JP7399931B2 - Information processing device, information processing method, and information processing program - Google Patents

Description

The present invention relates to an information processing device, an information processing method, and an information processing program.

In recent years, advertisement distribution via the Internet has become popular. For example, a technique is known in which advertising content such as a company or a product is displayed in an advertising space set on an advertising medium such as a web page (see Patent Document 1).

There are various aspects of advertisements in advertisement distribution, such as the advertising medium in which the advertisement is displayed, the position and size of the advertisement in the advertising medium, and whether it is a still image or a video. Advertisers purchase advertisements of any type from advertising distributors and display them on advertising media while considering advertising costs. Hereinafter, any form of advertisement sold to advertisers will be referred to as an "advertisement product."

Japanese Patent Application Publication No. 2002-203119

However, with the above-mentioned conventional technology, for example, it is difficult for an advertiser to appropriately predict the effect obtained by an advertisement (hereinafter also referred to as advertising effect) before purchasing the advertised product. may hesitate to purchase. Therefore, the above-described conventional technology has room for further improvement in terms of being able to promote the purchase of advertised products by advertisers.

The present application has been made in view of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can promote the purchase of advertised products by advertisers.

The information processing device according to the present application includes a reception unit that receives, from a client of the advertisement, desired attribute conditions regarding the delivery person attributes of the delivery person whose advertising medium is a delivery person who delivers a product to a user; The delivery system further includes an estimating unit that estimates performance information regarding the performance of a target delivery person who satisfies the desired attribute conditions based on the performance performance of the delivery person.

The estimating unit is configured to calculate information based on the performance record of the delivery person that satisfies an attribute condition regarding the predetermined delivery person attribute when delivery person attribute information regarding the predetermined delivery person attribute of the delivery person is input into the first machine learning model. Using the first machine learning model trained to output performance information regarding the delivery person's performance, performance information regarding the target delivery person's performance is estimated.

According to one aspect of the embodiment, it is possible to promote the purchase of advertised products by advertisers.

FIG. 1 is a diagram illustrating a configuration example of an information processing system according to a first embodiment. FIG. 2 is a diagram for explaining an aspect of an advertisement using a delivery person as an advertisement medium according to an embodiment. FIG. 3 is a diagram for explaining an overview of information processing according to the first embodiment. FIG. 4 is a diagram illustrating a configuration example of an information processing apparatus according to the first embodiment. FIG. 5 is a diagram illustrating an example of a delivery person information storage unit according to the first embodiment. FIG. 6 is a diagram illustrating an example of the operation record information storage unit according to the first embodiment. FIG. 7 is a diagram illustrating an example of a viewing record information storage unit according to the first embodiment. FIG. 8 is a diagram illustrating a configuration example of an information processing apparatus according to the second embodiment. FIG. 9 is a diagram illustrating an example of a learning data storage unit according to the second embodiment. FIG. 10 is a diagram illustrating an example of the first machine learning model according to the second embodiment. FIG. 11 is a diagram illustrating an example of a second machine learning model according to a modification of the second embodiment. FIG. 12 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device.

DESCRIPTION OF THE PREFERRED EMBODIMENTS An information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail below with reference to the drawings. Note that the information processing apparatus, information processing method, and information processing program according to the present application are not limited to this embodiment. Further, in each of the embodiments below, the same parts are given the same reference numerals, and redundant explanations will be omitted.

(Embodiment)
[1. First embodiment]
[1-1. Configuration example of information processing system]
FIG. 1 is a diagram illustrating a configuration example of an information processing system according to a first embodiment. As shown in FIG. 1, the information processing system 1 includes a delivery person terminal 10, an advertiser terminal 20, and an information processing device 100. The delivery person terminal 10, the advertiser terminal 20, and the information processing device 100 are connected via a predetermined network N so that they can communicate by wire or wirelessly. Note that the information processing system 1 shown in FIG. 1 may include any number of delivery person terminals 10, any number of advertiser terminals 20, and any number of information processing devices 100.

The delivery person terminal 10 is, for example, an information processing device mounted on a delivery bag used by a delivery person of a food delivery service or the like to deliver products. The delivery person terminal 10 includes a screen that can display arbitrary content. For example, the delivery person terminal 10 displays advertising content requested by an advertising client (hereinafter also referred to as an advertiser) on its screen. The delivery person terminal 10 is, for example, a smartphone, a tablet type terminal, or the like. In the following, a case will be described in which the delivery person terminal 10 is a tablet-type terminal.

For example, when the delivery bag is box-shaped, the delivery person terminal 10 may be installed on at least one side of the delivery bag other than the top and bottom surfaces. For example, when the delivery bag is a box-shaped rucksack that is carried on the back of the delivery person, the delivery person terminal 10 is configured to carry out at least one of the delivery bags except for the top surface, the bottom surface, and the surface on the back side of the delivery person. It may be installed on the surface. In the following, a case where the delivery bag is a box-shaped backpack will be described.

The delivery person terminal 10 also includes various sensors. Specifically, the delivery person terminal 10 is equipped with a sensor that can acquire information regarding the viewer who viewed the advertising content displayed on the screen of the delivery person terminal 10. For example, the delivery person terminal 10 is equipped with a camera capable of photographing the surroundings of the delivery person terminal 10. Further, the delivery person terminal 10 transmits an image taken by the camera to the information processing device 100.

The advertiser terminal 20 is an information processing device used by an advertiser. For example, the advertiser terminal 20 is a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or the like. In accordance with the operation of the advertiser, the advertiser terminal 20 transmits to the information processing device 100, together with an advertisement request and advertisement content, desired attribute conditions regarding the delivery person attributes of the delivery person who uses the delivery person as an advertisement medium. do.

The information processing device 100 receives, from the advertiser terminal 20, desired attribute conditions regarding the delivery person attributes of the delivery person who carries out an advertisement using the delivery person as an advertising medium. In addition, the information processing device 100 estimates operation information regarding the operation of a target delivery person who satisfies desired attribute conditions based on the delivery person's performance record.

FIG. 2 is a diagram for explaining an aspect of an advertisement using a delivery person as an advertisement medium according to an embodiment. In the example shown in FIG. 2, a delivery bag used by a delivery person of a food delivery service to deliver products is equipped with a delivery person terminal 10, which is a tablet-type terminal. Then, the target delivery person delivers the advertisement content requested by the advertiser on the screen of the delivery person terminal 10 of the target delivery person who is a delivery person who satisfies the desired attribute conditions desired by the advertiser. By doing this, advertisements will be developed using the target delivery person as a medium.

More specifically, the information processing device 100 receives an advertisement request and advertisement content regarding cosmetics of company A from the advertiser terminal 20. Further, the information processing device 100 receives an advertisement request as well as desired attribute conditions regarding the delivery person attributes of the delivery person mediating the advertisement from the advertiser terminal 20. Subsequently, the information processing device 100 extracts the target delivery person who satisfies the desired attribute conditions from the database, and transmits the advertising content to the delivery person terminal 10 of the target delivery person. Then, the target delivery person makes a delivery with advertising content displayed on the screen of the delivery person terminal 10, thereby developing an advertisement using the target delivery person as a medium.

Here, the delivery staff of food delivery services, which has been increasing in recent years, are gig workers (independent contractors) who undertake delivery work on a job-by-job basis, which may give them a negative image in advertising. Furthermore, in advertising, there are some delivery people who go against the brand image of the advertised product or service. Therefore, the information processing device 100 receives the attribute desired condition regarding the delivery person attribute of the delivery person desired by the advertiser, and extracts the target delivery person who satisfies the attribute condition regarding the delivery person attribute of the delivery person desired by the advertiser. Then, the information processing device 100 causes the target delivery person to perform delivery while displaying the advertising content on the screen of the delivery person terminal 10 of the target delivery person who satisfies the attribute condition regarding the delivery person attribute of the delivery person desired by the advertiser. Thereby, the information processing device 100 can develop an advertisement using a delivery person as an advertising medium without damaging the brand image of an advertisement target in the advertisement development.

[1-2. Overview of information processing]
FIG. 3 is a diagram for explaining an overview of information processing according to the first embodiment. In the example shown in FIG. 3, the advertiser wishes to request an advertisement regarding cosmetics from company A. In addition, the desired attributes of the delivery person desired by the advertiser are that the delivery person's gender is "female," the age of the delivery person is "18 to 30 years old," and the delivery person's main attributes are The delivery area is the 23 wards of Tokyo, and the delivery satisfaction level of the delivery person is 95% or higher. Furthermore, the advertising period desired by the advertiser is "April". At this time, the information processing device 100 receives the desired attribute conditions shown in FIG. 3 from the advertiser terminal 20.

When the information processing device 100 receives the desired attribute condition from the advertiser terminal 20, it estimates the performance information regarding the performance of the target delivery person who satisfies the desired attribute condition based on the performance information regarding the performance performance of the delivery person. In the example shown in FIG. 3, the information processing device 100 estimates, as an example of the operation information, the number of working target delivery personnel, the total expected working time of the target delivery personnel on weekdays, and the total expected working time on holidays. After estimating the operating information, the information processing device 100 transmits the estimated operating information to the advertiser terminal 20. As a result, the information processing device 100 can provide the advertiser with operation prediction information regarding the prediction of the operation of the target delivery person that satisfies the desired attribute conditions desired by the advertiser. It is possible to reduce the risk of ``paying for invisible effects''. Therefore, the information processing device 100 can promote the purchase of advertised products by advertisers.

Furthermore, the information processing device 100 estimates viewing information regarding viewing by a viewer who views an advertisement using the target delivery person as an advertising medium, based on the viewing performance of the viewer who viewed the advertisement. In the example shown in FIG. 3, the information processing device 100 estimates, as an example of viewing information, the number of viewers and total viewing time of viewers who view an advertisement using the target delivery person as an advertising medium. After estimating the viewing information, the information processing device 100 transmits the estimated viewing information to the advertiser terminal 20. As a result, the information processing device 100 can provide the advertiser with viewing prediction information regarding the prediction of viewing by viewers who view an advertisement whose advertising medium is a target delivery person who satisfies desired attribute conditions desired by the advertiser. Therefore, it is possible to reduce the risk of ``paying for invisible effects'', which is a concern for advertisers. Therefore, the information processing device 100 can promote the purchase of advertised products by advertisers.

[1-3. Configuration example of information processing device]
FIG. 4 is a diagram illustrating a configuration example of the information processing device 100 according to the first embodiment. As shown in FIG. 4, the information processing device 100 includes a communication section 110, a storage section 120, and a control section 130. Note that the information processing device 100 includes an input unit (for example, a keyboard, a mouse, etc.) that accepts various operations from an administrator of the information processing device 100, and a display unit (for example, a liquid crystal display, etc.) for displaying various information. May have.

(Communication Department 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to a network (for example, network N in FIG. 1) by wire or wirelessly, and sends and receives information to and from the delivery person terminal 10 and the advertiser terminal 20.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 according to the first embodiment includes a delivery person information storage unit 121, an operation performance information storage unit 122, and a viewing performance information storage unit 123, as shown in FIG.

(Delivery person information storage unit 121)
The delivery person information storage unit 121 stores various information regarding delivery persons. FIG. 5 is a diagram illustrating an example of a delivery person information storage unit according to the first embodiment. In the example shown in FIG. 5, the delivery person information storage unit 121 stores "delivery person ID", "gender", "age", "main delivery start area (prefecture)", "main delivery start area (city, town, village)", It has items such as "delivery satisfaction", "delivery method", "work history", and "quest completion rate".

"Deliveryman ID" indicates identification information for identifying a deliveryman. "Gender" indicates the gender of the delivery person. "Age" indicates the age of the delivery person. “Main delivery start area (prefecture)” indicates the prefecture in which the delivery person starts the main delivery area. “Main delivery start area (municipality)” indicates the city/town/village of the main delivery start area by the delivery person. "Delivery satisfaction level" indicates the customer's satisfaction level with the delivery person. "Delivery means" indicates the means of delivery by the delivery person. "Work history" indicates that the delivery person performs delivery work full-time or as a side job. The "quest achievement rate" indicates the achievement rate of the delivery task that the delivery person is in charge of.

(Operation performance information storage unit 122)
The performance information storage unit 122 stores various information regarding the performance of the delivery person. FIG. 6 is a diagram illustrating an example of the operation record information storage unit according to the first embodiment. In the example shown in FIG. 6, the operation performance information storage unit 122 stores "delivery person ID", "date", "day of the week", "operating hours", "number of deliveries (morning)", "number of deliveries (afternoon)", It has items such as "Main delivery start area (prefecture)", "Main delivery start area (municipality)", "Weather (morning)", "Weather (afternoon)", "Delivery method", and "Operating distance".

"Deliveryman ID" indicates identification information for identifying a deliveryman. "Date" indicates the date on which the delivery was made by the delivery person. "Day of the week" indicates the day of the week when the delivery person made the delivery. "Working hours" indicates the working hours of the delivery person. “Number of deliveries (morning)” indicates the number of deliveries made by the delivery person in the morning of the day on which the delivery was made. "Number of deliveries (afternoon)" indicates the number of deliveries made by the delivery person in the afternoon of the day on which the delivery was made. “Main delivery start area (prefecture)” indicates the prefecture in which the delivery person starts the main delivery area. “Main delivery start area (municipality)” indicates the city/town/village of the main delivery start area by the delivery person. "Weather (morning)" indicates the weather in the morning on the day the delivery person made the delivery. "Weather (afternoon)" indicates the weather in the afternoon on the day the delivery person made the delivery. "Delivery means" indicates the means of delivery by the delivery person. "Working distance" indicates the total distance traveled by the delivery person during delivery.

(Viewing record information storage unit 123)
The viewing performance information storage unit 123 stores various information regarding the viewing performance of advertisements. FIG. 7 is a diagram illustrating an example of a viewing record information storage unit according to the first embodiment. In the example shown in FIG. 7, the viewing performance information storage unit 123 stores "delivery person ID,""date,""day of the week,""number of viewers (morning),""number of viewers (afternoon)," and "viewing time (morning)." )” and “Viewing time (afternoon)”.

"Deliveryman ID" indicates identification information for identifying a deliveryman. "Date" indicates the date on which the delivery was made by the delivery person. "Day of the week" indicates the day of the week when the delivery person made the delivery. “Number of viewers (morning)” indicates the number of viewers who viewed the advertisement posted on the delivery bag of the delivery person in the morning of the day the delivery was made by the delivery person. “Number of viewers (afternoon)” indicates the number of viewers who watched the advertisement posted on the delivery bag of the delivery person in the afternoon of the day when the delivery person made the delivery. "Viewing time (morning)" indicates the total viewing time of the advertisement by viewers who viewed the advertisement posted on the delivery bag of the delivery person in the morning of the day when the delivery person made the delivery. "Viewing time (afternoon)" indicates the total viewing time of the advertisement by viewers who viewed the advertisement posted on the delivery bag of the delivery person in the afternoon of the day when the delivery person made the delivery.

(Control unit 130)
Returning to the explanation of FIG. 4, the control unit 130 is a controller, and for example, controls the internal processing of the information processing apparatus 100 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), etc. This is realized by executing various programs (corresponding to an example of an information processing program) stored in the storage device of , using the RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 4, the control unit 130 includes an acquisition unit 131, a reception unit 132, an estimation unit 133, and a provision unit 134, and realizes or executes information processing functions and operations described below. . Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 4, and may be any other configuration as long as it performs information processing to be described later.

(Acquisition unit 131)
The acquisition unit 131 acquires delivery person information from the delivery person terminal 10 of each delivery person. Upon acquiring the delivery person information, the acquisition unit 131 stores the acquired delivery person information in the delivery person information storage unit 121 in association with the delivery person ID.

The acquisition unit 131 also acquires operation performance information from the delivery person terminal 10 of each delivery person. Upon acquiring the operation record information, the acquisition unit 131 stores the acquired operation record information in the operation record information storage unit 122 in association with the delivery person ID.

The acquisition unit 131 also acquires viewing performance information from the delivery person terminal 10 of each delivery person. Note that the acquisition unit 131 may acquire images taken by the camera of the delivery person terminal 10 of each delivery person from the delivery person terminal 10 of each delivery person. Subsequently, the acquisition unit 131 may acquire viewing performance information by analyzing each acquired image using a known image analysis technique. Upon acquiring the viewing performance information, the acquisition unit 131 stores the acquired viewing performance information in the viewing performance information storage unit 123 in association with the delivery person ID.

(Reception Department 132)
The reception unit 132 receives from the advertiser the desired attribute conditions regarding the delivery person attributes of the delivery person whose advertising medium is the delivery person who delivers the product to the user. Specifically, the reception unit 132 receives an advertisement request and advertisement content from the advertiser terminal 20. Further, the receiving unit 132 receives from the advertiser terminal 20 a request for an advertisement as well as desired attribute conditions regarding the attributes of the delivery person who mediates the advertisement.

(Estimation unit 133)
The estimating unit 133 estimates performance information regarding the performance of the target delivery person, who is a delivery person who satisfies the desired attribute conditions, based on the performance performance of the delivery person. Specifically, the estimating unit 133 estimates the performance information regarding the target delivery person's performance based on the desired attribute conditions and the performance information regarding the delivery person's performance performance. For example, the estimating unit 133 estimates the number of working target delivery personnel as an example of operation information regarding the working of the target delivery personnel. For example, the estimation unit 133 narrows down the target delivery people who correspond to the desired attribute conditions from among the delivery people corresponding to the delivery person information held in the delivery person information storage unit 121 by filtering or the like. Estimate the number of people in operation.

For example, the advertiser's desired attribute conditions regarding the attributes of a delivery person are that the gender of the delivery person is "female," the age of the delivery person is "18 to 30 years old," and the delivery person's main attributes are It is assumed that the delivery area is "Tokyo's 23 Wards", the delivery satisfaction level of the delivery staff is "95% or more", and the total number of delivery staff held in the delivery staff information storage unit 121 is 100,000. At this time, the estimating unit 133 calculates the number of delivery workers narrowed down to "female" by the delivery worker "gender" filter to be 20,000. Next, the estimating unit 133 calculates the number of delivery persons narrowed down to "female" and further narrowed down to "18 to 30 years old" by the delivery worker "age" filter to 10,000. Next, the estimation unit 133 calculates the number of delivery workers narrowed down to "18 to 30 years old" and further narrowed down to "Tokyo's 23 wards" using the delivery worker's "main delivery area" filter to 4,000. calculate. Subsequently, the estimating unit 133 calculates the number of delivery persons narrowed down to "Tokyo's 23 wards" to be 3,500, the number of which is further narrowed down to "95% or more" by the delivery worker's "delivery satisfaction" filter. In this way, the estimating unit 133 estimates the number of target delivery workers to be 3,500.

Furthermore, the estimation unit 133 estimates the total working time of the target delivery person as an example of operation information regarding the operation of the target delivery person. For example, the estimation unit 133 estimates the target delivery person's total working hours on weekdays. For example, the estimating unit 133 calculates the working hours from Monday to Friday of delivery personnel under the same conditions in the same month in the past, and estimates the total working hours of the target delivery personnel on weekdays this year. In the following, a case will be described in which the information processing apparatus 100 stores operation record information for the years 2016 to 2020 in the operation record information storage unit 122.

For example, assume that the advertiser's advertisement placement request is for May 2021. In addition, the desired attributes of the delivery person desired by the advertiser are that the delivery person's gender is "female," the age of the delivery person is "18 to 30 years old," and the delivery person's main attributes are Assume that the delivery area is "Tokyo's 23 Wards", the delivery satisfaction level of the delivery person is "95% or more", and the total number of delivery persons held in the delivery person information storage unit 121 is 100,000 (hereinafter referred to as (Also referred to as Attribute Desired Condition #1). At this time, the estimation unit 133 calculates desired attribute condition #1 in May 2021 based on how the target delivery person satisfying desired attribute condition #1 performed in each May from 2016 to 2020. Estimate the total weekday working hours of the target delivery person. For example, the estimation unit 133 multiplies the average weekday working hours A of each target delivery person who satisfies desired attribute condition #1 in each May from 2016 to 2020 by the number of target delivery personnel in May 2021. The number is estimated to be the target delivery person's total working hours B on weekdays in May 2021. For example, the estimation unit 133 calculates "{(Working hours of the target delivery person on weekdays in May 2016)+...+(Working hours of the target delivery person on weekdays in May 2020)}/{(Working hours of the target delivery person on weekdays in May 2016) Weekday working hours per target delivery person who satisfies desired attribute condition #1 in May 2021 using the formula: Calculate the average A.

Here, since the market environment changes every year, it is necessary to multiply (weight) each year's data by a coefficient so that among past data, the closer to the most recent year, the stronger the influence. For example, let α be the coefficient for 2020, β be the coefficient for 2019, γ be the coefficient for 2018, δ be the coefficient for 2017, and ε be the coefficient for 2016. Further, each coefficient satisfies the condition "α + β + γ + δ + ε = 1". Further, for example, the degree of influence of the coefficient changes according to the market environment, such as "α : β : γ : δ : ε=0.5 : 0.3 : 0.1 : 0.05 : 0.05". At this time, the estimating unit 133 calculates "α {(Operating hours of target delivery personnel on weekdays in May 2020)/(Number of target delivery personnel on weekdays in May 2020)}+β{(Target delivery hours on weekdays in May 2019) Working hours of delivery staff)/(Number of target delivery staff on weekdays in May 2019)}+γ {(Working hours of target delivery staff on weekdays in May 2018)/(Number of target delivery staff on weekdays in May 2018)}+δ {(Working hours of targeted delivery personnel on weekdays in May 2017)/(Number of targeted delivery personnel on weekdays in May 2017)}+ε{(Working hours of targeted delivery personnel on weekdays in May 2016)/(May 2016 The average working hours A' on weekdays for each target delivery person who satisfies desired attribute condition #1 in May 2021 is calculated using the formula: Next, the estimating unit 133 multiplies the calculated average weekday working hours A′ per target delivery person by the number of target delivery staff in May 2021 to calculate the number of target delivery staff in May 2021. The total working time on weekdays is estimated to be B'.

(Providing unit 134)
The providing unit 134 provides the operating information estimated by the estimating unit 133 to the advertiser. Specifically, the providing unit 134 transmits the operating information estimated by the estimating unit 133 to the advertiser terminal 20.

In addition, gig work promises freedom for delivery workers, and fluctuations in prices are a cause for concern for advertisers. Therefore, the providing unit 134 calculates data that is an element of the blur value and provides the information to the advertiser. Specifically, the providing unit 134 calculates each numerical value of "shaking factors" that affect delivery. For example, the providing unit 134 may provide operation results for similar temperature days (±2℃) on weekdays of the same month in the past (2016-2020/May), operation results by weather, operation results by time zone, operation results by area, We will also analyze differences in operational performance (delivery method (bicycle, motorcycle, etc.), work history (full-time or side job, etc.)) by delivery person attribute. Next, unstable factors are provided as additional information from the general operation forecast and used as reference data for advertisers.

[1-4. Modified example]
[1-4-1. Paper media advertisement]
Further, in the first embodiment described above, a case has been described in which the delivery person terminal 10 displays advertising content on the screen, but the manner in which the advertisement is posted is not limited to displaying the advertising content on the screen. For example, a paper advertisement such as a poster may be pasted on the side of the delivery bag.

[1-4-2. Super coupon by rare delivery person〕
Further, in the first embodiment described above, the reception unit 132 determines that the delivery person's gender is "female," the delivery person's age is "18 to 30 years old," and the delivery person's main delivery area is Although we have explained the case where we accept desired attribute conditions related to delivery worker attributes such as "Tokyo's 23 wards" and delivery satisfaction of "95% or more", the reception unit 132 also accepts other conditions from the advertiser. Good too.

For example, the reception unit 132 may make a delivery where the number of delivery staff is "up to 3", the delivery satisfaction level of the delivery staff is "100%", and the main delivery area of the delivery staff is "Chiyoda Ward". You may accept desired attribute conditions regarding employee attributes. Further, the receiving unit 132 receives advertising content including information regarding a limited discount coupon for cosmetics of Company A from an advertiser. As a result, the information processing device 100 enables a delivery person to run an advertisement that projects a limited discount ticket that you will be lucky to find on the street.

[1-5. Effects of the first embodiment]
As described above, the information processing device 100 according to the first embodiment includes the receiving section 132 and the estimating section 133. The reception unit 132 receives from the advertisement client the desired attribute conditions regarding the delivery person attributes of the delivery person whose advertising medium is the delivery person who delivers the product to the user. The estimating unit 133 estimates performance information regarding the performance of the target delivery person, who is a delivery person who satisfies the desired attribute conditions, based on the performance performance of the delivery person.

Thereby, the information processing device 100 can provide the advertiser with operation prediction information regarding the prediction of the operation of the target delivery person that satisfies the desired attribute conditions desired by the advertiser. It is possible to reduce the risk of ``paying for invisible effects''. Therefore, the information processing device 100 can promote the purchase of advertised products by advertisers.

Furthermore, the estimating unit 133 estimates the operation information regarding the target delivery person's operation based on the desired attribute conditions and the operation performance information regarding the delivery person's operation performance.

As a result, the information processing device 100 can appropriately estimate the operation information regarding the target delivery person's operation based on the delivery person's operation record. ” can be reduced.

Furthermore, the estimating unit 133 estimates the number of working target delivery personnel as operation information regarding the working of the target delivery personnel.

Thereby, the information processing device 100 can provide the number of working target delivery workers to the advertiser as operation prediction information.

Furthermore, the estimation unit 133 estimates the total working time of the target delivery person as operation information regarding the operation of the target delivery person.

Thereby, the information processing device 100 can provide the total operating time of the target delivery person to the advertiser as operation prediction information.

[2. Second embodiment]
The second embodiment will now be described. The second embodiment differs from the first embodiment in that a machine learning model is used to estimate operation information regarding the operation of the target delivery person. Note that descriptions of points similar to those in the first embodiment will be omitted as appropriate. In the second embodiment, the information processing system 1 includes an information processing device 100A instead of the information processing device 100. Note that the machine learning model according to the second embodiment (the first machine learning model M1 and the second machine learning model M2 described later) is generated by machine learning using a neural network such as a convolutional neural network or a regression neural network, for example. but is not limited to such examples. For example, the machine learning model according to the second embodiment may be generated using machine learning using a learning algorithm such as linear regression or logistic regression instead of using a neural network.

[2-1. Configuration example of information processing device]
FIG. 8 is a diagram illustrating a configuration example of an information processing apparatus according to the second embodiment. As shown in FIG. 8, the information processing device 100A includes a communication section 110, a storage section 120A, and a control section 130A. Note that in the information processing device 100A, descriptions of the same points as the information processing device 100 will be omitted as appropriate.

(Storage unit 120A)
The storage unit 120A is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. As shown in FIG. 8, the storage unit 120A according to the second embodiment includes a delivery person information storage unit 121, an operation performance information storage unit 122, a viewing performance information storage unit 123, and a learning data storage unit 124A. have

(Learning data storage unit 124A)
FIG. 9 is a diagram illustrating an example of a learning data storage unit according to the second embodiment. In the example shown in FIG. 9, the learning data storage unit 124A stores "year", "date", "day of the week", "area (prefecture)", "area (municipality)", "weather (morning)", "weather (afternoon),""Number of delivery personnel (morning),""Number of delivery personnel (afternoon),""Number of full-time workers,""Number of side jobs,""Total working hours (hours)," and "Total number of deliveries."

"Year" indicates the year in which the delivery was made. "Date" indicates the date on which the delivery was made. "Day of the week" indicates the day of the week when the delivery was made. “Area (prefecture)” indicates the prefecture in the area where the delivery was made. "Area (municipality)" indicates the municipality of the area where the delivery was made. "Weather (morning)" indicates the weather in the morning on the day the delivery was made. "Weather (afternoon)" indicates the weather in the afternoon on the day the delivery was made. "Number of delivery people (morning)" indicates the number of delivery people in the morning of the day the delivery was made. "Number of delivery personnel (afternoon)" indicates the number of delivery personnel in the afternoon of the day the delivery was made. "Number of professionals" indicates. Shows the number of delivery workers who specialize in deliveries on the day the delivery was made. The "number of side jobs" indicates the number of delivery people who do delivery as a side job among the delivery people on the day the delivery was performed. "Total working time (hours)" indicates the total working time of each delivery person on the day of delivery. The "total number of deliveries" indicates the total number of deliveries made by each delivery person on the day of delivery.

Although not shown, the learning data storage unit 124A stores "gender", "age", "main delivery start area (prefecture)", "main delivery start area (municipality)", "delivery satisfaction level", It further includes items indicating delivery person attributes such as "delivery means", "work history", and "quest completion rate". That is, the learning data storage unit 124A stores learning data for each date for each delivery person attribute.

(Control unit 130A)
Returning to the explanation of FIG. 8, the control unit 130A is a controller, and includes various programs (information processing programs) stored in a storage device inside the information processing device 100A by, for example, a CPU, MPU, GPU, etc. (corresponding to one example) is realized by being executed using RAM as a work area. Further, the control unit 130A is a controller, and is realized by, for example, an integrated circuit such as an ASIC or an FPGA.

As shown in FIG. 8, the control unit 130A includes an acquisition unit 131, a reception unit 132, an estimation unit 133A, and a provision unit 134, and realizes or executes information processing functions and operations described below. . Note that the internal configuration of the control unit 130A is not limited to the configuration shown in FIG. 8, and may be any other configuration as long as it performs information processing to be described later.

(Estimation unit 133A)
The estimating unit 133A estimates performance information regarding the performance of the target delivery person, who is a delivery person who satisfies the desired attribute conditions, based on the performance performance of the delivery person. Specifically, when the estimating unit 133A inputs the delivery person attribute information regarding the predetermined delivery person attribute of the delivery person into the first machine learning model, the estimation unit 133A determines the operation performance of the delivery person who satisfies the attribute condition regarding the predetermined delivery person attribute. Using the first machine learning model trained to output performance information regarding the delivery person's performance based on the above, the performance information regarding the target delivery person's performance is estimated. For example, the estimation unit 133A estimates the number of active target delivery personnel (hereinafter also referred to as the number of delivery personnel or predicted number of delivery personnel) as an example of operation information regarding the operation of the target delivery personnel.

FIG. 10 is a diagram showing an example of the first machine learning model M1 according to the second embodiment. Specifically, the estimating unit 133A refers to the learning data storage unit 124A and determines whether the first machine Learning model M1 is learned. For example, the estimating unit 133A refers to the learning data storage unit 124A, and stores learning data (for example, "year", "date", " "Day of the week", "Area (prefecture)", "Area (municipality)", "Weather (morning)", "Weather (afternoon)", "Number of delivery people (morning)", "Number of delivery people (afternoon)", "Special day job" Attribute conditions regarding the predetermined delivery person attributes on each date in 2016 when inputting "Number of side jobs," "Number of side jobs," "Total working hours (hours)," and "Total number of deliveries" to the first machine learning model M1. The first machine learning model M1 is trained to output the number of delivery persons satisfying the condition. Although not shown, the estimating unit 133A also includes information such as "gender", "age", "main delivery start area (prefecture)", "main delivery start area (municipality)", "delivery satisfaction", "delivery When information indicating predetermined delivery worker attributes such as "method", "work history", and "quest completion rate" is input into the first machine learning model M1, the attribute conditions regarding the predetermined delivery worker attributes on each date in 2016 are satisfied. The first machine learning model M1 is trained to output the number of delivery persons.

Furthermore, the estimating unit 133A estimates the number of delivery people who meet the attribute conditions regarding the predetermined delivery person attributes on a certain day in 2017 using the first machine learning model M1 learned based on the learning data of 2016. do. Specifically, the estimating unit 133A stores learning data regarding a delivery person who satisfies attribute conditions regarding a predetermined delivery person attribute on a certain day in 2017 (for example, “year”, “date”, “day of the week”, “area (city)”). ``Prefecture)'', ``Area (municipality)'', ``Weather (morning)'', ``Weather (afternoon)'', ``Number of delivery people (morning)'', ``Number of delivery people (afternoon)'', ``Number of full-time employees'', ``Number of side jobs'' , "Total working time (hours)" and "Total number of deliveries") are input to the first machine learning model M1, the number of delivery persons output from the first machine learning model M1 is obtained as the estimation result. Although not shown, the estimating unit 133A also includes information such as "gender", "age", "main delivery start area (prefecture)", "main delivery start area (municipality)", "delivery satisfaction", "delivery When information indicating predetermined delivery person attributes such as "means", "work history", and "quest completion rate" is input to the first machine learning model M1, the number of delivery workers output from the first machine learning model M1 is used as the estimation result. obtain. Subsequently, the estimating unit 133A uses, for example, an error backpropagation method to estimate the number of delivery persons output from the first machine learning model M1 and the delivery persons who satisfy the attribute conditions regarding the predetermined delivery person attributes on a certain day in 2017. The weight of the first machine learning model M1 is learned so that the error with the correct data, which is the actual number of delivery people, is small.

Similarly, in addition to the learning data of 2016, the estimation unit 133A uses the first machine learning model based on the information regarding the operation performance of the delivery person who satisfies the attribute condition regarding the predetermined delivery person attribute on each date of every year. Learn M1. Furthermore, in addition to the number of delivery people who meet the attribute conditions regarding predetermined delivery person attributes on a certain day in 2017, the estimation unit 133A also calculates the number of delivery people output from the first machine learning model M1 and each date of every year. The weights of the first machine learning model M1 are learned so that the error from the correct data, which is the actual number of delivery people who satisfy the attribute condition regarding the predetermined delivery person attributes in , is small.

In FIG. 10, a case has been described in which the estimation unit 133A estimates the number of working people of the target delivery person as an example of the operation information regarding the operation of the target delivery person. , the total working time of the target delivery person may be estimated. For example, instead of learning the first machine learning model M1 to output the number of delivery persons who meet the attribute conditions regarding the predetermined delivery person attributes on each date in 2016 as described in FIG. The first machine learning model M1' is trained to output the total working time of a delivery person who satisfies an attribute condition regarding a predetermined delivery person attribute on each date in 2016. In addition, the estimation unit 133A generates correct data that is the total working time output from the first machine learning model M1' and the actual total working time of a delivery person that satisfies the attribute conditions regarding a predetermined delivery person attribute on a certain day in 2017. The weights of the first machine learning model M1' are learned so that the error with respect to the first machine learning model M1' becomes smaller.

[2-2. Modified example]
In the second embodiment described above, a case has been described in which the estimation unit 133A uses a machine learning model to estimate the operation information regarding the operation of the target delivery person. Here, as a modified example of the second embodiment, a case will be described in which the estimating unit 133A uses a machine learning model to estimate viewing information regarding viewing by a viewer who views an advertisement using a target delivery person as an advertising medium. do.

Specifically, when the estimating unit 133A inputs the delivery person attribute information regarding the predetermined delivery person attributes of the delivery person into the second machine learning model, the estimation unit 133A selects the delivery person who satisfies the attribute condition regarding the predetermined delivery person attribute from the advertising medium. Using a second machine learning model that has been trained to output viewing information about the viewer's viewing based on the viewing history of the viewer who viewed the advertisement, the viewer views the advertisement that uses the target delivery person as the advertising medium. Estimating viewing information regarding people's viewing. For example, the estimation unit 133A estimates the viewer's total viewing time (hereinafter also referred to as viewing time prediction) as an example of viewing information regarding viewing by a viewer who views an advertisement using the target delivery person as an advertising medium.

FIG. 11 is a diagram illustrating an example of a second machine learning model according to a modification of the second embodiment. Specifically, the estimating unit 133A refers to the learning data storage unit 124A to estimate the number of viewers who viewed an advertisement whose advertising medium is a delivery person who satisfies the attribute conditions regarding predetermined delivery person attributes on each date of each year. A second machine learning model M2 is learned based on the information regarding the viewing performance. For example, the estimating unit 133A refers to the learning data storage unit 124A, and stores learning data (for example, "year", "date", " "Day of the week", "Area (prefecture)", "Area (municipality)", "Weather (morning)", "Weather (afternoon)", "Number of delivery people (morning)", "Number of delivery people (afternoon)", "Special day job" Attribute conditions regarding the predetermined delivery person attributes on each date in 2016 when inputting "number of side jobs," "number of side jobs," "total working hours (hours)," and "total number of deliveries" to the second machine learning model The second machine learning model M2 is trained to output the total viewing time of viewers who viewed an advertisement whose advertising medium is a delivery person that satisfies the following conditions. Furthermore, the estimating unit 133A calculates the advertising genre and advertising content (such as whether it is a still image or a video) of an advertisement whose advertising medium is a delivery person that satisfies the attribute conditions regarding predetermined delivery person attributes on each date in 2016 to a second machine. When input to the learning model M2, the second machine outputs the total viewing time of viewers who viewed an advertisement whose advertising medium is a delivery person who satisfies attribute conditions regarding predetermined delivery person attributes on each date in 2016. Learning model M2 is learned. Although not shown, the estimating unit 133A also includes information such as "gender", "age", "main delivery start area (prefecture)", "main delivery start area (municipality)", "delivery satisfaction", "delivery When information indicating predetermined delivery person attributes, such as "method", "work history", and "quest completion rate" is input to the second machine learning model M2, the attribute conditions regarding the predetermined delivery person attributes on each date in 2016 are satisfied. The second machine learning model M2 is trained to output the total viewing time of viewers who viewed an advertisement using a delivery person as an advertising medium.

Furthermore, the estimating unit 133A uses the second machine learning model M2 learned based on the learning data of 2016 to select a delivery person who satisfies the attribute condition regarding a predetermined delivery person attribute on a certain day in 2017 as an advertising medium. Estimate the total viewing time of viewers who watched the advertisement. Specifically, the estimating unit 133A stores learning data regarding a delivery person who satisfies attribute conditions regarding a predetermined delivery person attribute on a certain day in 2017 (for example, “year”, “date”, “day of the week”, “area (city)”). ``Prefecture)'', ``Area (municipality)'', ``Weather (morning)'', ``Weather (afternoon)'', ``Number of delivery people (morning)'', ``Number of delivery people (afternoon)'', ``Number of full-time employees'', ``Number of side jobs'' , "total operating time (hours)" and "total number of deliveries") are input to the second machine learning model M2, the total viewing time output from the second machine learning model M2 is obtained as the estimation result. The estimating unit 133A also calculates the advertising genre and advertising content (such as whether it is a still image or a video) of an advertisement whose advertising medium is a delivery person who satisfies the attribute conditions related to a predetermined delivery person attribute on a certain day in 2017 to a second machine. When input to the learning model M2, the total viewing time output from the second machine learning model M2 is obtained as the estimation result. Although not shown, the estimating unit 133A also includes information such as "gender", "age", "main delivery start area (prefecture)", "main delivery start area (municipality)", "delivery satisfaction", "delivery Estimated total viewing time output from the second machine learning model M2 when information indicating predetermined delivery worker attributes such as "means", "work history", and "quest completion rate" is input to the second machine learning model M2. get as. Subsequently, the estimating unit 133A uses, for example, an error backpropagation method to estimate the total viewing time output from the second machine learning model M2 and the delivery that satisfies the attribute conditions regarding the predetermined delivery person attributes on a certain day in 2017. The weights of the second machine learning model M2 are learned so that the error from the correct data, which is the actual total viewing time of viewers who viewed an advertisement using a person as an advertising medium, is small.

Similarly, in addition to the learning data of 2016, the estimation unit 133A calculates the viewing performance of viewers who viewed advertisements whose advertising medium is a delivery person who satisfies the attribute conditions regarding predetermined delivery person attributes on each date of every year. A second machine learning model M2 is learned based on the information regarding the second machine learning model M2. In addition to the total viewing time of viewers who watched an advertisement whose advertising medium is a delivery person who satisfies the attribute conditions regarding a predetermined delivery person attribute on a certain day in 2017, the estimation unit 133A also uses the second machine learning model M2. The difference between the total viewing time output from and the correct data, which is the actual total viewing time of viewers who viewed an advertisement whose advertising medium is a delivery person who satisfies the attribute conditions regarding the predetermined delivery person attributes on each date of every year. The weights of the second machine learning model M2 are learned so that the weight of the second machine learning model M2 becomes small.

In FIG. 11, a case has been described in which the estimating unit 133A estimates the total viewing time of a viewer as an example of viewing information regarding viewing by a viewer who views an advertisement using a target delivery person as an advertising medium. may estimate the number of viewers as viewing information regarding viewing by viewers who view an advertisement using the target delivery person as an advertising medium. For example, the estimating unit 133A outputs the total viewing time of viewers who viewed an advertisement whose advertising medium is a delivery person who satisfies the attribute conditions regarding the predetermined delivery person attributes on each date in 2016 described in FIG. 11. Instead of learning the second machine learning model M2, the second machine learning model M2 is configured to output the number of viewers who viewed an advertisement whose advertising medium is a delivery person who satisfies the attribute conditions regarding predetermined delivery person attributes on each date in 2016. 2 machine learning model M2' is learned. In addition, the estimation unit 133A calculates the number of viewers output from the second machine learning model M2' and the number of viewers who viewed an advertisement using a delivery person as an advertising medium that satisfies attribute conditions regarding predetermined delivery person attributes on a certain day in 2017. The weight of the second machine learning model M2' is learned so that the error from the correct data, which is the actual number of viewers, is small.

Further, the providing unit 134 provides the viewing information estimated by the estimating unit 133 to the advertiser. Specifically, the providing unit 134 transmits the viewing information estimated by the estimating unit 133 to the advertiser terminal 20.

[2-3. Effects of the second embodiment]
As described above, the information processing device 100A according to the second embodiment includes the receiving section 132 and the estimating section 133A. The reception unit 132 receives from the advertisement client the desired attribute conditions regarding the delivery person attributes of the delivery person whose advertising medium is the delivery person who delivers the product to the user. The estimating unit 133A estimates performance information regarding the performance of the target delivery person, who is a delivery person who satisfies the desired attribute conditions, based on the performance performance of the delivery person.

Thereby, the information processing device 100A can provide the advertiser with operation prediction information regarding the prediction of the operation of the target delivery person that satisfies the desired attribute conditions desired by the advertiser, so that the advertiser's concerns can be It is possible to reduce the risk of ``paying for invisible effects''. Therefore, the information processing device 100A can promote the purchase of advertised products by advertisers.

In addition, when the delivery person attribute information regarding the predetermined delivery person attribute of the delivery person is input into the first machine learning model, the estimation unit 133A performs a delivery based on the operation performance of the delivery person who satisfies the attribute condition regarding the predetermined delivery person attribute. Using the first machine learning model trained to output performance information regarding the delivery person's performance, performance information regarding the target delivery person's performance is estimated.

As a result, the information processing device 100A can appropriately estimate the operation information regarding the target delivery person's operation by using the machine learning model. ” can be reduced.

Further, the estimating unit 133A estimates the number of working target delivery personnel as operation information regarding the working of the target delivery personnel.

Thereby, the information processing device 100A can provide the number of active target delivery workers to the advertiser as operation prediction information.

Furthermore, the estimation unit 133A estimates the total working time of the target delivery person as operation information regarding the operation of the target delivery person.

Thereby, the information processing device 100A can provide the total operating time of the target delivery person to the advertiser as operation prediction information.

In addition, when the delivery person attribute information regarding the predetermined delivery person attribute of the delivery person is input into the second machine learning model, the estimating unit 133A generates an advertisement using the delivery person as an advertising medium that satisfies the attribute conditions regarding the predetermined delivery person attribute. Using a second machine learning model trained to output viewing information about viewers based on the viewing performance of viewers who viewed the program, the second machine learning model was trained to output viewing information about viewers who viewed the advertisement based on the viewing performance of the viewers who viewed the advertisement. Estimate viewing information about.

As a result, the information processing device 100A can provide the advertiser with viewing prediction information regarding the prediction of viewing by viewers who view an advertisement whose advertising medium is a target delivery person who satisfies desired attribute conditions desired by the advertiser. Therefore, it is possible to reduce the risk of ``paying for invisible effects'', which is a concern for advertisers. Therefore, the information processing device 100 can promote the purchase of advertised products by advertisers.

Furthermore, the estimating unit 133A estimates the number of viewers as viewing information regarding viewing by viewers who view an advertisement using the target delivery person as an advertising medium.

Thereby, the information processing device 100A can provide the advertiser with the number of viewers who view an advertisement using the target delivery person as an advertising medium, as viewing prediction information.

Furthermore, the estimating unit 133A estimates the total viewing time of the viewer as viewing information regarding the viewing of the advertisement by the viewer who views the advertisement using the target delivery person as the advertising medium.

Thereby, the information processing device 100A can provide the total viewing time of viewers who view an advertisement using the target delivery person as an advertising medium to the advertiser as viewing prediction information.

[3. Hardware configuration]
Further, the information processing apparatus 100 according to the first embodiment or the information processing apparatus 100A according to the second embodiment described above is realized by, for example, a computer 1000 having a configuration as shown in FIG. 12. FIG. 12 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device 100 or the information processing device 100A. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I/F) 1500, an input/output interface (I/F) 1600, and a media interface (I/F) 1700.

CPU 1100 operates based on a program stored in ROM 1300 or HDD 1400, and controls each section. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, programs depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from other devices via a predetermined communication network and sends it to CPU 1100, and transmits data generated by CPU 1100 to other devices via a predetermined communication network.

The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and mouse via an input/output interface 1600. CPU 1100 obtains data from an input device via input/output interface 1600. Further, CPU 1100 outputs the generated data to an output device via input/output interface 1600.

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200. CPU 1100 loads this program from recording medium 1800 onto RAM 1200 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the information processing device 100 according to the first embodiment or the information processing device 100A according to the second embodiment, the CPU 1100 of the computer 1000 executes a program loaded on the RAM 1200. Accordingly, the functions of the control unit 130 or the control unit 130A are realized. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via a predetermined communication network.

Some of the embodiments of the present application have been described above in detail based on the drawings, but these are merely examples, and various modifications and variations may be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to carry out the invention in other forms with modifications.

[4. others〕
Furthermore, among the processes described in the above embodiments and modified examples, all or part of the processes described as being performed automatically can be performed manually, or are described as being performed manually. All or part of this processing can also be performed automatically using known methods. In addition, information including the processing procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed arbitrarily, unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured.

Further, the information processing device 100 or the information processing device 100A described above may be realized by a plurality of server computers, and depending on the function, an external platform may be called using an API (Application Programming Interface), network computing, etc. The configuration can be changed flexibly.

Further, the embodiments and modifications described above can be combined as appropriate within the range that does not conflict with the processing contents.

Further, the above-mentioned "section, module, unit" can be read as "means", "circuit", etc. For example, the estimating section can be replaced with estimating means or estimating circuit.

1 Information processing system 10 Delivery person terminal 20 Advertiser terminal 100 Information processing device 110 Communication unit 120 Storage unit 121 Delivery person information storage unit 122 Operation performance information storage unit 123 Viewing performance information storage unit 130 Control unit 131 Acquisition unit 132 Reception unit 133 Estimation unit 134 Providing unit 100A Information processing device 120A Storage unit 124A Learning data storage unit 130A Control unit 133A Estimation unit

Claims (10)

a reception unit that receives desired attribute conditions regarding the delivery person attributes of the delivery person whose advertising medium is a delivery person who delivers the product to a user from the advertisement requester;
an estimating unit that estimates operation information regarding the operation of the target delivery person who satisfies the desired attribute condition based on the operation record of the delivery person;
An information processing device comprising: The estimation unit is
When delivery person attribute information regarding a predetermined delivery person attribute of the delivery person is input into a first machine learning model, the delivery person's operation performance based on the performance record of the delivery person that satisfies the attribute condition regarding the predetermined delivery person attribute. estimating operation information regarding the target delivery person's operation using the first machine learning model learned to output operation information regarding the target delivery person;
The information processing device according to claim 1. The estimation unit is
estimating operation information regarding the operation of the target delivery person based on the desired attribute conditions and operation performance information regarding the operation performance of the delivery person;
The information processing device according to claim 1. The estimation unit is
As operation information regarding the operation of the target delivery person, estimating the number of working people of the target delivery person;
The information processing device according to any one of claims 1 to 3. The estimation unit is
Estimating the total working time of the target delivery person as operation information regarding the operation of the target delivery person;
The information processing device according to any one of claims 1 to 4. The estimation unit is
When delivery person attribute information regarding a predetermined delivery person attribute of the delivery person is input into a second machine learning model, viewing and viewing an advertisement using the delivery person as an advertising medium that satisfies the attribute conditions regarding the predetermined delivery person attribute. Using the second machine learning model trained to output viewing information regarding the viewer's viewing based on the viewer's viewing record, the second machine learning model is used to generate information regarding the viewing of the viewer who views the advertisement using the target delivery person as the advertising medium. Estimate viewing information,
The information processing device according to any one of claims 1 to 5. The estimation unit is
Estimating the number of viewers of the viewers as viewing information regarding the viewing of the advertisement using the target delivery person as an advertising medium;
The information processing device according to claim 6. The estimation unit is
Estimating the total viewing time of the viewer as viewing information regarding the viewing by the viewer who views the advertisement using the target delivery person as an advertising medium;
The information processing device according to claim 6 or 7. An information processing method performed by a computer, the method comprising:
a reception step of receiving desired attribute conditions regarding the delivery person attributes of the delivery person whose advertising medium is the delivery person who delivers the product to the user from the advertisement requester;
an estimation step of estimating operation information regarding the operation of the target delivery person who satisfies the desired attribute condition based on the operation record of the delivery person;
Information processing methods including. a reception procedure for receiving desired attribute conditions regarding the delivery person attributes of the delivery person whose advertising medium is the delivery person who delivers the product to the user from the client of the advertisement;
an estimation procedure for estimating operation information regarding the operation of the target delivery person who satisfies the desired attribute condition based on the operation record of the delivery person;
An information processing program that causes a computer to execute.

Images