JP7171350B2 - Information processing device and program - Google Patents

Description

The present invention relates to an information processing apparatus and program.

Patent Literature 1 discloses an advertisement delivery system capable of controlling advertisements delivered to user terminals based on user location information.

JP 2018-81670 A

However, it may be difficult to always obtain the user's location information in real time. For example, if the user's device is out of battery, cannot connect to the network, or is not running an application related to location information, it is difficult for the ad distributor to obtain the user's location information in real time.

The present invention has been made in view of such circumstances, and provides an information processing device and a program capable of efficiently distributing appropriate advertisements to users even when the user's location information cannot be obtained satisfactorily. intended to provide

Various embodiments of the present invention are illustrated below. The embodiments shown below can be combined with each other.

According to the present invention, an information processing device configured to be able to communicate with a user terminal operated by a user, comprising a location information acquisition unit, a related information acquisition unit, a behavior prediction unit, and a distribution control unit, wherein the location information acquisition The unit is configured to be able to acquire position information of the user terminal, and the related information acquisition unit acquires at least traffic information, weather information, SNS information, search information, calendar information, ticket information, accommodation reservation information, and behavior pattern information. Related information including one can be acquired from the user terminal, the related information is information generated by the user operating the user terminal, and the behavior prediction unit receives the position information and Based on at least one of the related information, it is configured to be able to execute a prediction process for predicting the user's staying position at a first time, and the distribution control unit is configured to perform a prediction process in a predetermined time period from the first time. An information processing device is provided that is configured to be capable of distributing a predetermined advertisement to the user terminal, the advertisement being an advertisement set in advance for each region.

In the present invention, it is possible to predict the user's staying position at the first time based on the positional information and related information, and to distribute an advertisement corresponding to the staying position based on the prediction.

Various embodiments of the present invention are illustrated below. The embodiments shown below can be combined with each other.

1 is a schematic diagram of a system 100 including an information processing device 1 according to an embodiment of the invention; FIG. 3 is a functional block diagram of a user terminal 5; FIG. FIG. 3A shows part of the log transmitted from the user terminal 5. FIG. FIG. 3B is an example of action prediction-related data generated by the action prediction module 10. FIG. FIG. 3C is an example of advertisement distribution-related data managed by the advertisement distribution module 20. FIG. 4 is an example of a flowchart representing processing by the system 100. FIG. FIG. 7 is a diagram showing how the behavior prediction module 10 re-executes prediction processing and rewrites behavior prediction-related data. 6 is an example of a flow chart showing processing of distribution control by the advertisement distribution module 20. FIG. It is an example of a flow chart showing processing of distribution control when action prediction related data is updated. 4 is a conceptual diagram for explaining various states that change according to time t; FIG. 4 is a schematic diagram showing a reachable range estimated by a reachable range estimating unit 17. FIG.

Embodiments of the present invention will be described below with reference to the drawings. Various features shown in the embodiments shown below can be combined with each other.

1. Outline of Information Processing Apparatus 1 As shown in FIG. 1 , the information processing apparatus 1 according to the present embodiment includes an action prediction module 10 , an advertisement distribution module 20 , a storage section 30 and a communication section 40 . The information processing device 1 is configured by a computer such as a server.

The behavior prediction module 10 includes a user ID acquisition unit 11, a position information acquisition unit 12, a time acquisition unit 13, a related information acquisition unit 14, a behavior prediction unit 15, a state estimation unit 16, a reach range estimation unit 17, and a monitoring unit 18. .

The advertisement distribution module 20 includes a bid control section 21 and a distribution control section 22 .

The information processing device 1 is configured to be able to communicate with a user terminal 5 operated by a user. In this embodiment, the information processing device 1 is configured to be able to communicate with a plurality of user terminals 5 via the network NT, and the information processing device 1 and the user terminals 5 constitute a system 100 . Here, the user terminal 5 is composed of, for example, a smart phone, tablet device, laptop computer, car navigation system, portable music player, smart watch, smart glasses, and the like. The configuration of the information processing apparatus 1 will be specifically described below.

(1-1) Action prediction module 10
The user ID acquisition unit 11 acquires a user ID for identifying a user who owns the user terminal 5 . Information such as a user name is specified by the user ID.

The location information acquisition unit 12 is configured to be able to acquire location information of the user terminal 5 . Specifically, the location information acquisition unit 12 acquires current location information where the user terminal 5 exists. Location information includes latitude and longitude. In addition, it is preferable that the location information includes information about base stations with which the user terminal 5 communicates and area information specified by short-range wireless communication such as Bluetooth (registered trademark).

Here, as shown in FIG. 3A, the location information acquisition unit 12 preferably acquires the user ID, the current time, and the fixed location information in the future together with the location information.

The time acquisition unit 13 acquires the current time acquired from a program stored in the information processing device 1 or from another information processing device. The time acquisition unit 13 is configured to be able to acquire the time when the position information was transmitted from the user terminal 5 or the time when the communication unit 40 received the position information. Hereinafter, in this embodiment, the time when the position information is transmitted from the user terminal 5 will be used for the sake of simplification of explanation.

The related information acquisition unit 14 is configured to acquire related information including at least one of traffic information, weather information, SNS information, search information, calendar information, ticket information, accommodation reservation information, and behavior pattern information. The acquisition route of the related information is not particularly limited, and the relevant information may be acquired from the user terminal 5 or may be acquired from the user terminal 5 via another server. Here, the relevant information is information generated by the user operating the user terminal 5 . Specifically, it is generated by executing a specific application on the user terminal 5 or by operating a search engine. For example, when searching for a train scheduled to arrive at Karuizawa at 10:00 on August 23, 2018, the estimated time of arrival, place of arrival, and means of transportation are traffic information. Also, when searching for the weather in Karuizawa at 10:00 on August 23, 2018, the date and time and location are the weather information resulting from the weather investigation. Also, the SNS information is generated by analyzing the content written by the user of the user terminal 5 on SNS (Social Network System). For example, by performing a natural language analysis on the content posted on the SNS, SNS information indicating that the user will move to a specific place on a specific date and time is generated. Also, search information is generated due to a search word by a search engine. Search information is generated by natural language analysis in the same manner as SNS information. Also, the calendar information is generated based on the calendar in which the user's schedule is entered. For example, a calendar application installed in the user terminal 5 or a schedule entered in a web application format calendar becomes the calendar information. The ticket information is information about event tickets such as concerts and exhibitions at a predetermined place on a predetermined date and time, reserved seat tickets for bullet trains, express trains, etc., and other tickets (eg, advance tickets for a designated date and time). The ticket information is generated by inputting into the user terminal 5 information related to the ticket reserved by the user in addition to the electronic ticket reserved by the user terminal 5 . Further, the lodging reservation information is information relating to lodging at a predetermined place on a predetermined date and time. The lodging reservation information is generated by inputting to the user terminal 5 information about the lodging reservation reserved by the user in addition to the lodging reservation reserved by the user terminal 5 . Also, the behavioral pattern information is information representing a user's usual behavioral pattern, and is generated from, for example, calendar information and location information for the past 1 to 12 months.

The behavior prediction unit 15 is configured to be capable of executing a prediction process of predicting the user's stay position at the first time based on at least one of the position information and the related information. In this embodiment, the stay position is a concept that includes not only a point defined by latitude and longitude, but also a predetermined range centering on such point. Here, the first time is a future time after execution of the prediction process. For example, if the location information of the user terminal 5 obtained at 10:00 on August 1, 2018 indicates Tokyo Station, and the location information obtained at 12:00 on the same day indicates the vicinity of Nagoya, see related information. By doing so, it can be predicted that the user's stay position at 12:30 (first time) on August 1, 2018 is around Nagoya. Here, it is possible to predict the user's stay position at the first time only from the change in position information without using the related information, but in order to improve the prediction accuracy, refer to the related information together with the position information. preferably. Conversely, it is also possible to perform prediction processing using only related information without using position information.

Here, the action pattern information is information that generalizes the user's actions in a predetermined period, and the user does not always act according to the action pattern, so the prediction accuracy is relatively low compared to other information. On the other hand, traffic information, weather information, SNS information, search information, ticket information, and lodging reservation information do not depend on the user's behavior pattern, and contain necessary information at that time. becomes relatively large. Therefore, in the present embodiment, the action prediction unit 15 compares the degree of contribution of at least one of traffic information, weather information, SNS information, and search information to the prediction process with the contribution of action pattern information to the prediction process. to a larger value. In addition, it has been empirically recognized that prediction processing using calendar information is often intermediate between the above information and behavior pattern information, so the degree of contribution to prediction processing of calendar information is It is preferable to set the information to an intermediate level between the above information and the behavior pattern information.

Then, coefficients corresponding to the degrees of contribution set in three stages are set, and prediction processing by the behavior prediction unit 15 is executed based on at least one of the position information and the related information.

The state estimator 16 is configured to be able to estimate the user's state based on at least one of the positional information and related information. The state here represents at least one of the classification of the place where the user is estimated to stay and the movement state of the user. Specifically, the classification of places where the user is estimated to stay includes home, workplace, convenience store, movie theater, beauty salon, restaurant, game arcade, and the like. In addition, the moving state of the user includes stationary, walking, bicycle, car, train, airplane, and the like.

The reachable range estimation unit 17 is configured to be capable of estimating a reachable range reachable by the user between now and the third time based on the user's current stay position and map data. The map data may be stored in the storage unit 30 or may be data provided by other companies. Further, in the present embodiment, the reachable range estimating unit 17 is configured to be able to estimate the reachable range that the user can reach from the current time to the third time by referring to the position information, the related information, and the state. Here, the third time represents the time after the lapse of a predetermined time from the current time. A specific estimation method of the reachable range estimation unit 17 will be described later with reference to FIG. 9 .

The monitoring unit 18 monitors position information acquired by the user ID acquisition unit 11 . In the present embodiment, whether or not the location information of the user terminal 5 acquired by the monitoring unit 18 in a predetermined time period from the first time indicates outside a predetermined range from the stay location predicted in the prediction process. is determined. Specifically, when the behavior prediction unit 15 predicts that the user is staying in Kyoto at 13:00 (first time) on August 1, 2018, 13:00 (first time) When the location information of the user terminal 5 acquired in a predetermined time period (eg, 12:45 to 13:15) from the It is determined that it is outside a predetermined range from the position (Kyoto). Here, the predetermined range can be arbitrarily set. For example, a range that can be reached within one hour from the stay position predicted by the prediction process, or a predetermined range around the stay position predicted by the prediction process Can be set as concentric circles of distance. Also, the predetermined time period can be obtained by referring to the current time obtained by the time obtaining unit 13 .

(1-2) Ad distribution module 20
The bid control unit 21 is for bidding on an advertising slot for posting an advertisement distributed to the user terminal 5 by the advertisement distribution module 20 . The bidding control unit 21 executes a bidding process for the provider of the information processing device 1 to secure an advertisement space for an advertisement display medium such as a smartphone application. Here, the type of advertisement is not particularly limited, and image advertisements or video advertisements displayed on cooking recipe apps, SNS, video viewing services, homepages, blogs, etc., and voices played while using music distribution services or car navigation systems It may be an advertisement.

The distribution control unit 22 is configured to be able to distribute a predetermined advertisement to the user terminal 5 in a predetermined time period from the first time. For example, to distribute a predetermined advertisement to the user terminal 5 during a predetermined time period (eg, 12:45 to 13:15) from 13:00 (first time) on August 1, 2018. can be done. In this embodiment, such an advertisement is an advertisement preset for each region. Here, the predetermined time zone can be obtained by referring to the current time obtained by the time obtaining unit 13 .

(1-3) Storage unit 30
The storage unit 30 stores various programs and data, and includes, for example, memory, hard disk, SSD, and the like. In this embodiment, the storage unit 30 stores action prediction related data and advertisement distribution related data. Here, the behavior prediction-related data is data used for user behavior prediction processing by the behavior prediction module 10 . Further, the advertisement delivery-related data is data used for advertisement delivery control by the advertisement delivery module 20 .

In this embodiment, as shown in FIG. 3B, the behavior prediction related data includes a user ID, predicted arrival and departure times at a predetermined point, and predicted arrival point. In the example of FIG. 3B, in the case of a user whose user ID is represented by ABC, prediction results for behavior from August 23, 2018 to August 25, 2018 based on at least one of location information and related information is stored. Here, the behavior prediction-related data is generated by the behavior prediction unit 15 executing prediction processing. The storage unit 30 associates them and stores them as action prediction related data. Further, as shown in FIG. 3C, the advertisement distribution related data includes an advertiser ID for identifying an advertiser who distributes an advertisement, a banner ID for individually identifying an advertisement, and an advertisement distribution point for distributing an advertisement. The storage unit 30 associates them and stores them as advertisement delivery-related data. Here, in the example of FIG. 1, the storage unit 30 is provided in the information processing apparatus 1, but the storage unit 30 is provided outside the information processing apparatus 1, and the information processing apparatus 1 can store the storage unit 30 as necessary. It may be in the form of so-called cloud computing that accesses to.

(1-4) Communication unit 40
The communication unit 40 is configured to be capable of data communication with other constituent elements of the information processing device 1, the user terminal 5, and other information processing devices by wire or wirelessly. In this embodiment, the communication unit 40 transmits and receives various data between the information processing device 1 and the user terminal 5 via the network NT.

Here, in the example of FIG. 1, the behavior prediction module 10 and the advertisement distribution module 20 are configured to be provided inside one information processing device 1, but the behavior prediction module 10 and the advertisement distribution module 20 are provided by separate servers may be configured. At this time, the behavior prediction related data may be stored in the server that constitutes the behavior prediction module 10 and the advertisement distribution related data may be stored in the server that constitutes the advertisement distribution module 20 . In this case, a communication unit is provided for each server.

2. Overview of User Terminal 5 Next, the user terminal 5 will be described with reference to FIG. In this embodiment, the user terminal 5 includes a user ID acquisition section 51 , a location information acquisition section 52 , a related information acquisition section 53 , a control section 54 , a storage section 55 , a display section 56 and a communication section 57 .

The user ID acquisition unit 51, the location information acquisition unit 52, the related information acquisition unit 53, and the communication unit 57 have the same functions as the user ID acquisition unit 11, the location information acquisition unit 12, the related information acquisition unit 14, and the communication unit 40, respectively. Prepare.

The control unit 54 controls various elements forming the user terminal 5 according to a program (not shown) stored in the storage unit 55 . The storage unit 55 stores various programs and data for controlling the user terminal 5, and is composed of, for example, memory, hard disk, SSD, and the like. The display unit 56 displays various images and moving images.

In one embodiment, the user ID acquisition unit 51 and the location information acquisition unit 52 can be realized using a program that operates within the user terminal 5 as SDK (Software Development Kit). In this case, a program that implements the user ID acquisition unit 51 and the location information acquisition unit 52 is stored in the storage unit 55 . Also, the related information acquired by the related information acquisition unit 53 is information acquired from various applications installed in the user terminal 5 .

Then, various information acquired by the user ID acquisition unit 51 , the position information acquisition unit 52 and the related information acquisition unit 53 are transmitted from the communication unit 57 to the communication unit 40 of the information processing device 1 . Then, the information received by the communication unit 40 is acquired by the user ID acquisition unit 11, the position information acquisition unit 12, and the related information acquisition unit 14. FIG.

In this embodiment, the communication section 57 transmits and receives various data to and from the communication section 40 of the information processing apparatus 1 via the network NT.

Here, each component constituting the information processing apparatus 1 and the user terminal 5 may be realized by software or by hardware. When realized by software, various functions can be realized by the CPU executing a program. The program may be stored in a built-in storage unit, or may be stored in a computer-readable non-temporary recording medium. Alternatively, a program stored in an external storage unit may be read out and implemented by so-called cloud computing. When implemented by hardware, it can be implemented by various circuits such as ASIC, FPGA, or DRP. In this embodiment, various information and concepts including this are handled, and these are represented by high and low signal values as binary bit aggregates composed of 0 or 1, and the above software or hardware Communication and computation can be performed according to the aspect of .

3. Flow of Processing Executed by Information Processing Apparatus 1 (3-1) Overall Flow Next, processing executed by the information processing apparatus 1 will be described with reference to FIGS. 4 and 5. FIG.

As shown in FIG. 4, position information is transmitted from the user terminal 5 to the behavior prediction module 10 in S1.

The behavior prediction module 10 receives the location information transmitted from the user terminal 5 in S11.

Next, in S<b>12 , the location information of the user terminal 5 and the time when the location information was transmitted are acquired by the location information acquisition unit 12 and the time acquisition unit 13 .

Next, in S<b>13 , related information is acquired by the related information acquisition unit 14 . Here, the execution timing of S13 is arbitrary, and S13 may be executed before S11.

Next, in S14, the monitoring unit 18 determines whether or not the position information at the time acquired in S12 is within a predetermined range from the stay position predicted by the behavior prediction unit 15. . Then, if the user's current position is within a predetermined range (YES), the behavior prediction module 10 transmits a distribution control instruction to the advertisement distribution module 20 to instruct distribution control of advertisement distribution.

On the other hand, in S14, when the user's current position is outside the predetermined range (NO), the process proceeds to S15 to update the action prediction related data. Such update is performed by the action prediction unit 15 re-executing the prediction process. That is, in the present embodiment, the behavior prediction unit 15 determines that the location information of the user terminal 5 acquired during the predetermined time period from the first time is outside the predetermined range from the stay location predicted in the prediction process. If so, the prediction process is re-executed to predict the user's stay position at the second time.

Re-execution of the prediction process will be specifically described below with reference to FIG. 3B. For example, the behavior prediction module 10 acquired location information from the user terminal 5 during a predetermined time period (eg, 9:45 to 10:15) from 10:00 (first time) on August 23, 2018. In this case, it is determined whether or not the position information is included within a predetermined range (eg, a concentric circle with a radius of 5 km centered on Karuizawa) from the stay position (Karuizawa at the predicted arrival point) predicted in the prediction process. . Then, when the prediction by the action prediction module 10 is incorrect, the prediction process is re-executed using the position information acquired in S12. This predicts the user's staying position at the second time (eg, 10:30 on August 23, 2018). Here, the second time represents a time later than the first time.

As a result, as shown in FIG. 5, the action prediction related data is rewritten, and the rewritten action prediction related data is stored in the storage unit 30 .

On the other hand, the advertisement distribution module 20 receives the distribution control command transmitted from the action prediction module 10 in S21.

Next, distribution control is executed in S22. Then, in S23, the advertisement is distributed to the user terminal 5. FIG.

(3-2) Distribution Control The distribution control in S22 of FIG. 4 will be described below with reference to FIGS. 6 and 7. FIG.

<When there is no update of behavior prediction related data: YES in S14>
As shown in FIG. 6, in S221, the advertisement distribution module 20 interprets the distribution control instructions received from the behavior prediction module 10. FIG. Then, this flow is executed when the instruction indicating that the action prediction related data is updated is not included.

Next, in S222, the distribution control unit 22 searches for the advertiser ID and banner ID corresponding to the user's predicted stay position. In the example of FIG. 3C, when the predicted stay position of the user at 10:00 (first time) on August 23, 2018 is Karuizawa, advertisement distribution related data is searched, and advertiser IDs 123 and 456 are specified. Then, banner IDs 1000 and 1002 corresponding to each advertiser are identified. Here, these advertisements are preferably advertisements relating to shops, cafes, hotels, sightseeing spots, etc. around Karuizawa.

Next, in S223, the distribution control unit 22 refers to the order of priority for distributing advertisements. For example, priority is set in advance in descending order of the fee paid to the provider of the information processing device 1 from the advertiser ID, or in ascending order of the number of times the user is contacted with the specific advertisement. is referred to in S223. Note that the method of determining the order of priority is not particularly limited, and the order may be changed as appropriate.

Then, in S224, the distribution control unit 22 distributes the advertisement corresponding to the predicted stay position based on the order of priority. Here, the delivery time of the advertisement is not particularly limited, and it is not necessary to deliver the advertisement exactly at the first time. For example, if the user's predicted stay position at 10:00 (first time) on August 23, 2018 is Karuizawa, a predetermined time zone from the first time (eg: 9:45 to 10:15) ) may serve ads. At this time, it is preferable to distribute advertisements in descending order of priority in S223. This makes it possible to distribute advertisements in advance while on a train heading for the predicted stay position, or to distribute advertisements after arriving at the predicted stay position.

<When action prediction related data is updated: NO in S14>
As shown in FIG. 7, at S225, the advertisement distribution module 20 interprets the distribution control instructions received from the behavior prediction module 10. FIG. Then, this flow is executed when an instruction to the effect that the behavior prediction related data is updated is included.

Next, in S<b>226 , the bid control unit 21 stops the advertisement bidding executed by the advertisement distribution module 20 . This is because even if an advertisement corresponding to the originally predicted location of stay (Karuizawa) is distributed in Nagoya, where the user is actually expected to stay, the advertisement effect is considered to be low.

At the same time, the distribution control unit 22 stops distributing the advertisement corresponding to the initial predicted stay position. That is, in the present embodiment, the distribution control unit 22 determines that the location information of the user terminal 5 acquired during the predetermined time period from the first time is outside the predetermined range from the stay location predicted in the prediction process. If so, stop delivering the advertisement corresponding to the predicted stay position. This is because it is predicted that the user will move to Nagoya instead of Karuizawa, which is the originally predicted location of stay. The distribution of advertisements about Karuizawa that was scheduled to be distributed before will be stopped.

Next, in S227, the advertiser ID and banner ID corresponding to the predicted stay position after the re-execution of the prediction process are searched. In the present embodiment, as shown in FIG. 5 (after rewriting), when the user's predicted stay position at 10:30 (second time) on August 23, 2018 is Nagoya, the advertisement distribution-related data is searched. , Nagoya are identified. Then, the banner ID 1003 corresponding to the advertiser is identified. Here, such advertisements are preferably advertisements relating to stores, cafes, hotels, sightseeing spots, etc. around Nagoya.

Then, in S228, the distribution advertisement to be distributed from the advertisement distribution module 20 to the user terminal 5 is changed. Specifically, the delivery advertisement specified by banner ID1000,1002 is changed into the delivery advertisement specified by banner ID1003. That is, in the present embodiment, the behavior prediction unit 15 determines that the location information of the user terminal 5 acquired during the predetermined time period from the first time is outside the predetermined range from the stay location predicted in the prediction process. If so, a prediction process is performed to predict the user's stay position at the second time. Then, the distribution control unit 22 is configured to be able to distribute the advertisement corresponding to the user's staying position at the second time to the user terminal 5 .

This improves the possibility of delivering advertisements corresponding to the user's actual staying position even if the result of the prediction processing is incorrect.

As described above, the information processing apparatus 1 according to the present embodiment, even if it is not possible to acquire the position information from the user terminal 5 in real time, based on at least one of the position information and the related information, the information processing apparatus 1 can predict the user's future. behavior can be predicted. As a result, even if the user's current location information cannot be obtained and the user's location cannot be accurately determined, advertisements corresponding to the predicted location where the user is expected to stay can be delivered appropriately. becomes possible.

4. State Estimation Next, state estimation performed by the state estimator 16 will be described with reference to FIG. Here, state estimation is not essential, and can be combined with the above-described prediction processing as needed.

FIG. 8 is an example of a result of prediction processing by the action prediction unit 15. In FIG. For example, it is assumed that the behavior prediction unit 15 predicts that the user will board a train bound for Kamakura at 8:00 on a certain day and return home from Kamakura at 17:00. In this case, the state estimating unit 16 calculates the distance to the user's home address and the train station, and if it takes 20 minutes at a general walking speed, the state estimating unit 16 can walk from "home" at 7:40. I'm assuming you're leaving. Then, the state estimation unit 16 estimates that the user is in the "moving" state from the time the user leaves the "home" until the time the user arrives at the station. At this time, the user's stay position before 7:40 can be estimated using the user's position information and related information. Here, the address of the user may be stored in advance in the storage unit 30 of the information processing device 1, or may be obtained from related information such as SNS information of the user.

Also, when the behavior prediction unit 15 predicts that the user will stay in Kamakura between 10:00 and 17:00, the state estimation unit 16 estimates that the user's state during that time is "sightseeing". Furthermore, when it is predicted that the user will arrive at the local station at 19:00, and it is found from the related information that the friend is requesting the pick-up and drop-off, the state estimation unit 16 It can be presumed that the user will travel by "car" to his/her home. Note that the state estimating unit 16 estimates that the user is in the "moving" state until the user arrives at home from the local station, in the same manner as described above.

Based on the state estimated in this way, it becomes possible to distribute an advertisement according to the state of the user from the advertisement distribution module 20 to the user terminal 5 . For example, if it is presumed to be at "home", it will deliver advertisements about hobbies. Also, when it is presumed that the user is traveling by "train", an advertisement about an English conversation school is delivered. Also, when it is estimated that the user is traveling by "car", a voice advertisement can be delivered so as not to reduce the attention to driving.

Such state estimation can be incorporated in S22 of FIG. 4, and appropriate advertisements can be delivered in S23 according to the result of state estimation. In this case, the distribution control unit 22 is configured to be able to switch advertisements to be distributed to the user terminal 5 based on the state of the user.

5. Reaching Range Estimation Next, referring to FIG. 9, reaching range estimation executed by the reaching range estimating unit 17 will be described. Here, reaching range estimation is not essential, and can be combined with the above-described prediction processing as necessary.

In this embodiment, the reachable range estimating unit 17 is configured to be able to estimate the reachable range that the user can reach from the current time to the third time based on the user's current stay position and the map data. . For example, position information representing the current (eg, 15:00) stay position of the user is acquired, or a third time (eg, :16:00) to estimate the reachable range that the user can reach. Such estimation is performed with reference to map data including information on roads, buildings, topography, etc., and based on average moving speeds. In FIG. 9 , the reachable range at the third time estimated by the reachable range estimation unit 17 is represented by a dotted line.

Here, the reaching range estimation by the reaching range estimating section 17 can refer to the result of state estimation by the state estimating section 16 . For example, when it is estimated that the user will take a “taxi” from now on, the reachable range that can be reached within a predetermined period of time is wider than in the case of “walking”.

Such reach estimation can be incorporated in S22 of FIG. 4, and appropriate advertisements can be delivered in S23 according to the result of reach estimation. In this case, the distribution control unit 22 is configured to be able to switch advertisements to be distributed to the user terminal 5 based on the coverage estimated by the coverage estimation unit 17 .

Specifically, as shown in FIG. 9, it is assumed that a user who will or is predicted to stay at point X at 15:00 is predicted to board a train at 16:00. At this time, it is assumed that the stores targeted for advertisements that can be delivered by the advertisement delivery module 20 are store A, store B, and store C. FIG. Then, if the required time from point X to store A, store B, and store C is 10 minutes, 5 minutes, and 60 minutes, respectively, even if an advertisement about store C is distributed, it will reach store C from point X. By this time, it is already time for the train to depart, and the user is practically unable to head to the store C. Therefore, the advertisement distribution module 20 stops distributing the advertisement regarding the store C.

On the other hand, if the required time from store A and store B to the station is 15 minutes and 10 minutes, respectively, even if you go from point X to the station via store A and store B, you will not be able to reach the station by the departure time of the train. be in time. However, if the average stay time at store A is 30 minutes and the average stay time at store B is 60 minutes, even if the user is guided to store B, taking into account the departure time of the train, store B is sufficiently visited. Difficult to enjoy. Therefore, in the example of FIG. 9, the distribution control unit 22 preferably sets the advertisement regarding the store A as a distribution target based on the reach range.

6. Others The information processing apparatus 1 according to the present invention can also be implemented in the following aspects.

causing the computer to function as a location information acquisition unit, a related information acquisition unit, a behavior prediction unit, and a distribution control unit;
The location information acquisition unit is configured to be able to acquire location information of a user terminal operated by a user,
The related information acquisition unit is configured to acquire related information including at least one of traffic information, weather information, SNS information, search information, calendar information, ticket information, accommodation reservation information, and behavior pattern information from the user terminal. ,
The related information is information generated by the user operating the user terminal,
The behavior prediction unit is configured to be capable of executing a prediction process of predicting a position of stay of the user at a first time based on at least one of the position information and the related information,
The distribution control unit is configured to be able to distribute a predetermined advertisement to the user terminal in a predetermined time period from a first time,
The advertisement is an advertisement set in advance for each stay location,
program.

Moreover, you may provide as a computer-readable non-temporary recording medium which stores the above-mentioned program.

Further, the transmission route of information transmitted from the user terminal 5 to the information processing device 1 is not particularly limited. For example, in addition to the mode in which information is transmitted from the user terminal 5 to the information processing device 1, it is also possible to transmit the information via another information processing device operated by a third party. In this case, the information transmitted from the user terminal 5 may be received by another information processing device, and the information may be promptly transmitted to the information processing device 1, or may be transmitted to the information processing device 1 at regular intervals. good.

1: Information processing device 10: Action prediction module 11: User ID acquisition unit 12: Position information acquisition unit 13: Time acquisition unit 14: Related information acquisition unit 15: Action prediction unit 16: State estimation unit 17: Reach range estimation unit 18 : Monitoring unit 20 : Ad distribution module 21 : Bid control unit 22 : Distribution control unit 30 : Storage unit 40 : Communication unit 5 : User terminal 51 : User ID acquisition unit 52 : Location information acquisition unit 53 : Related information acquisition unit 54 : Control unit 55: Storage unit 56: Display unit 57: Communication unit 100: System

Claims (8)

An information processing device configured to be communicable with a user terminal operated by a user,
Equipped with a location information acquisition unit, a related information acquisition unit, a behavior prediction unit, and a distribution control unit,
The location information acquisition unit is configured to be able to acquire location information of the user terminal,
The related information acquisition unit is configured to be able to acquire related information including at least one of traffic information, weather information, SNS information, search information, calendar information, ticket information, accommodation reservation information, and behavior pattern information,
The related information is information generated by the user operating the user terminal,
The behavior prediction unit is configured to be capable of executing a prediction process of predicting the user's stay position at a first time based on the position information and the related information ,
The behavior prediction unit predicts the degree of contribution of at least one of the traffic information, the weather information, the SNS information, the search information, the ticket information, and the accommodation reservation information to the prediction processing, and predicts the prediction of the behavior pattern information. Set large compared to the contribution to processing,
The distribution control unit is configured to be able to distribute a predetermined advertisement to the user terminal in a predetermined time period from a first time,
The advertisement is an advertisement preset for each region,
Information processing equipment. If the location information of the user terminal acquired in a predetermined time period from a first time is outside a predetermined range from the stay location predicted in the prediction processing, the behavior prediction unit performs the prediction processing. and predicting the user's stay position at a second time,
The information processing device according to claim 1 . When the position information of the user terminal acquired in a predetermined time period from a first time is outside a predetermined range from the stay position predicted in the prediction process, the distribution control unit performs the predicted stop the delivery of advertisements corresponding to the location of stay;
The information processing apparatus according to claim 1 or 2 . If the location information of the user terminal acquired in a predetermined time period from a first time is outside a predetermined range from the stay location predicted in the prediction processing, the behavior prediction unit performs the prediction processing. to predict the user's stay position at a second time,
The distribution control unit is configured to be capable of distributing an advertisement corresponding to the user's staying position at a second time to the user terminal.
The information processing apparatus according to any one of claims 1 to 3 . a state estimator,
The state estimation unit is configured to be able to estimate the state of the user based on the position information and the related information ,
The state represents at least one of a classification of a place where the user is estimated to stay and a travel state of the user;
The distribution control unit is configured to be able to switch advertisements to be distributed to the user terminal based on the state.
The information processing apparatus according to any one of claims 1 to 4 . a reachable range estimator,
The reachable range estimating unit is configured to be capable of estimating a reachable range reachable by the user between now and a third time based on the user's current stay position and map data,
The distribution control unit is configured to be able to switch advertisements to be distributed to the user terminal based on the range of reach.
The information processing apparatus according to any one of claims 1 to 5 . a state estimator,
The state estimation unit is configured to be able to estimate the state of the user based on the position information and the related information ,
the state represents at least one of a classification of a place where the user stays and a travel state of the user;
The reachable range estimating unit is configured to be able to estimate a reachable range reachable by the user between now and a third time by referring to the position information, the related information, and the state.
The information processing device according to claim 6 . causing the computer to function as a location information acquisition unit, a related information acquisition unit, a behavior prediction unit, and a distribution control unit;
The location information acquisition unit is configured to be able to acquire location information of a user terminal operated by a user,
The related information acquisition unit is configured to acquire related information including at least one of traffic information, weather information, SNS information, search information, calendar information, ticket information, accommodation reservation information, and behavior pattern information,
The related information is information generated by the user operating the user terminal,
The behavior prediction unit is configured to be capable of executing a prediction process of predicting the user's stay position at a first time based on the position information and the related information ,
The behavior prediction unit predicts the degree of contribution of at least one of the traffic information, the weather information, the SNS information, the search information, the ticket information, and the accommodation reservation information to the prediction processing, and predicts the prediction of the behavior pattern information. Set large compared to the contribution to processing,
The distribution control unit is configured to be able to distribute a predetermined advertisement to the user terminal in a predetermined time period from a first time,
The advertisement is an advertisement preset for each region,
program.

Images