JP6683558B2 - Information processing apparatus and information processing method - Google Patents

Description

  Embodiments of the present invention relate to an information processing apparatus and an information processing method for estimating a funnel structure of a user 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, consideration, immediately before, etc.) based on the intent and the like. The distribution of users in each layer 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 amount of the advertisement, and it is necessary to know the funnel structure as a premise. .

  However, conventionally, in order to visualize the funnel structure, an analog method such as a questionnaire has been used. Analog methods such as questionnaires are costly and it is difficult to collect a sufficient amount of data. In addition, objective information is not always obtained in the questionnaire, including answers based on misidentifications or answers that try to make oneself look good.

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

Japanese Patent Publication No. 2014-512613

  In order to solve the above problems, an information processing apparatus and an information processing method for estimating a funnel structure are provided.

According to the embodiment, the information processing device that estimates the funnel structure is a conversion user log extraction unit, a route extraction unit, a setting unit, an unconverted user log extraction unit, a layer estimation unit, and a structure estimation unit. Equipped with. The conversion user log extraction unit extracts a conversion user log of a user who has completed conversion. The route extraction unit extracts, based on the conversion user log, a category that the user who has completed the conversion browses until the conversion and a transition route of the category. The setting unit sets the browsing ratio of the category for each hierarchy of the funnel structure based on the category extracted by the route extracting unit and the transition route of the category . The unconverted user log extraction unit extracts an unconverted user log of a user who has not completed the conversion. The tier estimation unit estimates the tier of the user who has not completed the conversion, based on the unconverted user log and the browsing ratio of the category. The structure estimation unit estimates the funnel structure based on the estimation result of the hierarchy estimation unit.

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

  That is, the information processing apparatus can estimate the number of users for each layer and the transfer probability between layers. Therefore, by the above estimation, it is possible to estimate the volume for each tier and which tier will be expanded or reduced in the future.

  In addition, the information processing apparatus can estimate the funnel structure of the user who has browsed the advertisement and the funnel structure of the user who has not browsed the advertisement. Therefore, the information processing device can present the advertising effect as the difference between the funnel structures. For example, if the number of users at a specific layer of the funnel structure of the user who viewed the advertisement is increasing and the level immediately above (for example, “cognition” if the specific layer is “interest”), the advertisement is Is estimated to have the effect of causing the user to transition from the layer directly above to the specific layer.

  Further, the information processing apparatus estimates both funnel structures after the advertisement distribution. As a result, it is possible to cancel the difference caused by the other elements (for example, TV commercial) with respect to the difference between the funnel structures. Therefore, the effect of the advertisement can be grasped more clearly.

FIG. 1 is a diagram showing a configuration example of a funnel structure according to an embodiment. FIG. 2 is a block diagram showing a configuration example of the information processing apparatus according to the embodiment. FIG. 3 is a diagram showing an example of category transition according to the embodiment. FIG. 4 is a diagram showing an example of category transition according to the embodiment. FIG. 5 is a hierarchy table according to the embodiment. FIG. 6 is a transition 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 showing an operation example of the information processing apparatus according to the embodiment. FIG. 9 is a flowchart showing 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.

Funnel structure 1 indicates the number of users for each tier associated with conversion of a given advertisement.
Conversions are the final product of advertising performed by advertisers. For example, the conversion is a purchase of a predetermined product, a request for materials, a browsing of a predetermined site, or the like. The content of the conversion is not limited to a specific configuration.

  As shown in FIG. 1, the funnel structure 1 includes layers 2 to 6 and the like. Layers 2 to 6 are “cognition”, “interest / interest”, “examination”, “immediately before”, and “conversion”, respectively. In the example shown in FIG. 1, the larger the hierarchical area, the more users. The funnel structure 1 does not have to include “conversion” as a hierarchy.

  “Cognition” is a layer that recognizes matters related to conversion results. For example, when the conversion is the purchase of a predetermined product, “recognition” is a layer that recognizes the product as a matter related to the result. Further, when the conversion is browsing of the event notification site, “cognition” is a layer in which the event or the like is recognized as a matter related to the result.

  The “interest / interest” is a layer that is interested or interested in a matter related to the result. In other words, “interest / interest” is a layer that has a certain level of interest / interest in a matter related to the result, although it is not enough to consider conversion.

  “Review” is the hierarchy under consideration for conversion. That is, the “examination” is a layer that considers performing conversion beyond mere interest.

  "Immediately before" is a layer immediately before conversion. That is, "immediately before" is a layer in which the examination of conversion has been completed and it has been decided to perform conversion.

  “Conversion” is a layer that has completed conversion.

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

  Note that the funnel structure may further include other layers. In addition, the funnel structure does not have to include the above hierarchy. Further, the number of layers of the funnel structure is not limited to a specific number. The configuration of the funnel structure is not limited to a particular configuration.

Next, the information processing apparatus according to the embodiment will be described.
FIG. 2 is a block diagram showing a configuration example of the information processing device 10.
In the configuration example illustrated in FIG. 2, the information processing device 10 includes, as a basic configuration, 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. These respective units are connected to each other via a data bus. Note that the information processing apparatus 10 may have a configuration as necessary in addition to the configuration shown in FIG. 2 or may exclude a specific configuration.

  The CPU 11 has a function of controlling the operation of the entire information processing device 10. The CPU 11 may include an internal cache and various interfaces. The CPU 11 realizes various processes by executing a program 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 the function executed by the hardware circuit.

  The ROM 12 is a non-volatile memory in which control programs 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 device 10. The ROM 12 stores, for example, a program (for example, BIOS) that controls the circuit board of the information processing device 10.

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

  The NVM 14 is a non-volatile memory in which data can be written and rewritten. The NVM 14 is composed of, 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 device 10.

  The NVM 14 also includes a storage area 14a that stores a Web browsing log that is a record of a user browsing the site. For example, the Web browsing log includes a user, a visited site (for example, URL), a browsed date and time, and the like.

  The communication unit 15 is an interface for transmitting / receiving data to / from an external device through the communication network 5. The communication unit 15 is, for example, an interface that supports LAN connection.

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

  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 or the like. When the operation unit 16 is composed of a touch panel or the like, the display unit 17 may be formed integrally with the operation unit 16.

Next, the functions realized by the CPU 11 will be described.
First, the CPU 11 has a function (conversion user log extraction unit) for extracting a web browsing log (conversion user log) of a user who has completed conversion.
The CPU 11 extracts, from the storage area 14a, the web browsing log of the user whose conversion has been completed, which is a web browsing log that has been delayed for a predetermined period from the date and time when the conversion was completed. For example, the CPU 11 extracts a Web browsing log 30 days, 60 days, or 90 days before the conversion is completed. The CPU 11 may determine the period to be delayed based on the 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. Further, for example, the CPU 11 may set a relatively short period for conversions that can be decided in a short period of time (for example, purchase of low-priced products). The method by which the CPU 11 determines the period for extracting the web browsing log is not limited to a specific method.

The CPU 11 has a function (route extraction unit) that specifies a category of a site browsed by a user who has completed conversion and a route through which the category transits based on the extracted Web browsing log.
The CPU 11 sets a category for the extracted web browsing log site.
Categories are set based on the characteristics of the site. The site category may be manually set in advance for each site. The category of the site may be automatically set by the CPU 11 according to a predetermined algorithm. The method of setting a category for a site is not limited to a specific method.

  Next, the CPU 11 extracts what category the user who has completed the conversion transits to reach the conversion. That is, the CPU 11 extracts a category characteristically viewed by the user who has completed the conversion, and extracts a transition path of the category.

  For example, the CPU 11 extracts a category that the user who completed the conversion particularly browses. Further, the CPU 11 calculates the transition probability between categories. That is, the CPU 11 calculates the probability that a user who has completed conversion browses a site of a certain category and then browses a site of another category.

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

  For example, the CPU 11 may use the Bayesian network to extract the categories browsed by the user who has completed the conversion, and may extract the transition paths of the categories leading to the conversion.

3 and 4 show transition examples of categories of users who have completed conversion.
Here, it is assumed that the CPU 11 has extracted categories 21 to 24. Categories 21 to 24 are “usually used media”, “life change”, “beauty and health”, and “related product information”, respectively.

  The “usually used media” are sites that users use on a daily basis. For example, "usually used media" includes a search engine or a portal site.

  The “life change” is a site browsed when the user's life changes or is about to change. For example, “life change” includes sites related to moving and the like.

  “Beauty and health” is a site related to beauty or health. For example, “beauty and health” includes sites related to cosmetics or health foods.

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

  In FIGS. 3 and 4, arrows indicate paths. That is, the arrow indicates that the user makes a transition from the category at the start point of the arrow to the category at the end point of the arrow.

  As shown in FIG. 3 and FIG. 4, one of the transition paths leading to conversion by the user is a path that sequentially follows category 21 (“usually used media”), category 24 (“related product information”), and “conversion”. is there. In addition, another one of the transition paths leading to conversion by the user is category 21 (“usually used media”), category 23 (“beauty and health”), category 24 (“related product information”), and “conversion” in order. This is the route to follow. Further, another one of the transition paths leading to conversion by the user is a path that sequentially follows category 21 (“usually used media”), category 23 (“beauty and health”), and “conversion”. In addition, another one of transition paths leading to conversion by the user is category 21 (“usually used media”), category 22 (“life change”), category 23 (“beauty and health”), category 24 (“related products”). Information ”) and“ conversion ”. In addition, another one of the transition paths leading to conversion by the user is to sequentially follow category 21 (“usually used media”), category 22 (“life change”), category 23 (“beauty and health”), and “conversion”. It is a route.

  The number of categories extracted by the CPU 11 is not limited to a specific number. The configuration of the categories extracted by the CPU 11 is not limited to a particular configuration. Further, the route extracted by the CPU 11 is not limited to a particular configuration.

  Further, the CPU 11 has a function (setting unit) of setting the browsing ratio of the extracted category for each hierarchy of the funnel structure. That is, the CPU 11 sets the ratio of categories browsed by the user for each hierarchy of the funnel structure. For example, the CPU 11 sets the browsing ratio of each category with respect to all browsing of the extracted category. For example, the CPU 11 generates a table (hierarchy table) in which the hierarchy of the funnel structure and the browsing ratio of the category in the hierarchy are associated with each other.

  FIG. 5 shows an example of the structure of a hierarchy table in which the hierarchy of the funnel structure is associated with the browsing ratio of the categories in the hierarchy.

  As shown in FIG. 5, in the hierarchy table, the users belonging to “cognition” list “usually used media”, “life change”, “beauty and health”, and “related product information” at 80%, 10%, 7%, respectively. Indicates that browsing is performed at a rate of 3%. In the hierarchy table, the users belonging to “interest / interest” have 40%, 30%, 15% and 15% of “usually used media”, “life change”, “beauty and health” and “related product information”, respectively. Indicates browsing by ratio. In addition, the hierarchy table shows that users belonging to “Review” have 10%, 20%, 60% and 20% of “usually used media”, “life change”, “beauty and health” and “related product information”, respectively. Indicates to browse with. In the hierarchy table, users belonging to “immediately before” have 5%, 10%, 50% and 35% of “usually used media”, “life change”, “beauty and health” and “related product information”, respectively. Indicates to browse with.

  The ratio of each category set by the CPU 11 for each hierarchy is 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.

  Further, the CPU 11 has a function (transition probability calculation unit) that calculates the probability that a user belonging to each layer will be transferred to each layer after a predetermined period of time, based on the category and the transition route (transition probability) between the categories. That is, the CPU 11 calculates the transfer probability between layers. For example, the CPU 11 generates a table (transition probability table) in which a hierarchy having a funnel structure is associated with a probability that a user in the hierarchy will move to each hierarchy after a predetermined period. Note that the transition probability table also includes the probability that the user stays in the hierarchy.

  FIG. 6 shows a configuration example of a transition probability table in which the hierarchy of the funnel structure is associated with the probability that a user in the hierarchy will move to each hierarchy after a predetermined period.

  As shown in FIG. 6, the transition probability table shows that the users belonging to “cognition” are “cognitive”, “interest / interest”, “examination”, “immediately before” and “conversion” after a predetermined period of 80% and 2 respectively. %, 3%, 15% and 0% probability of transfer. In the transition probability table, the users belonging to “interest / interest” are assigned 81%, 5%, 14% and 0% to “interest / interest”, “examination”, “immediately before” and “conversion” after a predetermined period, respectively. It indicates that the transfer will occur with the probability of. Further, the transition probability table indicates that the users belonging to “examination” are transferred to “examination”, “immediately before” and “conversion” with a probability of 79%, 21%, and 0% after a predetermined period, respectively. Further, the transition probability table shows that the users belonging to "immediately before" are transferred to "immediately before" and "conversion" with a probability of 87% and 13% respectively after a predetermined period.

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

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

For example, the CPU 11 generates a hierarchy table and a transition probability table according to a hidden Markov model or the like.
The method of generating the hierarchy table and the transition probability table is not limited to a particular method.

The CPU 11 has a function (unconverted user log extraction unit) for extracting a web browsing log (unconverted user log) of a user who has not completed conversion.
The CPU 11 extracts the web browsing log of the user who has not completed the conversion from the storage area 14a. The CPU 11 may extract a web browsing log whose browsing date and time is within a predetermined period from the web browsing logs of users who have not completed conversion.

  Further, the CPU 11 has a function (tier estimation unit) of estimating the tier of each user who has not completed conversion from the web browsing log and the tier table of the user who has not completed conversion.

The CPU 11 estimates the hierarchy for each user based on the extracted Web browsing log. For example, the CPU 11 extracts a web browsing log of a site included in the category indicated by the hierarchy table from the web browsing log of a certain user. The CPU 11 calculates the browsing ratio of each category of the user based on the extracted Web browsing log. The CPU 11 refers to the hierarchical table and compares the browsing ratio of each category of the user with the browsing ratio of each category indicated by the hierarchical table. The CPU 11 estimates the layer that best matches the browsing ratio of each category of the user as the layer to which the user belongs.
The CPU 11 executes the above operation for each user and estimates the hierarchy of each user.

  Further, the CPU 11 has a function (structure estimation unit) of estimating the funnel structure from the hierarchy of each user. 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 hierarchy. The CPU 11 may add “conversion”, which is a hierarchy of users who have completed conversion, to the funnel structure.

  Further, the CPU 11 has a function of estimating a funnel structure formed by a user who has browsed a predetermined advertisement and a funnel structure formed by a user who has not browsed the advertisement. Here, it is assumed that the advertiser has delivered a predetermined advertisement on a predetermined Web. FIG. 7 shows a configuration example of a funnel structure 1a of a user who has browsed an advertisement and a funnel structure 1b of a user who has not browsed an advertisement.

  The CPU 11 extracts the web browsing log (browsing user log) of the user who has not completed the conversion and has browsed the advertisement from the storage area 14a (browsing user log extraction unit). For example, the CPU 11 extracts a user having a web browsing log indicating that the advertisement has been browsed, and extracts the web browsing log of the user.

  The CPU 11 estimates the hierarchy of each user who browsed the advertisement from the extracted Web browsing log and hierarchy table (browsing user hierarchy estimation unit). Based on the estimation result, the CPU 11 estimates the funnel structure 1a of the user who browsed the advertisement (browsing user structure estimation unit). The CPU 11 may add the layer of the user who browsed the advertisement and completed the conversion to the funnel structure 1a as the layer of "conversion".

  Further, the CPU 11 extracts a web browsing log (non-browsing user log) of a user who has not completed the conversion and has not browsed the advertisement from the storage area 14a (non-browsing user log extraction unit). For example, the CPU 11 extracts a user having a web browsing log indicating that the advertisement has been browsed, and extracts web browsing logs other than the user.

  The CPU 11 estimates the hierarchy of each user who has not browsed the advertisement from the extracted web browsing log of the user and the hierarchy table (non-browsing user hierarchy estimation unit). Based on the estimation result, the CPU 11 estimates the funnel structure 1b of the user who has not browsed the advertisement (non-browsing user structure estimation unit). It should be noted that the CPU 11 may add the layer of the user who has not browsed the advertisement and who has completed the conversion to the funnel structure 1b as the layer of "conversion".

  With the above operation, as shown in FIG. 7, the CPU 11 can estimate the funnel structure 1a of the user who has browsed the advertisement and the funnel structure 1b of the user who has not browsed the advertisement after the advertisement distribution. It should be noted that the CPU 11 may classify the users by the number of times the advertisement has been browsed, and estimate the funnel structure for each number of browses.

Next, an operation example of the information processing device 10 will be described.
First, an operation example in which the information processing device 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 device 10 estimates the funnel structure.

  First, the CPU 11 extracts the Web browsing log of the user who has completed the conversion from the storage area 14a for a predetermined period of time (S11). When the web browsing log of the user who has completed the conversion is extracted, the CPU 11 extracts the category and the transition route between the categories based on the extracted web browsing log (S12).

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

  When the transition probability table is generated, the CPU 11 extracts the web browsing log of the user who has not completed the conversion (S15). When the web browsing 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 web browsing log and the hierarchy table (S16).

  When estimating the hierarchy of each user who has not completed conversion, the CPU 11 estimates the funnel structure based on the 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 a funnel structure of a user who browses an advertisement and a funnel structure of a user who does not browse an advertisement will be described.

FIG. 9 is a flowchart for explaining an operation example in which the CPU 11 of the information processing device 10 estimates the funnel structure of the user who browses the advertisement and the funnel structure of the user who does not browse 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, the Web browsing log of the user who has not completed the conversion and has browsed the advertisement (S21). When the web browsing log is extracted, the CPU 11 estimates the hierarchy of each user who browsed the advertisement based on the hierarchy table (S22).

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

  When the Web browsing log is extracted, the CPU 11 estimates the hierarchy of each user who has not browsed the advertisement based on the hierarchy table (S25). When the hierarchy of each user who has not browsed the advertisement is estimated, the CPU 11 estimates the funnel structure of the user who has not browsed the advertisement (S26).

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

  The CPU 11 may acquire the web browsing 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.

It should be noted that the present invention is not limited to the above-described embodiment, and can be variously modified at the stage of implementation without departing from the spirit of the invention. In addition, the respective embodiments may be combined as appropriate as much as possible, in which case the combined effects can be obtained. Further, the 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 elements are deleted from all the constituent elements shown in the embodiment, the problem described in the section of the problem to be solved by the invention can be solved, and the effect described in the section of the effect of the invention When the above is obtained, the configuration in which this constituent element is deleted can be extracted as the invention.
The inventions described in the claims at the beginning of the present application will be additionally described below.
[C1]
An information processing device for estimating a funnel structure,
A conversion user log extraction unit that extracts a conversion user log of a user who has completed conversion,
A path extraction unit that extracts, based on the conversion user log, a category that the user who has completed the conversion browses until the conversion and a transition path of the category;
A setting unit that sets a browsing ratio of the category for each hierarchy of the funnel structure based on the category extracted by the route extraction unit and the transition route of the category;
A transition probability calculation unit that calculates a transition probability that a user belonging to each hierarchy of the funnel structure transitions to each hierarchy based on the category extracted by the path extraction unit and the transition path of the category,
An unconverted user log extraction unit that extracts an unconverted user log of a user who has not completed the conversion,
A layer estimation unit that estimates a layer of a user who has not completed the conversion based on the unconverted user log and the browsing ratio of the category,
A structure estimation unit that estimates a funnel structure based on the estimation result of the hierarchy estimation unit,
An information processing apparatus including.
[C2]
The conversion user log and the non-conversion user log indicate the sites browsed by the user,
The category is a classification of sites,
The information processing device according to C1.
[C3]
The conversion user log extraction unit extracts, as the conversion user log, a log that has been delayed for a predetermined period from the date and time when the conversion is completed,
The information processing device according to C1 or 2.
[C4]
The hierarchy estimation unit calculates a browsing ratio of the category of users who have not completed the conversion based on the unconverted user log, and the browsing ratio of the calculated category and the category set by the setting unit. Estimate the hierarchy of the user by comparing with the browsing ratio,
The information processing apparatus according to any one of C1 to C3.
[C5]
The structure estimation unit estimates the number of users belonging to each hierarchy as the funnel structure,
The information processing apparatus according to any one of C1 to C4.
[C6]
The conversion is the purchase of a product,
The information processing apparatus according to any one of C1 to C5.
[C7]
An information processing device for estimating a funnel structure,
A conversion user log extraction unit that extracts a conversion user log of a user who has completed conversion,
A path extraction unit that extracts, based on the conversion user log, a category that the user who has completed the conversion browses until the conversion and a transition path of the category;
A setting unit that sets a browsing ratio of the category for each hierarchy of the funnel structure based on the category extracted by the route extraction unit and the transition route of the category;
A transition probability calculation unit that calculates a transition probability that a user belonging to each hierarchy of the funnel structure transitions to each hierarchy based on the category extracted by the path extraction unit and the transition path of the category,
A browsing user log extraction unit that extracts a browsing user log of a user who has not completed the conversion and has browsed an advertisement,
A browsing user hierarchy estimation unit that estimates the hierarchy of the user based on the browsing user log and the browsing ratio of the category,
A browsing user structure estimation unit that estimates the funnel structure of the user based on the estimation result of the browsing user hierarchy estimation unit,
An information processing apparatus including.
[C8]
further,
A non-browsing user log extraction unit that extracts a non-browsing user log of a user who has not completed the conversion and has not browsed the advertisement;
A non-viewing user hierarchy estimation unit that estimates the hierarchy of the user based on the non-viewing user log and the viewing ratio of the category;
A non-browsing user structure estimation unit that estimates the funnel structure of the user based on the estimation result of the non-browsing user hierarchy estimation unit;
With
The information processing device according to C7.
[C9]
An information processing method for estimating a funnel structure,
Extract the conversion user log of the user who completed conversion,
Based on the conversion user log, the category that the user who has completed the conversion browses until the conversion and the transition path of the category are extracted,
Based on the category and the transition path of the category, for each hierarchy of the funnel structure, set the browsing ratio of the category,
Based on the extracted category and the transition path of the category, the transition probability that a user belonging to each layer of the funnel structure transits to each layer is calculated,
Extract the unconverted user log of the user who has not completed the conversion,
Estimating the hierarchy of users who have not completed the conversion based on the unconverted user log and the browsing ratio of the category,
Estimate the funnel structure based on the estimation result,
Information processing method.

  1 (1a and 1b) ... Funnel structure, 2 to 6 ... Hierarchy, 10 ... Information processing device, 11 ... CPU, 12 ... ROM, 13 ... RAM, 14 ... NVM, 14a ... Storage area, 15 ... Communication unit, 16 ... Operation part, 17 ... Display part.

Claims (9)

An information processing device for estimating a funnel structure,
A conversion user log extraction unit that extracts a conversion user log of a user who has completed conversion,
A path extraction unit that extracts, based on the conversion user log, a category that the user who has completed the conversion browses until the conversion and a transition path of the category;
A setting unit that sets a browsing ratio of the category for each hierarchy of the funnel structure based on the category extracted by the route extraction unit and the transition route of the category ;
An unconverted user log extraction unit that extracts an unconverted user log of a user who has not completed the conversion,
A layer estimation unit that estimates a layer of a user who has not completed the conversion based on the unconverted user log and the browsing ratio of the category,
A structure estimation unit that estimates a funnel structure based on the estimation result of the hierarchy estimation unit,
An information processing apparatus including. The conversion user log and the non-conversion user log indicate the sites browsed by the user,
The category is a classification of sites,
The information processing apparatus according to claim 1. The conversion user log extraction unit extracts, as the conversion user log, a log that has been delayed 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 hierarchy estimation unit calculates a browsing ratio of the category of users who have not completed the conversion based on the unconverted user log, and the browsing ratio of the calculated category and the category set by the setting unit. Estimate the hierarchy of the user by comparing with the browsing ratio,
The information processing apparatus according to any one of claims 1 to 3. The structure estimation unit estimates the number of users belonging to each hierarchy as the funnel structure,
The information processing apparatus according to any one of claims 1 to 4. The conversion is the purchase of a product,
The information processing apparatus according to any one of claims 1 to 5. An information processing device for estimating a funnel structure,
A conversion user log extraction unit that extracts a conversion user log of a user who has completed conversion,
A path extraction unit that extracts, based on the conversion user log, a category that the user who has completed the conversion browses until the conversion and a transition path of the category;
A setting unit that sets a browsing ratio of the category for each hierarchy of the funnel structure based on the category extracted by the route extraction unit and the transition route of the category ;
A browsing user log extraction unit that extracts a browsing user log of a user who has not completed the conversion and has browsed an advertisement,
A browsing user hierarchy estimation unit that estimates the hierarchy of the user based on the browsing user log and the browsing ratio of the category,
A browsing user structure estimation unit that estimates the funnel structure of the user based on the estimation result of the browsing user hierarchy estimation unit,
An information processing apparatus including. further,
A non-browsing user log extraction unit that extracts a non-browsing user log of a user who has not completed the conversion and has not browsed the advertisement;
A non-viewing user hierarchy estimation unit that estimates the hierarchy of the user based on the non-viewing user log and the viewing ratio of the category;
A non-browsing user structure estimation unit that estimates the funnel structure of the user based on the estimation result of the non-browsing user hierarchy estimation unit;
With
The information processing apparatus according to claim 7. An information processing method for estimating a funnel structure,
Extract the conversion user log of the user who completed conversion,
Based on the conversion user log, the category that the user who has completed the conversion browses until the conversion and the transition path of the category are extracted,
Based on the category and the transition path of the category, for each hierarchy of the funnel structure, set the browsing ratio of the category ,
Extract the unconverted user log of the user who has not completed the conversion,
Estimating the hierarchy of users who have not completed the conversion based on the unconverted user log and the browsing ratio of the category,
Estimate the funnel structure based on the estimation result,
Information processing method.