests an advertisement from the information processing apparatus 10 and displays the advertisement.

  Various operation instructions are input to the operation unit 16 by the operator of the information processing apparatus 10. The operation unit 16 transmits an operation instruction signal input to the operator to the CPU 11. The operation unit 16 is, for example, a keyboard, a numeric keypad, and a touch panel.

  The display unit 17 is a display device that displays various information under the control of the CPU 11. The display unit 17 is, for example, a liquid crystal monitor. When the operation unit 16 is configured with a touch panel or the like, the display unit 17 may be formed integrally with the operation unit 16.

Next, the action log will be described.
The behavior log is a log related to the user's behavior. For example, the behavior log stores information indicating behavior and the date and time when the behavior is performed in association with each other.

  For example, actions targeted by the action log include Web access, user location, content listening, healthcare information, purchasing, SNS posting, application use, content viewing, or operation of devices owned by the user. .

  Web access is, for example, a search keyword, a browsing site, text in content, an image or video, a click, a mouse-over, or a heat map.

  The location of the user is, for example, GPS information such as a smartphone possessed by the user, an IP address of the smartphone, a store visit by a beacon, or entrance / exit of an automatic ticket gate.

The content listening is, for example, music listening or radio listening.
Health care information is information about the user's body. Health care information is, for example, exercise, blood pressure, or heart rate.

Purchase is the purchase of an item that does not result in a conversion. For example, the purchase is settlement with electronic money or purchase at an EC site.
The posting to the SNS is, for example, posting of text, an image, or a moving image to the SNS site.

Application use includes, for example, downloading an application, starting an application, using an application, or deleting an application.
The content viewing is, for example, television viewing or moving image viewing on a moving image site or the like.

The operation of the device possessed by the user is, for example, the operation of a smart home appliance, the driving of an automobile, automatic driving, or communication between devices.
The behavior targeted by the behavior log is not limited to a specific configuration.

Next, functions realized by the CPU 11 will be described.
First, the CPU 11 has a function of extracting a behavior log (conversion user log) of a user who has completed conversion (conversion user log extraction unit).
The CPU 11 extracts, from the storage area 14a, an action log of the user who has completed the conversion, and an action log which has been given for a predetermined period from the date and time when the conversion was completed. For example, the CPU 11 extracts an action log 30 days, 60 days, or 90 days before the conversion is completed. CPU11 may determine the period which speaks based on conversion. For example, the CPU 11 may set a relatively long period for a conversion (for example, purchase of a high-priced product) that seems to take time to make a decision. In addition, for example, the CPU 11 may set a relatively short period for conversion that can be determined in a short period (for example, purchase of a low-priced product). The method for determining the period during which the CPU 11 extracts the action log is not limited to a specific method.

The CPU 11 has a function of specifying a user's behavior after conversion and a route along which the behavior transitions based on the extracted behavior log (route extraction unit).
For example, the CPU 11 sets a category for the extracted action log.
The category is set based on the feature of the action. The category may be set manually for each action in advance. The category may be automatically set by the CPU 11 according to a predetermined algorithm. The method for setting the category in the action log is not limited to a specific method.

  For example, a category is a set of Web sites viewed by a user. For example, a category is a collection of websites related to specific content. For example, the category is “usually used media” or “related product information”.

  “Usual media” is a site that users use on a daily basis. For example, “usually used media” includes a search engine or a portal site.

  “Related product information” is a site that is strongly related to conversion. For example, when the conversion is purchase of a product, the “related product information” is a critique site for the product or an introduction site for a product similar to the product.

  A category is a set of user locations. For example, the category indicates a specific area where the user is located, such as a predetermined store, a building, or a park. For example, the category is “convenience store”.

  “Convenience store” indicates that the user has entered a specific or arbitrary convenience store.

  A category is a set relating to user healthcare. For example, the category is a classification related to blood pressure. For example, the category is “high blood pressure”, “low blood pressure”, “average blood pressure”, or the like.

“High blood pressure” indicates that the user has a blood pressure value higher than a predetermined threshold value.
“Low blood pressure” indicates that the user has a blood pressure value lower than a predetermined threshold value.
“Average blood pressure” indicates that the user's blood pressure value does not belong to either “high blood pressure” or “low blood pressure”.
Note that the CPU 11 does not have to set a category in the action log. Moreover, CPU11 does not need to set a category to some action logs and to set a category to another action log.

  Next, the CPU 11 extracts what behavior the user who has completed the conversion has changed to reach the conversion. That is, the CPU 11 extracts the behavior that the user who has completed the conversion characteristically performs, and extracts the transition path of the behavior.

  For example, the CPU 11 extracts an action (or category) particularly performed by the user who has completed the conversion. Moreover, CPU11 calculates the transition probability between each action. That is, the CPU 11 calculates the probability of performing another action after the user who has completed the conversion performs a certain action.

  The CPU 11 sets a path as a transition route between the actions based on the transition probability between the actions. For example, the CPU 11 may set a path between actions whose transition probability is higher than a predetermined threshold. Further, the CPU 11 may set paths with different thicknesses between actions (that is, paths with different intensities) according to the transition probability.

  For example, the CPU 11 may extract an action performed by a user who has completed the conversion using a Bayesian network and extract a transition path of the action leading to the conversion.

3 and 4 show an example of the transition of the behavior of the user who has completed the conversion.
Here, it is assumed that the CPU 11 has extracted the actions 21 to 25. Actions 21 to 24 are categories. Actions 21 to 24 are “usually used media”, “high blood pressure”, “convenience store”, and “related product information”, respectively. The action 25 is “application DL”.

“Daily media”, “High blood pressure”, “Convenience store”, and “Related product information” are as described above.
“App DL” indicates an action of downloading a specific app.

  3 and 4, arrows indicate paths. That is, the arrow indicates that the user transitions from the action at the start point of the arrow to the action at the end point of the arrow.

  As shown in FIGS. 3 and 4, one of the transition paths that the user leads to conversion is a path that sequentially follows action 21 (“usually used media”), action 24 (“related product information”), and “conversion”. is there. Further, another one of the transition paths leading to the conversion by the user follows action 21 (“usually used media”), action 23 (“convenience store”), action 24 (“related product information”), and “conversion” in this order. It is a route.

  In addition, another transition path through which the user leads to conversion is a path that sequentially follows action 21 (“usually used media”), action 23 (“convenience store”), and “conversion”. Further, another one of the transition paths leading to conversion by the user is action 21 (“usually used media”), action 22 (“hypertension”), action 23 (“convenience store”), action 24 (“related product information”). ) And “conversion” in order.

  In addition, another transition path leading to the conversion by the user is a path that follows action 21 (“usually used media”), action 22 (“hypertension”), action 23 (“convenience store”), and “conversion” in this order. is there.

  In addition, another one of the transition paths leading to conversion by the user is a path that sequentially follows action 21 (“usually used media”), action 22 (“hypertension”), action 25 (“application DL”), and “conversion”. It is.

  Note that the number of actions extracted by the CPU 11 is not limited to a specific number. The configuration of actions extracted by the CPU 11 is not limited to a specific configuration. Further, the route extracted by the CPU 11 is not limited to a specific configuration.

  Moreover, CPU11 has a function which sets the action ratio of the extracted action (or category) for every hierarchy of funnel structure (setting part). The action ratio is the ratio of the users who perform the extracted action in the hierarchy or the probability that each user takes the action in the hierarchy.

For example, the CPU 11 generates a table (hierarchy table) that associates the hierarchy of the funnel structure with the action ratio of each action in the hierarchy.
FIG. 5 shows a configuration example of a hierarchy table in which a funnel structure hierarchy and an action ratio of actions in the hierarchy are associated with each other.

  As shown in FIG. 5, in the hierarchy table, in “recognition”, the behavior ratios of “usually used media”, “high blood pressure”, “convenience store”, “related product information”, and “application DL” are 77% and 10%, respectively. 7%, 3% and 3%. For example, the hierarchy table indicates that 77% of the users belonging to “recognition” perform actions belonging to “usually used media”.

  In addition, in the hierarchy table, in “interest / interest”, the behavior ratios of “ordinary media”, “hypertension”, “convenience store”, “related product information” and “application DL” are 45%, 15% and 17%, respectively. , 15% and 8%.

  In the “review”, the hierarchy table indicates that the behavior ratios of “usually used media”, “high blood pressure”, “convenience store”, “related product information”, and “application DL” are 10%, 17%, 35%, 28, respectively. % And 10%.

  In the hierarchy table, the action ratios of “ordinary media”, “hypertension”, “convenience store”, “related product information”, and “application DL” are 6%, 19%, 25%, and 35, respectively, immediately before. % And 15%.

  In addition, each action which CPU11 sets for every hierarchy and the ratio of each action are not limited to a specific value. That is, the configuration of the hierarchy table set by the CPU 11 is not limited to a specific configuration.

  In addition, the CPU 11 has a function of calculating a probability that a user belonging to each layer moves to each layer after a predetermined period based on behavior and a transition route (transition probability) between the behaviors (transfer probability calculation unit). That is, the CPU 11 calculates the transfer probability between tiers. For example, the CPU 11 generates a table (transfer probability table) in which a funnel structure hierarchy and a probability that a user in the hierarchy moves to each hierarchy after a predetermined period of time. Note that the transfer probability table includes the probability that the user stays in the hierarchy.

  FIG. 6 shows a configuration example of a transfer probability table in which a funnel structure layer is associated with a probability that a user in the layer moves to each layer after a predetermined period.

  As shown in FIG. 6, the transfer probability table shows that the users belonging to “recognition” are 80% each for “recognition”, “interest / interest”, “review”, “immediately”, and “conversion”. %, 3%, 15% and 0% probability of transfer. In addition, the transfer probability table indicates that users belonging to “interest / interest” are 81%, 5%, 14%, and 0% for “interest / interest”, “examination”, “immediately”, and “conversion” after a predetermined period, respectively. It indicates that it will move with the probability of. Further, the transfer probability table indicates that users belonging to “review” move to “review”, “immediately”, and “conversion” after a predetermined period with a probability of 79%, 21%, and 0%, respectively. The transfer probability table indicates that users belonging to “immediately before” move to “immediately” and “conversion” after a predetermined period with a probability of 87% and 13%, respectively.

  The probability that the CPU 11 is calculated for each hierarchy is not limited to a specific value. That is, the configuration of the transfer probability table calculated by the CPU 11 is not limited to a specific configuration.

For example, the CPU 11 generates a hierarchy table and a transfer probability table as follows.
The CPU 11 assumes the number of layers until “conversion” and the probability of transferring from each layer to the next layer. According to the assumption, the CPU 11 continuously evaluates to which hierarchy a certain user belongs and the probability of transition to the next hierarchy, and generates a hierarchy table and a transfer probability table.

For example, the CPU 11 generates a hierarchy table and a transfer probability table according to a hidden Markov model or the like.
Note that the method for generating the hierarchy table and the transfer probability table is not limited to a specific method.

The CPU 11 has a function of extracting an action log (unconverted user log) of a user whose conversion has not been completed.
CPU11 extracts the action log of the user who has not completed conversion from the storage area 14a. Note that the CPU 11 may further extract an action log within a predetermined period from the action log of a user who has not completed conversion.

  Moreover, CPU11 has a function which estimates the hierarchy of each user who has not completed conversion from the action log and hierarchy table of the user who have not completed conversion.

CPU11 estimates a hierarchy for every user based on the extracted action log. For example, the CPU 11 extracts an action log including an action indicated by the hierarchy table from an action log of a certain user. CPU11 matches the action which the extracted action log shows, and each action ratio of a hierarchy table. The CPU 11 estimates the layer that best matches the user's behavior as the layer to which the user belongs.
CPU11 performs said operation | movement for every user, and estimates the hierarchy of each user.

  Moreover, CPU11 has a function which estimates a funnel structure from each user's hierarchy. For example, the CPU 11 counts the number of users for each hierarchy, and estimates the number of users belonging to each hierarchy as a funnel structure. Further, for example, the CPU 11 may estimate the funnel structure at a rate for each layer. The CPU 11 may add “conversion”, which is a hierarchy of users who have completed the conversion, to the funnel structure.

  Moreover, CPU11 has a function which estimates the funnel structure which the user who browsed the predetermined | prescribed advertisement comprises, and the funnel structure which the user who is not browsing the said advertisement comprises. Here, it is assumed that the advertiser has distributed a predetermined advertisement on a predetermined Web. FIG. 7 shows a configuration example of the funnel structure 1a of the user who has viewed the advertisement and the funnel structure 1b of the user who has not viewed the advertisement.

  CPU11 extracts the action log (browsing user log) of the user who has not completed conversion and browsed the advertisement from the storage area 14a. For example, CPU11 extracts the user who has the action log which shows having browsed the said advertisement, and extracts the said user's action log.

  CPU11 estimates the hierarchy of each user who browsed the said advertisement from the extracted action log and hierarchy table. CPU11 estimates the funnel structure 1a of the user who browsed the said advertisement based on an estimation result. The CPU 11 may add, to the funnel structure 1a, the level of the user who has viewed the advertisement and completed the conversion as the “conversion” level.

  Moreover, CPU11 extracts the action log (non-browsing user log) of the user who has not completed conversion and is not browsing the advertisement from the storage area 14a. For example, the CPU 11 extracts a user having an action log indicating that the advertisement has been browsed, and extracts an action log other than the user.

  CPU11 estimates the hierarchy of each user who is not browsing the said advertisement from the extracted user's action log and hierarchy table. CPU11 estimates the funnel structure 1b of the user who is not browsing the said advertisement based on an estimation result. The CPU 11 may add the level of the user who has not viewed the advertisement and completed the conversion as the “conversion” level to the funnel structure 1b.

  With the above operation, as shown in FIG. 7, after the advertisement is distributed, the CPU 11 can estimate the funnel structure 1a of the user who has viewed the advertisement and the funnel structure 1b of the user who has not viewed the advertisement. In addition, CPU11 may classify | categorize a user for every frequency | count of browsing an advertisement, and may estimate the funnel structure for every browsing frequency.

Moreover, CPU11 has a function which acquires the effect log for every advertisement (effect log acquisition part).
The effect log is a log indicating the effect of the advertisement. For example, the effect log is composed of the hierarchy of the user who presented the advertisement, the advertisement ID that identifies the advertisement, and the effect information indicating the effect. The effect information indicates the effect of the advertisement. For example, the effect information is information indicating whether the purpose of the advertisement has been achieved. For example, the effect information is information indicating whether conversion corresponding to the advertisement has been performed. The effect information may be information indicating whether an advertisement is clicked.

  CPU11 distributes a plurality of advertisements to a user at random. For example, the CPU 11 receives an advertisement request from the user terminal 20 through the communication unit 15. The advertisement request may be transmitted, for example, when the user terminal 20 executes predetermined html or the like.

When the CPU 11 receives the request from the user terminal 20, the CPU 11 estimates the user hierarchy of the user terminal 20. When the user hierarchy is estimated, the CPU 11 randomly selects one advertisement from a plurality of advertisements (selection unit). For example, the plurality of advertisements may be advertisements having different elements such as a placement surface, a format, a size, or a creative. For example, the CPU 11 may select one advertisement from a plurality of advertisements whose elements such as the placement surface, format, size, or creative are individually controlled.
The CPU 11 transmits the selected advertisement as a response to the request to the user terminal 20 (selected advertisement transmission unit).

  CPU11 monitors a user's operation for a predetermined period after transmitting an advertisement to user terminal 20 (monitoring part). For example, based on a signal from the user terminal 20, the CPU 11 monitors behavior such as whether the user clicked on an advertisement or conversion from the advertisement. For example, CPU11 acquires the action log which shows a user's action after transmitting an advertisement to user terminal 20. The CPU 11 generates effect information based on the monitoring result.

  CPU11 produces | generates an effect log (effect log production | generation part). For example, the CPU 11 generates an effect log that stores the user hierarchy, the advertisement ID that identifies the advertisement distributed to the user, and the generated effect information. The effect log may further store a user ID that identifies the user. The CPU 11 stores the generated effect log in the storage area 14b.

Next, the CPU 11 has a function of determining an effective advertisement (an advertisement corresponding to each hierarchy) based on the effect log (optimization unit).
For example, the CPU 11 acquires a plurality of effect logs from the storage area 14b. When acquiring a plurality of effect logs, the CPU 11 classifies the effect logs for each hierarchy. CPU11 calculates the result rate for every advertisement based on the effect information of the effect log classified into a certain hierarchy. The result rate is a rate at which the purpose of the advertisement is achieved with respect to the number of displayed ads. For example, the result rate is a rate at which an advertisement is clicked (click rate) or a rate at which conversion is achieved (conversion rate). Further, the result rate may be a probability (transition rate) that the user's hierarchy changes after the advertisement is clicked.

For example, the CPU 11 counts the number of effect logs classified into the hierarchy and the number of effect logs having effect information indicating that the purpose has been achieved. The CPU 11 calculates the advertising result rate from both numbers.
The CPU 11 determines an advertisement with the highest result rate as an effective advertisement for the hierarchy.
CPU11 performs the same operation | movement about each hierarchy, and determines an effective advertisement for every hierarchy.

Further, the CPU 11 has a function of distributing advertisements according to the hierarchy of users (for example, users who have not completed conversion).
For example, the CPU 11 receives a request from the user terminal 20. CPU11 will estimate the hierarchy of the user who transmitted the said request, if a request is received (estimation part). For example, the CPU 11 acquires the action log of the user. CPU11 determines the hierarchy of the said user by matching the action which the said action log shows, and each action ratio of a hierarchy table. The estimation of the hierarchy is as described above.

  The CPU 11 may determine the level of each user in advance and store it in the NVM 14. The CPU 11 may determine the hierarchy of the user who transmitted the request with reference to the NVM 14.

  CPU11 determines the advertisement according to the determined user's hierarchy (advertisement determination part). For example, the NVM 14 stores a hierarchy and an advertisement in association with each other in advance. The CPU 11 refers to the NVM 14 and acquires an advertisement corresponding to the determined user hierarchy. The CPU 11 transmits the acquired advertisement to the user terminal 20 through the communication unit 15 (determination advertisement transmission unit).

  The advertisement associated with the hierarchy may be an effective advertisement determined based on the effect log. The advertisement associated with the hierarchy may be an advertisement determined by an operator.

Next, an operation example of the information processing apparatus 10 will be described.
First, an operation example in which the information processing apparatus 10 estimates the funnel structure will be described.
FIG. 8 is a flowchart for explaining an operation example in which the CPU 11 of the information processing apparatus 10 estimates the funnel structure.

  First, the CPU 11 extracts the action log of the user who has completed the conversion over a predetermined period from the storage area 14a (S11). When the behavior log of the user who has completed the conversion is extracted, the CPU 11 extracts a behavior (or category) and a transition path between the behaviors based on the extracted behavior log (S12).

  When the behavior and the transition route between the behaviors are extracted, the CPU 11 generates a hierarchy table based on the behavior and the transition route between the behaviors (S13). When the hierarchy table is generated, the CPU 11 generates a relocation probability table based on actions and transition paths between actions (S14).

  When the transfer probability table is generated, the CPU 11 extracts an action log of a user who has not completed conversion (S15). When the behavior log of the user who has not completed the conversion is extracted, the CPU 11 estimates the hierarchy of each user who has not completed the conversion based on the extracted behavior log and the hierarchy table (S16).

  If the hierarchy of each user who has not completed conversion is estimated, CPU11 will estimate a funnel structure based on an estimation result (S17). When the funnel structure is estimated, the CPU 11 ends the operation.

  Next, an operation example in which the information processing apparatus 10 estimates the funnel structure of the user who has viewed the advertisement and the funnel structure of the user who has not viewed the advertisement will be described.

FIG. 9 is a flowchart for explaining an operation example in which the CPU 11 of the information processing apparatus 10 estimates the funnel structure of the user who has viewed the advertisement and the funnel structure of the user who has not viewed the advertisement.
Here, it is assumed that the CPU 11 has finished generating the hierarchy table.

  First, the CPU 11 extracts, from the storage area 14a, an action log of a user who has not completed conversion and has viewed an advertisement (S21). When the action log is extracted, the CPU 11 estimates the hierarchy of each user who viewed the advertisement based on the hierarchy table (S22).

  When the hierarchy of each user who has viewed the advertisement is estimated, the CPU 11 estimates the funnel structure of the user who has viewed the advertisement based on the estimation result (S23). If the funnel structure of the user who has viewed the advertisement is estimated, the CPU 11 extracts from the storage area 14a the action log of the user who has not completed the conversion and has not viewed the advertisement (S24).

  When the action log is extracted, the CPU 11 estimates the hierarchy of each user who is not browsing the advertisement based on the hierarchy table (S25). If the hierarchy of each user who is not browsing advertisements is estimated, CPU11 will estimate the funnel structure of the user who is not browsing advertisements (S26).

  When the funnel structure of the user who is not browsing the advertisement is estimated, the CPU 11 ends the operation.

Next, an operation example in which the information processing apparatus 10 acquires an effect log will be described.
FIG. 10 is a flowchart for explaining an operation example in which the CPU 11 of the information processing apparatus 10 acquires the effect log.

  First, the CPU 11 determines whether an advertisement request is received from the user terminal 20 through the communication unit 15 (S31). If it determines with not having received the request (S31, NO), CPU11 will return to S31.

  If it determines with having received the request (S31, YES), CPU11 will estimate the hierarchy of the user of the user terminal 20 which transmitted the said request (S32). When the user hierarchy is estimated, the CPU 11 randomly selects one advertisement from a plurality of advertisements (S33).

  When one advertisement is selected, the CPU 11 transmits the selected advertisement to the user terminal 20 through the communication unit 15 (S34). When the selected advertisement is transmitted to the user terminal 20, the CPU 11 monitors the operation of the user (S35).

  When the user operation is monitored, the CPU 11 generates an effect log based on the user hierarchy determined in S32, the advertisement ID of the advertisement selected in S33, and the monitoring result in S35 (S36).

  When the effect log is generated, the CPU 11 stores the generated effect log in the storage area 14b (S37). When the effect log is stored, the CPU 11 ends the operation.

Next, an operation example in which the information processing apparatus 10 determines an effective advertisement will be described.
FIG. 11 is a flowchart for explaining an operation example in which the CPU 11 of the information processing apparatus 10 determines an effective advertisement.

  First, the CPU 11 acquires a plurality of effect logs from the storage area 14b (S41). When acquiring a plurality of effect logs, the CPU 11 sets a hierarchy for determining an effective advertisement (S42).

  When the hierarchy is set, the CPU 11 calculates a result rate for each advertisement in the hierarchy (S43). After calculating the result rate for each advertisement, the CPU 11 determines an effective advertisement for the hierarchy based on the result rate for each advertisement (S44).

  When the effective advertisement is determined, the CPU 11 determines whether there is another hierarchy for determining the effective advertisement (S45). When it is determined that there is another hierarchy for determining an effective advertisement (S45, YES), the CPU 11 returns to S43. If it is determined that there is no other hierarchy that determines an effective advertisement, the CPU 11 ends the operation.

Next, an operation example in which the information processing apparatus 10 distributes an advertisement according to the user's hierarchy will be described.
FIG. 12 is a flowchart for explaining an operation example in which the CPU 11 of the information processing apparatus 10 distributes an advertisement corresponding to a user's hierarchy.

  First, the CPU 11 determines whether an advertisement request is received from the user terminal 20 through the communication unit 15 (S51). If it is determined that the request has not been received (S51, NO), the CPU 11 returns to S51.

  If it determines with having received the request (S51, YES), CPU11 will estimate the hierarchy of the user of the user terminal 20 which transmitted the request (S52). When the user hierarchy is estimated, the CPU 11 determines an advertisement corresponding to the hierarchy (S53).

  When the advertisement corresponding to the hierarchy is determined, the CPU 11 transmits the determined advertisement to the user terminal 20 through the communication unit 15 (S54). When the determined advertisement is transmitted to the user terminal 20, the CPU 11 ends the operation.

  Note that the CPU 11 may acquire an action log or an effect log from an external device. Further, the CPU 11 may display data indicating the number of users in each layer on the display unit 17 as a funnel structure. Further, the CPU 11 may transmit data indicating the funnel structure to the external device through the communication unit 15 or the like.

  In addition, this invention is not limited to the said embodiment, In the implementation stage, it can change variously in the range which does not deviate from the summary. In addition, the embodiments may be appropriately combined as much as possible, and in that case, the combined effect can be obtained. Further, the above embodiments include inventions at various stages, and various inventions can be extracted by appropriately combining a plurality of disclosed constituent elements. For example, even if some constituent requirements are deleted from all the constituent requirements shown in the embodiment, the problem described in the column of the problem to be solved by the invention can be solved, and the effect described in the column of the effect of the invention Can be obtained as an invention.

  DESCRIPTION OF SYMBOLS 1 (1a and 1b) ... Funnel structure, 2 thru | or 6 ... hierarchy, 10 ... Information processing apparatus, 11 ... CPU, 12 ... ROM, 13 ... RAM, 14 ... NVM, 14a and 14b ... Storage area, 15 ... Communication part, 16 ... operation unit, 17 ... display unit, 20 ... user terminal.

Claims (10)

A conversion user log extractor for extracting a conversion user log of a user who has completed the conversion;
A route extracting unit that extracts an action to be performed by the user who has completed the conversion until the conversion and a transition route of the action based on the conversion user log;
Based on the behavior extracted by the route extraction unit and the transition route of the behavior, a setting unit that sets the behavior ratio of the behavior for each hierarchy of funnel structure;
A communication unit for transmitting and receiving data;
Upon receiving an advertisement request from a user terminal through the communication unit, an estimation unit that estimates a user hierarchy of the user terminal based on the behavior ratio;
An advertisement determining unit that determines an advertisement corresponding to the hierarchy;
A determined advertisement transmitting unit that transmits the advertisement through the communication unit;
An information processing apparatus comprising: further,
Based on the behavior extracted by the route extraction unit and the transition path of the behavior, a transfer probability calculation unit that calculates a transfer probability that a user belonging to each layer of the funnel structure moves to each layer,
The information processing apparatus according to claim 1. The conversion user log extraction unit extracts, as the conversion user log, an action log that has been given for a predetermined period from the date and time when the conversion is completed.
The information processing apparatus according to claim 1 or 2. The estimation unit matches the behavior indicated by the behavior log of the user and the behavior ratio to estimate the hierarchy of the user.
The information processing apparatus according to any one of claims 1 to 3. An effect log acquisition unit for acquiring an effect log indicating the effect of the advertisement;
An optimization unit that determines an advertisement corresponding to each hierarchy based on the effect log;
With
The advertisement determination unit determines the advertisement determined by the optimization unit as an advertisement corresponding to the hierarchy;
The information processing apparatus according to any one of claims 1 to 4. The effect log includes effect information indicating whether the purpose of the advertisement has been achieved,
The optimization unit calculates, for each advertisement, a result rate that is a rate at which the purpose of the advertisement is achieved with respect to the number of displayed advertisements, based on the effect information of the effect log classified into a certain hierarchy. Determining an advertisement corresponding to the hierarchy based on,
The information processing apparatus according to claim 5. The performance rate is at least one of an ad click rate, a conversion rate, or a transition rate,
The information processing apparatus according to claim 6. Upon receiving the request through the communication unit, a selection unit that selects one advertisement from a plurality of advertisements;
A selection advertisement transmission unit that transmits the advertisement selected by the selection unit through the communication unit;
A monitoring unit that acquires a behavior log of the user of the user terminal after the selection advertisement transmission unit transmits the advertisement;
Based on the action log acquired by the monitoring unit, an effect log generation unit that generates the effect log;
Comprising
The information processing apparatus according to any one of claims 5 to 7. The conversion is at least one of purchasing a predetermined product, requesting materials, browsing a predetermined site, or visiting a predetermined store.
The information processing apparatus according to any one of claims 1 to 8. Extract conversion user logs of users who have completed conversions,
Based on the conversion user log, the behavior that the user who has completed the conversion performs until the conversion and the transition path of the behavior are extracted,
Based on the behavior and the transition path of the behavior, setting the behavior ratio of the behavior for each hierarchy of funnel structure,
When receiving a request for an advertisement from a user terminal, the hierarchy of the user of the user terminal is estimated based on the action ratio,
Determine an advertisement corresponding to the hierarchy,
Send the advertisement,
Information processing method.