JP2023146141A - Information processing device, information processing method, and program - Google Patents

Abstract

To accurately predict the possibility of successful package delivery.SOLUTION: An information processing device acquires fact features about each of a plurality of users as user features, creates a relationship graph showing a social relationship between the plurality of users on the basis of the user features, sets a target user among the plurality of users, sets one or more users living with the target user as related users among the plurality of users on the basis of the relationship graph, and predicts the possibility of successful delivery of a package to the target user at a prescribed date and time on the basis of user features of the target user and user features of the related users.SELECTED DRAWING: Figure 8

Description

The present invention relates to an information processing device, an information processing method, and a program, and particularly relates to a technique related to predicting the possibility of a user being at home.

With the spread of electronic commerce in recent years, the demand for package delivery is rapidly increasing. If the user is not at home, the delivery company has to redeliver the package, and furthermore, there is no guarantee that the user will be at home even at the time of recurrence, increasing the burden on the delivery company. As a technology for dealing with such issues, Patent Document 1 discloses a learning model that is trained using the relationship between the user's service usage status and result information indicating whether the user is at home. , a technique for determining whether a user is likely to be at home has been disclosed.

JP2019-016411A

In the technology disclosed in Patent Document 1, the possibility that the target user is home is determined based on information regarding the behavior of the target user, but this information is only local information and it is possible that the target user lives with the user. The possibility that other users are home is not determined.

The present invention has been made in view of the above problems, and aims to provide a technology for accurately predicting the possibility of successful delivery based on comprehensive relationships between a user and multiple other users. purpose.

In order to solve the above problems, one aspect of the information processing device according to the present invention includes an acquisition unit that acquires factual characteristics about each of a plurality of users as user characteristics; creating means for creating a relationship graph showing social relationships among the users; target user setting means for setting target users among the plurality of users; , a related user setting means for setting one or more users who live together with the target user as related users, and a predetermined date and time of a package addressed to the target user based on the user characteristics of the target user and the user characteristics of the related user. prediction means for predicting the probability of successful delivery at.

The prediction means inputs the user characteristics of the target user and the user characteristics of the related user, and uses a machine learning model configured to output the probability of successful delivery of the package at the predetermined date and time, The probability of successful delivery of the package at the predetermined date and time can be predicted.

The probability of successful delivery of the package at the predetermined date and time may be expressed as a number between 0 and 1, with 1 being the maximum probability.

In the relationship graph, each user is represented by each user node, and the creation means may connect each node with a link based on the factual characteristics.

The creation means connects a pair of user nodes having the same factual characteristics with an explicit link, and based on the plurality of pairs of user nodes connected by the explicit link, the pair of user nodes connected by the explicit link is Implicit links can connect pairs of nodes that are not connected.

The generating means may determine the closeness of the connected pair based on one or more factual characteristics shared by the pair.

The user characteristics may include user demographic information and information regarding the user's use of web services.

In order to solve the above problems, one aspect of the information processing method according to the present invention includes an acquisition step of acquiring factual characteristics about each of a plurality of users as user characteristics; a creation step of creating a relationship graph showing social relationships among the users; a target user setting step of setting a target user among the plurality of users; and a target user setting step of setting a target user among the plurality of users based on the relationship graph. , a related user setting step of setting one or more users who live together with the target user as related users, and a predetermined date and time for the package addressed to the target user based on the user characteristics of the target user and the user characteristics of the related user. and predicting the probability of successful delivery at.

In order to solve the above problems, one aspect of the program according to the present invention is an information processing program for causing a computer to perform information processing, the program instructing the computer to obtain user information for each of a plurality of users. an acquisition process for acquiring features as user characteristics; a creation process for creating a relationship graph showing social relationships among the plurality of users based on the user characteristics; a related user setting process that sets one or more users who live with the target user among the plurality of users as related users based on the relationship graph; and a user of the target user. This is for executing a process including a prediction process of predicting the possibility of successful delivery of a package addressed to the target user at a predetermined date and time based on the characteristics and the user characteristics of the related user.

According to the present invention, it is possible to accurately predict the possibility of successful delivery of a product package.
The objects, aspects, and effects of the present invention described above and the objects, aspects, and effects of the present invention not described above can be understood by those skilled in the art by referring to the accompanying drawings and claims. It can be understood from the form of

FIG. 1 shows an example of the configuration of an information processing system. FIG. 2 shows an example of the functional configuration of the information processing device 10 according to the embodiment. FIG. 3 shows a flowchart of the relationship graph creation process. FIG. 4A is a diagram for explaining explicit links. FIG. 4B is a diagram for explaining explicit links. FIG. 4C is a diagram for explaining explicit links. FIG. 4D is a diagram for explaining implicit links. FIG. 5A is a diagram for explaining inference processing of relationships between links. FIG. 5B shows a flowchart of an example process for grouping pairs into clusters. FIG. 6A shows a conceptual diagram of a score (familiarity score) based on the intimacy of the relationship for a user pair. FIG. 6B shows a schematic architecture of the score prediction model 112. FIG. 7 shows a conceptual diagram of a relationship graph. FIG. 8 shows a schematic architecture of the at-home prediction model 111. FIG. 9 shows an example of the hardware configuration of the information processing device 10 and the user device 11. FIG. 10 shows a flowchart of processing executed by the information processing device 10.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments for carrying out the present invention will be described in detail with reference to the accompanying drawings. Among the constituent elements disclosed below, those having the same functions are given the same reference numerals, and their explanations will be omitted. The embodiments disclosed below are examples of means for realizing the present invention, and should be modified or changed as appropriate depending on the configuration of the device to which the present invention is applied and various conditions. The present invention is not limited to this embodiment. Furthermore, not all combinations of features described in this embodiment are essential to the solution of the present invention.

[Functional configuration of information processing device]
FIG. 1 shows a configuration example of an information processing system according to this embodiment. For example, as shown in FIG. 1, this information processing system includes an information processing device 10 and a plurality of user devices 11-1 to 11-N (N>1) used by arbitrary plurality of users 1 to N. ). Note that in the following description, the user devices 11-1 to 11-N may be collectively referred to as the user devices 11 unless otherwise specified. Furthermore, in the following description, the terms user device and user may be used interchangeably.

The user device 11 is, for example, a device such as a smartphone or a tablet, and is capable of communicating with the information processing device 10 via a public network such as LTE (Long Term Evolution) or a wireless communication network such as a wireless LAN (Local Area Network). It is composed of The user device 11 has a display unit (display surface) such as a liquid crystal display, and each user can perform various operations using a GUI (Graphic User Interface) provided on the liquid crystal display. The operation includes various operations on content such as an image displayed on the screen, such as a tap operation, a slide operation, and a scroll operation using a finger, a stylus, or the like.
Note that the user device 11 is not limited to the device shown in FIG. 1, but may be a device such as a desktop PC (Personal Computer) or a notebook PC. In that case, operations by each user may be performed using an input device such as a mouse or a keyboard. Further, the user device 11 may be provided with a separate display screen.

The user device 11 can log into a web service (Internet-related service) provided from the information processing device 10 or from another device (not shown) via the information processing device 10 and use the service. The web services may include online malls, online supermarkets, or services related to communications, finance, real estate, sports, and travel provided via the Internet. By using such a web service, the user device 11 can transmit information regarding the user of the user device 11 to the information processing device 10.

For example, the user device 11 can transmit, to the information processing device 10, information on characteristics related to the user device and the user, such as the IP (Internet Protocol) address of the user device 11, the user's address, and the user's name.
Further, the user device 11 performs positioning calculations based on signals received from GPS (Global Positioning System) satellites (not shown), and generates information obtained by the calculation as position information of the user device 11. , and can be transmitted to the information processing device 10.
The information processing device 10 acquires various information from the user device 11, and creates a relationship graph network (hereinafter referred to as a relationship graph) indicating social relationships between users based on the information. Then, the information processing device 10 uses the created relationship graph to predict the probability of successful delivery of the package addressed to the target user at a predetermined date and time.

[Functional configuration of information processing device 10]
The information processing device 10 according to this embodiment first acquires various information from the user devices 11-1 to 11-N, and creates a relationship graph showing the social relationships among the users 1 to N. Then, the information processing device 10 identifies the target user (the user to whom the package is delivered) among the users 1 to N, and creates information about the target user and information about users related to the target user. Retrieved based on the relationship graph obtained. The information processing device 10 applies the acquired information to a trained machine learning model to predict the possibility of successful delivery of the package to the target user at a predetermined date and time. Note that the package can include any item that can be delivered.

FIG. 2 shows an example of the functional configuration of the information processing device 10 according to this embodiment.
The information processing device 10 shown in FIG. 2 includes a user feature acquisition section 101, a graph creation section 102, a target user feature setting section 103, a related user feature setting section 104, a prediction section 105, a learning section 106, an output section 107, and a learning model storage. 110, and a user characteristic storage section 120. The learning model storage unit 110 stores an at-home prediction model 111 and a score prediction model 112. The various learning models will be described later. Further, the user characteristic storage unit 120 stores user characteristics 121.

The user characteristic acquisition unit 101 acquires factual characteristics (factual information) (hereinafter referred to as user characteristics) about the user devices and users from each of the user devices 11-1 to 11-N. A user characteristic is a fact-based characteristic (information) that is actually or objectively obtained from the user device or user. For example, the user characteristic acquisition unit 101 can acquire user characteristics directly from the user device 11. Further, the user characteristic acquisition unit 101 can acquire user characteristics as information registered in a predetermined web service by the user of the user device 11.

User characteristics include the IP address of the user device, the user's address and name, the credit card number held by the user, and the user's demographic information (demographic information such as gender, age, area of residence, occupation, family structure, etc.) user attributes), etc. Further, the user characteristics include location information (hereinafter referred to as geodata (geographic data)) of the user device for each time slot (time slot).

Further, the user characteristics may include a registration number and a registered name when using a predetermined web service. In addition, user characteristics can be accumulated based on call history, delivery address other than the user's address of the product when using a predetermined web service, usage status when using a predetermined web service, usage history, search history, and service usage. It may also include information regarding possible points. In this way, user characteristics can include any information, including information related to the user device or the user himself, and information related to the use of certain services via communications.
The user feature acquisition unit 101 stores the acquired user feature in the user feature storage unit 120 as the user feature 121.

The graph creation unit 102 creates a relationship graph using the various user characteristics acquired by the user characteristic acquisition unit 101. The relationship graph will be described later.

The target user characteristic setting unit 103 sets the user to whom the package is to be delivered (hereinafter referred to as the target user). The target user may be set by the operator through an input operation using the input unit (input unit 95 in FIG. 9), may be set in advance in the system, or may be set in the storage unit (ROM 92 or RAM 93 in FIG. 9). It may be set by any stored program. Further, the target user characteristic setting unit 103 acquires the user characteristics of the target user from the user characteristics 121 and sets them in the prediction unit 105.

The related user characteristic setting unit 104 determines one or more other users associated with the target user set by the target user characteristic setting unit 103 as related users based on the relationship graph created by the graph creation unit 102. do. In this embodiment, the related user characteristic setting unit 104 determines one or more other users having the same address as the target user as related users. Further, the related user characteristic setting unit 104 may determine one or more users who live in the vicinity of the target user as related users. Further, the related user feature setting unit 104 acquires the user feature of the related user from the user feature 121 and sets it in the prediction unit 105.

The prediction unit 105 calculates a predetermined date and time of the package addressed to the target user based on the user characteristics of the target user set by the target user characteristic setting unit 10 and the user characteristics of the related users set by the related user characteristic setting unit 104. Predicting the probability of successful delivery. In this embodiment, the at-home prediction model 111 trained by the learning unit 106 is used to predict the possibility of successful delivery. The process of predicting the possibility of successful delivery will be described later.

The learning unit 106 learns (trains) the at-home prediction model 111 and the score prediction model 112, and stores the learned at-home prediction model 111 and the score prediction model 112 in the learning model storage unit 110. The learning process for each learning model will be described later.

The output unit 107 outputs the prediction result of the probability of successful delivery predicted by the prediction unit 105. The output unit 107 may generate and output information regarding the predicted probability of successful delivery. The output may be any output process, and may be output to an external device via a communication I/F (communication I/F 97 in FIG. 9), or may be output to a display unit (display unit 96 in FIG. 9). may be displayed.

[Steps to create a relationship graph]
Next, a procedure for creating a relationship graph according to this embodiment will be described. Note that in the following description, users A to E are users referred to for the purpose of description, and may be users of the user device 11. Further, the relationship graph is configured by connecting each user node circled in FIGS. 4A to 4D, and in the following description, the user node will be simply referred to as a user. FIG. 3 shows a flowchart of the relationship graph creation process executed by the graph creation unit 102 according to this embodiment. Each step of the process shown in FIG. 3 will be explained below.

<S31: Creating a link>
In S31, the graph creation unit 102 predicts and creates links between multiple users.
The link creation process will be explained with reference to FIGS. 4A to 4D. 4A to 4C are diagrams for explaining explicit links, and FIG. 4D is a diagram for explaining implicit links. An explicit link is a link created by an explicit common feature between two users (user pair). An implicit link is a link that is created as an indirect relationship by using an already created explicit link, although the existence of an explicit common feature between the user pair is unclear. In this way, links between users are identified as explicit links and implicit links.

FIG. 4A shows an example of creating an explicit link using the IP address of the user's user equipment as a common feature. FIG. 4A shows an example in which an online mall 41, a golf course reservation service 42, a travel-related reservation service 43, and a card management system 44 exist as web services available to users A to C. Although these four web services are shown in FIGS. 4A-4C, the number of web services is not limited to a particular number.

The online mall 41 is a shopping mall that is available online (using the Internet). The online mall 41 can provide a wide variety of products and services, such as fashion, books, food, concert tickets, and real estate, for example.
The golf course reservation service 42 is operated by a website that provides services related to golf courses online, and can provide, for example, golf course searches, reservations, and lesson information.
The travel-related reservation service 43 is operated by a website that provides various travel services available online. The travel-related reservation service 43 can provide, for example, reservations for hotels and travel tours, reservations for airline tickets and rental cars, tourist information, hotels, and information around the hotels.
The card management system 44 is operated by a website that provides services related to credit cards issued and managed by a predetermined card management company. The card management system 44 may provide services in association with at least one of the online mall 41, the golf course reservation service 42, and the travel-related reservation service 43.

In the example of FIG. 4A, users A to C use the same IP address (=198.45.66.xx) to use the online mall 41, the golf course reservation service 42, and the travel-related reservation service 43. . Information on the IP address can be acquired by the user characteristic acquisition unit 101.
In such a case, the graph creation unit 102 creates an explicit link between users A to C (for example, link L1 between users A and C) with the same IP address characteristics, as shown in the link status 45. create.

FIG. 4B shows an example of creating explicit links using features of a user's address as a common feature. Similar to FIG. 4A, FIG. 4B shows an example in which an online mall 41, a golf course reservation service 42, a travel-related reservation service 43, and a card management system 44 exist as web services available to users A to C. Here, users A to C each register the same address (delivery address) and use the online mall 41, the golf course reservation service 42, and the travel-related reservation service 43. Address information can be acquired by the user characteristic acquisition unit 101.
In such a case, the graph creation unit 102 creates an explicit link between users A to C (for example, link L1 between users A and C) with the same address characteristics, as shown in link status 46. do.

FIG. 4C shows an example of creating an explicit link using characteristics of credit card numbers used by users as common characteristics. Similar to FIG. 4A, FIG. 4B shows an example in which an online mall 41, a golf course reservation service 42, a travel-related reservation service 43, and a card management system 44 exist as web services available to users A to C. Here, users A to C each register the same credit card and use the online mall 41, the golf course reservation service 42, and the travel-related reservation service 43. Information including the credit card number can be acquired by the user characteristic acquisition unit 101.
In such a case, the graph creation unit 102 allows users A to C to mutually create explicit links (for example, link L1 between users A and C) with the same card characteristics, as shown in link status 47. do.

FIG. 4D shows an example of creating implicit links between users. In the example of FIG. 4D, user A is connected to user C, user D, and user E through explicit links, and user B is connected to user C, user D, and user E through explicit links. There is. Such link features (features that indicate relationships between links) are embedded in a common feature space, and links that are inferred to implicitly establish relationships between each user (each node) are called implicit links. Created (established) as In the example of FIG. 4D, although users A and B are not connected by an explicit link, it is inferred that they have a relationship in a common feature space, and as a result, an implicit link L2 is created. Note that the graph creation unit 102 learns user relationship graphs (representation learning, relationship learning, embedding learning, knowledge graph embedding) consisting of nodes (users) connected by explicit links. Predict and create implicit links between. At this time, the graph creation unit 102 may perform the learning based on a known embedded model or its extension as appropriate.

<S32: Inference of relationships between links>
In S32, the graph creation unit 102 infers the relationship between the links predicted and created in S31. Processing for inferring relationships between links will be described with reference to FIGS. 5A and 5B. FIG. 5A is a diagram for explaining the process of inferring the relationship between links, and shows an example of inferring the relationship between the links between user A and user B who are connected by an explicit link.

The graph creation unit 102 treats the pair of users connected by the link created in S31 as a data point, and uses the various information acquired by the user characteristic acquisition unit 101 to convert the pair (data point) into a common Group into clusters representing types. The various information can be information such as an IP address, address, credit card, age, gender, and friends. Further, each cluster may be a cluster having relationships such as spouses, parents and children, neighbors, same household, colleagues, friends, same-sex siblings, different-sex siblings, and the like. In the example of FIG. 5A, pairs of users are indicated by cross marks, and the clusters in which the pairs can be grouped include a parent-child cluster 51, a spouse cluster 52, a same-sex sibling cluster 53, a friend cluster 54, and a colleague cluster. Note that although five clusters are shown in FIG. 5A, the number of clusters is not limited to a specific number.

For example, if user A and user B have (share) the characteristics 50 such as the same last name, an age difference of less than 10 years, opposite genders, and the same address, the graph creation unit 102 The pair of A and user B can be grouped into clusters (spouse clusters 52) representing the relationship between husband and wife (spouse).

FIG. 5B shows a flowchart of an example of a process of grouping pairs into clusters, which is executed by the graph creation unit 102.
At the start of S51, it is assumed that the pairs to be grouped have the same address and the same last name. In S52, the graph creation unit 102 determines whether or not the subject pair has the same gender characteristics. If the pair of subjects have the same gender characteristics (Yes in S52), the graph creation unit 102 determines in S53 whether or not the age difference between the pair of subjects is equal to or less than a predetermined threshold (=X value). do. If the difference in age between the pair of objects is greater than the X value (No in S53), the graph creation unit 102 groups the pair of objects into a parent-child cluster 51. If the age difference is less than or equal to the X value (Yes in S53), the graph creation unit 102 groups the subject pair into the same-sex sibling cluster 53. Further, if the pair of subjects do not have the same gender characteristics (No in S52), the graph creation unit 102 determines whether the age difference between the pair of subjects is less than or equal to a predetermined threshold (=Y value) in S54. Determine whether If the age difference is greater than the Y value (No in S54), the graph creation unit 102 groups the subject pair into a parent-child cluster 51. If the age difference is less than or equal to the Y value (Yes in S54), the graph creation unit 102 groups the target pair into a spouse cluster 52.

<S33: Score assignment based on intimacy of relationship>
In S33, the graph creation unit 102 predicts a score based on the intimacy of the relationship for the pair inferred in S32, and assigns the score to the pair. In this embodiment, the score is a numerical value between 0 and 1, but there is no particular limitation on the numerical value that the score can take. FIG. 6A shows a conceptual diagram of a score (hereinafter referred to as an intimacy score) based on the intimacy of a relationship between a pair of users.

In the example of FIG. 6A, the intimacy of the relationship between the user pair changes depending on the characteristics that users A and B who are connected by an explicit link have (share). In the upper part of FIG. 6A, if user A and user B have the characteristics 60 of being siblings of the same gender, same address, 1200 call history, and 50 gift exchanges, the parent of the relationship between the user pair The density (ie, familiarity score) will be high. On the other hand, in the lower part of FIG. 6A, if user A and user B have the characteristics 61 of being siblings of the same gender, different addresses, 30 call history, and 2 gift exchanges, the relationship between the user pair Sexual intimacy (ie, intimacy score) is lower. In this way, as in the example of FIG. 6A, even if users A and B are siblings of the same gender, the intimacy of the relationship between the pair will be lower due to other characteristics shared by the pair of users. It will be different. It is observed that pairs with high relationship intimacy are close to each other's social distance and have high influence. On the other hand, pairs with low relationship intimacy are observed to have a long social distance from each other and are not in a close relationship.

In this embodiment, the familiarity score for a user pair is predicted using the score prediction model 112. FIG. 6B shows a schematic architecture of the score prediction model 112. The score prediction model 112 is a learning model that receives a feature 63 of a user pair as an input and predicts a familiarity score 64 for the feature 63.

The score prediction model 112 is, for example, a learning model that performs weak supervised learning, and is, for example, a learning model using a convolutional neural network (CNN). In this embodiment, the score prediction model 112 is a learning model that is trained using familiarity scores (0 to 1) assigned to multiple features for user pairs as training data, as shown in FIG. 6A. . For example, in the learning stage, combined data such as a familiarity score close to 1 set to the feature 60 in FIG. 6A and a closeness score close to 0 set to the feature 61 in FIG. 6A is used as the teacher data. The learning process is performed by the learning unit 108. Note that the score prediction model 112 may be different for each type of relationship between user pairs, and may be a learning model trained according to one type of relationship.

Note that in this embodiment, the intimacy score for the user pair is predicted using the score prediction model 112, but the graph creation unit 102 may be configured to predict the score using another method.

Through the above processing, explicit links or implicit links are formed between a plurality of users, a familiarity score is assigned between each link, and a relationship graph is created. A conceptual diagram of the relationship graph is shown in FIG. Each of the users 71 to 73 has a plurality of characteristics, and the predicted intimacy score is assigned to the pair of users as described above.

[Processing to predict the possibility of successful delivery of packages addressed to users]
Next, a process for predicting the possibility of successful delivery of a package addressed to a user according to this embodiment will be described. In this embodiment, the prediction unit 105 uses the learned at-home prediction model 111 to predict the possibility of successful delivery of a package addressed to a target user. FIG. 8 shows a schematic architecture of the at-home prediction model 111. The at-home prediction model 111 is, for example, a learning model using a convolutional neural network (CNN).

In the learning stage, the learning unit 106 teaches combinations of the user characteristics acquired by the user characteristic acquisition unit 101 and past delivery history (correct data (label)) associated with at least one of the user characteristics. The at-home prediction model 111 is trained using the data. Specifically, the past delivery history includes delivery date and time information when delivery of a product previously purchased by an arbitrary user using a web service was completed (delivery success). The delivery date and time information includes, for example, the date of delivery (for example, a specific day of the week, a holiday, etc.) and the time slot of delivery (for example, in the morning, 18:00 to 20:00). time, etc.).

The learned at-home prediction model 111 is based on the user characteristics of the target user and the user characteristics of one or more other users (related users) who have the same address as the target user, who are identified based on the created relationship graph. is configured to predict the probability of successful delivery of a package addressed to the target user. As described above, the user characteristics of the target user are set in the prediction unit 105 by the target user characteristic setting section 103, and the user characteristics of the related user are set by the related user characteristic setting section 104. The related user characteristic setting unit 104 may determine one or more other users having the same address as the target user as related users, for example, based on the parent-child cluster 51 and the spouse cluster 52 in FIG. 5A. Furthermore, even if the addresses of multiple users are registered as different addresses, the approximate distance between the user devices as determined by the IP address of each user device may determine that the address is the same as that of the target user. One or more other users may be determined as related users.

In the prediction stage, the prediction unit 105 inputs the user characteristics of the target user, the user characteristics of the related users identified based on the created relationship graph, and the information of the target time slot into the at-home prediction model 111. , predicts the possibility that the target user and/or the related user will be at home. Packages addressed to the target user can be received by other users who live with the target user even if the target user is absent, and the possibility of successful delivery depends on whether the target user and/or the related users are at home. synonymous with gender, or can be applied to the probability of successful delivery. The target time slot information includes not only time slot (time) information but also date information (that is, date and time information). In this embodiment, the at-home prediction model 111 is configured to output the possibility of successful delivery as a numerical value between 0 and 1 (1 being the maximum possibility). Note that in this embodiment, the at-home prediction model 111 may be configured for each time slot. Here, the prediction unit 105 may use the at-home prediction model 111 depending on the time slot.

In this embodiment, as shown in FIG. 8, the user characteristics 82 of the target user, the user characteristics 83 of the spouse of the target user who lives with the target user (that is, has the same address), and the user characteristics 83 of the spouse of the target user who lives with the target user The user characteristics 84 of the parent of the target user and the target time slot 85 (information on a predetermined date and time) are input to the at-home prediction model 111, and the probability 86 of successful delivery in the time slot 85 is predicted. Note that when the at-home prediction model 111 is configured for each time slot, inputting the time slot 85 to the at-home prediction model 111 is not necessary.

As described above, in this embodiment, the probability of successful delivery is expressed as a value between 0 and 1, for example. The prediction unit 105 can determine that the probability of successful delivery is high when the probability of successful delivery 86 output from the at-home prediction model 111 is higher than a predetermined threshold. The predetermined threshold value is, for example, 0.7.

In Figure 8, demographic information (demographic user attributes such as gender, age, area of residence, occupation, family structure, etc.) for each user is used to predict the probability of successful delivery of a package addressed to the target user. , geodata (location information of the user device for each time slot), and the IP address (source address) of the user device are used. Note that the input data to the at-home prediction model 111 is not limited to the data shown in FIG. 8 (demographic information, geodata, IP address), but also all information that each user may have, such as information regarding the user's use of web services. may be input to the at-home prediction model 111.

Further, user characteristics of related users may be weighted and used. For example, the user characteristics of a user with a high intimacy score may be given a high weighting, and the user characteristics of a user with a low intimacy score may be given a low weighting, and these may be input into the at-home prediction model 111.

In the above description, the spouse and parents of the target user are selected (determined) as related users related to the target user, but users who live in the neighborhood of the target user may also be selected. For example, if the target user allows delivery to the home of a user who lives in the neighborhood instead of his or her home through a web service, the prediction unit 105 may predict the possibility that the user who lives in the neighborhood is home. good. In this case, in FIG. 8, instead of/in addition to the characteristics of the target user, the characteristics of the user living in the neighborhood are used, and the characteristics of the user living in the neighborhood and one or more of the users living in the neighborhood User characteristics may also be used to predict the probability of successful delivery of a package addressed to the target user.

[Hardware configuration of information processing device 10]
FIG. 9 is a block diagram showing an example of the hardware configuration of the information processing device 10 according to this embodiment.
The information processing apparatus 10 according to this embodiment can be implemented on any single or multiple computers, mobile devices, or any other processing platform.
Referring to FIG. 9, an example is shown in which the information processing device 10 is implemented in a single computer, but the information processing device 10 according to the present embodiment is implemented in a computer system including a plurality of computers. good. A plurality of computers may be connected to each other through a wired or wireless network so that they can communicate with each other.

As shown in FIG. 9, the information processing device 10 may include a CPU 91, a ROM 92, a RAM 93, an HDD 94, an input section 95, a display section 96, a communication I/F 97, and a system bus 98. The information processing device 10 may also include an external memory.
A CPU (Central Processing Unit) 91 centrally controls operations in the information processing device 10, and controls each component (92 to 97) via a system bus 98, which is a data transmission path.

A ROM (Read Only Memory) 92 is a nonvolatile memory that stores control programs and the like necessary for the CPU 91 to execute processing. Note that the program may be stored in a nonvolatile memory such as an HDD (Hard Disk Drive) 94 or an SSD (Solid State Drive), or an external memory such as a removable storage medium (not shown).
A RAM (Random Access Memory) 93 is a volatile memory and functions as the main memory, work area, etc. of the CPU 91. That is, the CPU 91 loads necessary programs and the like from the ROM 92 into the RAM 93 when executing processing, and implements various functional operations by executing the programs and the like. The learning model storage unit 110 and user characteristic storage unit 120 shown in FIG. 2 may be configured with a RAM 93.

The HDD 94 stores, for example, various data and information necessary when the CPU 91 performs processing using a program. Further, the HDD 94 stores, for example, various data and various information obtained by the CPU 91 performing processing using programs and the like.
The input unit 95 includes a pointing device such as a keyboard and a mouse.
The display section 96 is composed of a monitor such as a liquid crystal display (LCD). The display section 86 may function as a GUI (Graphical User Interface) by being configured in combination with the input section 95.

The communication I/F 97 is an interface that controls communication between the information processing device 10 and external devices.
The communication I/F 97 provides an interface with a network and executes communication with an external device via the network. Via the communication I/F 97, various data, various parameters, etc. are transmitted and received with external devices. In this embodiment, the communication I/F 87 may perform communication via a wired LAN (Local Area Network) or a dedicated line that complies with communication standards such as Ethernet (registered trademark). However, the network that can be used in this embodiment is not limited to this, and may be configured as a wireless network. This wireless network includes a wireless PAN (Personal Area Network) such as Bluetooth (registered trademark), ZigBee (registered trademark), and UWB (Ultra Wide Band). It also includes wireless LAN (Local Area Network) such as Wi-Fi (Wireless Fidelity) (registered trademark) and wireless MAN (Metropolitan Area Network) such as WiMAX (registered trademark). Furthermore, it includes wireless WAN (Wide Area Network) such as LTE/3G, 4G, and 5G. Note that the network only needs to connect each device so that they can communicate with each other, and the communication standard, scale, and configuration are not limited to the above.

At least some of the functions of each element of the information processing device 10 shown in FIG. 2 can be realized by the CPU 91 executing a program. However, at least some of the functions of each element of the information processing device 10 shown in FIG. 2 may operate as dedicated hardware. In this case, the dedicated hardware operates under the control of the CPU 91.

[Hardware configuration of user device 11]
The hardware configuration of the user device 11 shown in FIG. 1 may be the same as that in FIG. 9. That is, the user device 10 may include a CPU 91 , a ROM 92 , a RAM 93 , an HDD 94 , an input section 95 , a display section 96 , a communication I/F 97 , and a system bus 98 . The user device 11 displays various information provided by the information processing device 10 on the display section 96, and performs processing corresponding to input operations received from the user via the GUI (configured by the input section 95 and the display section 96). be able to.

<Processing flow>
FIG. 10 shows a flowchart of processing executed by the information processing device 10 according to this embodiment. The process shown in FIG. 9 can be realized by the CPU 91 of the information processing device 10 loading a program stored in the ROM 92 or the like into the RAM 93 and executing it. For explanation of FIG. 10, reference will be made to the information processing system shown in FIG. It is assumed that the at-home prediction model 111 and the score prediction model 112, which have been learned by the learning unit 106, are stored in the learning model storage unit 110.

In S101, the user characteristic acquisition unit 101 acquires the user characteristics of each user from the user devices 11-1 to 11-N, and stores them as the user characteristics 121 in the user characteristic storage unit 120. The process of S101 may be a process of acquiring (collecting) user characteristics during a certain period in the past.

In S102, the graph creation unit 102 creates relationship graphs for users 1 to N using the various user characteristics acquired by the user characteristic acquisition unit 101. The procedure for creating the relationship graph is as described above.

In S103, the target user characteristic setting unit 103 sets a user (target user) to whom the package will be delivered from among users 1 to N. As described above, the target user may be set by the operator through an input operation using the input unit 95, may be set in advance in the system, or may be set by an arbitrary program stored in the ROM 92 or RAM 93. May be set. Furthermore, in S<b>103 , the target user characteristic setting unit 103 acquires the user characteristics of the target user from the user characteristics 121 and sets them in the prediction unit 105 .

In S104, the related user characteristic setting unit 104 determines one or more other users having the same address as the target user as related users based on the relationship graph created by the graph creation unit 102. Further, the related user feature setting unit 104 acquires the user feature of the related user from the user feature 121 and sets it in the prediction unit 105.

In S105, the prediction unit 105 inputs the user characteristics of the target user, the user characteristics of the related user, and the target time slot (date and time) set in S103 and S104 to the at-home prediction model 111, and Predict the probability of successful delivery of a package addressed to the target user in the target time slot.

In S106, the output unit 107 outputs the prediction result of the probability of successful delivery predicted in S105. The output unit 107 may generate information regarding the prediction result and output it to an external device (not shown).

In this way, the information processing device 10 creates a relationship graph network (relationship graph) indicating social relationships between users from the user characteristics of a plurality of users, and based on the relationship graph, Predict the likelihood of successful delivery of a package addressed to you. As a result, the accuracy of predicting the probability of successful delivery of a package addressed to a target user can be improved, and the risk of redelivery by a delivery company can be reduced.

Note that although specific embodiments have been described above, these embodiments are merely illustrative and are not intended to limit the scope of the present invention. The apparatus and methods described herein may be embodied in forms other than those described above. In addition, appropriate omissions, substitutions, and changes may be made to the embodiments described above without departing from the scope of the present invention. Such omissions, substitutions, and modifications are included within the scope of the claims and their equivalents, and fall within the technical scope of the present invention.

1 to N: User, 10: Information processing device, 11-1 to 11-N: User device, 101: User feature acquisition unit, 102: Graph creation unit, 103: Target user feature setting unit, 104: Related user feature setting 105: Prediction unit, 106: Learning unit, 107: Output unit, 110: Learning model storage unit, 111: At-home prediction model, 112: Score prediction model, 120: User feature storage unit, 121: User characteristics

In order to solve the above problems, one aspect of the information processing device according to the present invention includes an acquisition unit that acquires factual characteristics about each of a plurality of users as user characteristics, and a target user among the plurality of users. One or more users who live together with the target user among the plurality of users are set as related users based on a target user setting means to be set and a relationship graph showing social relationships among the plurality of users. It has a related user setting means, and a prediction means for predicting the possibility of successful delivery of a package addressed to the target user at a predetermined date and time based on the user characteristics of the target user and the user characteristics of the related user.

In the relationship graph, each user is represented by a respective user node, and each user node can be connected with a link based on the factual characteristics.

In the relationship graph , a pair of user nodes having the same factual characteristics are connected by an explicit link, and based on a plurality of pairs of user nodes connected by the explicit link, the pair of user nodes are connected by the explicit link. Pairs of user nodes that are not linked may be connected with implicit links.

The relationship graph may have a closeness assigned to the connected pair of user nodes based on one or more factual characteristics shared by the pair .

In order to solve the above problems, one aspect of the information processing method according to the present invention includes an acquisition step of acquiring factual characteristics about each of a plurality of users as user characteristics, and a target user among the plurality of users. One or more users who live with the target user among the plurality of users are set as related users based on a target user setting step and a relationship graph showing social relationships among the plurality of users. The method includes a related user setting step, and a prediction step of predicting the possibility of successful delivery of a package addressed to the target user at a predetermined date and time based on the user characteristics of the target user and the user characteristics of the related user.

In order to solve the above problems, one aspect of the program according to the present invention is an information processing program for causing a computer to perform information processing, the program instructing the computer to obtain user information for each of a plurality of users. an acquisition process for acquiring features as user characteristics; a target user setting process for setting a target user among the plurality of users; and a relationship graph indicating social relationships between the plurality of users . A related user setting process that sets one or more users who live together with the target user among a plurality of users as related users, and a related user setting process that sets one or more users who live together with the target user as related users, and a process for setting a message addressed to the target user based on the user characteristics of the target user and the user characteristics of the related user. This is for executing a process including a prediction process for predicting the possibility of successful delivery of a package at a predetermined date and time.

Claims (9)

acquisition means for acquiring factual characteristics about each of the plurality of users as user characteristics;
Creation means for creating a relationship graph showing social relationships between the plurality of users based on the user characteristics;
Target user setting means for setting target users among the plurality of users;
Related user setting means for setting one or more users who live together with the target user among the plurality of users as related users based on the relationship graph;
Prediction means for predicting the possibility of successful delivery of a package addressed to the target user at a predetermined date and time based on the user characteristics of the target user and the user characteristics of the related user;
An information processing device comprising: The prediction means inputs the user characteristics of the target user and the user characteristics of the related user, and uses a machine learning model configured to output the probability of successful delivery of the package at the predetermined date and time, The information processing apparatus according to claim 1, wherein the information processing apparatus predicts the possibility of successful delivery of the package at the predetermined date and time. 3. The information processing apparatus according to claim 1, wherein the probability of successful delivery of the package at the predetermined date and time is expressed as a numerical value between 0 and 1, with 1 being the maximum probability. 4. In the relationship graph, each user is represented by each user node, and the creation means connects each node with a link based on the factual characteristics. The information processing device described. The creation means connects a pair of user nodes having the same factual characteristics with an explicit link, and based on the plurality of pairs of user nodes connected by the explicit link, the pair of user nodes connected by the explicit link is 5. The information processing apparatus according to claim 4, wherein pairs of nodes that are not connected are connected by implicit links. 6. The information processing apparatus according to claim 4, wherein the creation means determines the intimacy of the connected pair based on one or more factual features shared by the pair. 7. The information processing apparatus according to claim 1, wherein the user characteristics include user demographic information and information regarding the user's use of a web service. an acquisition step of acquiring factual features about each of the plurality of users as user features;
a creation step of creating a relationship graph showing social relationships among the plurality of users based on the user characteristics;
a target user setting step of setting a target user among the plurality of users;
a related user setting step of setting one or more users who live together with the target user among the plurality of users as related users based on the relationship graph;
a prediction step of predicting the possibility of successful delivery of a package addressed to the target user at a predetermined date and time based on the user characteristics of the target user and the user characteristics of the related user;
An information processing method characterized by having the following. An information processing program for causing a computer to perform information processing, the program causing the computer to:
an acquisition process of acquiring factual features about each of the plurality of users as user features;
a creation process of creating a relationship graph showing social relationships between the plurality of users based on the user characteristics;
Target user setting processing for setting a target user among the plurality of users;
a related user setting process of setting one or more users who live with the target user among the plurality of users as related users based on the relationship graph;
A prediction process for predicting the possibility of successful delivery of a package addressed to the target user at a predetermined date and time based on the user characteristics of the target user and the user characteristics of the related user. be,
Information processing program.

Images