JP2020027489A - Device, method, and program for processing information - Google Patents

Abstract

To allow for accurately identifying actions taken by a user in a facility.SOLUTION: An information processing device of the present invention includes an acquisition unit and an identification unit. The acquisition unit is configured to acquire location information indicative of a location of a user within a facility based on predetermined features of a space in the facility when the location of the user cannot be determined using an external signal from outside the facility. The identification unit is configured to identify an action taken by the user in the facility using the location information acquired by the acquisition unit.SELECTED DRAWING: Figure 3

Description

  An embodiment of the present invention relates to an information processing device, an information processing method, and an information processing program.

  In recent years, information distribution via the Internet has been actively performed. For example, there is known a technique of arranging and displaying advertisement content such as a still image, a moving image, and text related to a company or a product at a predetermined position on a web page. By the way, there is known a technology that allows a user having a communication terminal to easily find a target product.

JP-A-2003-166847

  However, according to the above-described conventional technology, it is not always possible to accurately specify an action performed by a user in a facility. For example, in the above-described related art, navigation information from a current position to a display position of a product is generated from a comparison between the current position information and the display position information, and the generated navigation information is displayed on a terminal.

  In order to enable navigation in the above-described conventional technology, a plurality of transmitting units for transmitting identification information to a communication terminal must be installed in a store, and information may be accurately transmitted from the transmitting unit depending on the installation location. It cannot always be obtained. For this reason, in the above-described conventional technology, it is not always possible to accurately specify the action performed by the user in a situation where the position of the user inside the facility (indoor) cannot be determined.

  The present application has been made in view of the above, and an object of the present invention is to provide an information processing apparatus, an information processing method, and an information processing program that can specify a behavior performed by a user in a facility with high accuracy. .

  The information processing apparatus according to the present application indicates a position of the user in the facility based on a feature of a predetermined space in the facility in a state where the position of the user cannot be determined based on an external signal from outside the facility. An acquisition unit for acquiring position information, and a specification unit for specifying an action performed by the user in the facility based on the position information acquired by the acquisition unit.

  According to an aspect of the embodiment, there is an effect that an action performed by a user in a facility can be specified with high accuracy.

FIG. 1 is a diagram illustrating an example of first information processing according to the embodiment. FIG. 2 is a diagram illustrating an example of the second information processing according to the embodiment. FIG. 3 is a diagram illustrating a configuration example of the information processing apparatus according to the embodiment. FIG. 4 is a diagram illustrating an example of the behavior information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of a model information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the magnetic information storage unit according to the embodiment. FIG. 7 is a flowchart illustrating an example of the first information processing according to the embodiment. FIG. 8 is a flowchart illustrating an example of the second information processing according to the embodiment. FIG. 9 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device.

  Hereinafter, an embodiment of an information processing apparatus, an information processing method, and an information processing program according to the present application (hereinafter, referred to as “embodiment”) will be described with reference to the drawings. The information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by the embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and overlapping description will be omitted.

[1. Overview of first information processing]
First, an outline of the first information processing of the information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of first information processing according to the embodiment. The first information processing is performed by the information processing device 100.

  Although the first information processing will be described in detail later, an action performed by the user is specified among step-by-step actions leading to a predetermined action based on position information indicating the position of the user, and the identification is performed. The advertising effect is determined based on the action performed.

  The information processing system according to the embodiment includes a terminal device 10 and an information processing device 100. Further, the first information processing is performed by the information processing apparatus 100 shown in FIG. For example, the information processing device 100 is realized by one or more devices such as a server device and a cloud system, and communicates with a terminal device 10 used by a user via a network such as a mobile communication network or a wireless LAN (Local Area Network). An information processing device capable of communication.

  The terminal device 10 is an information processing device used by a user. The terminal device 10 is, for example, a smartphone, a tablet terminal, a notebook PC (Personal Computer), a desktop PC, a mobile phone, a PDA (Personal Digital Assistant), or the like. In addition, the terminal device 10 displays various contents such as advertisement contents.

  Here, a premise that the first information processing is performed by the information processing apparatus 100 will be described. For example, advertisers advertise their products, services, human resources, etc. by providing various forms of advertising content. Examples of the form of the advertisement content include an Internet advertisement, a TV commercial, a traffic advertisement, an outdoor advertisement using a signboard or a signage, and a distribution flyer.

  For example, an advertiser attempts to increase advertising effectiveness by providing various types of advertising content by submitting advertising content and paying advertising costs to an advertising distributor. Also, the ad distributor can improve the advertiser by visualizing the effect of the submitted advertisement content on the user and feeding back the visualized data to the advertiser. This will be used as a consideration for the advertising method.

  However, it is not easy to visualize how much the advertising content actually affected the user and how directly the advertising content directly affected the business KPI of the advertiser. For example, it is possible to monitor the subsequent online (online) behavior of a user who has come into contact with an Internet advertisement, but the behavior of the user is not limited to online behavior, but may be behavior in the real world, that is, Some actions are offline. For example, when a user who comes into contact with advertising content takes steps offline in a step-by-step manner, it will eventually lead to conversion of the advertising content, It is not easy to visualize whether or not it is affected by

  That is, it is not easy to determine or evaluate the influence of the advertising content from the side of the user's gradual behavior. For this reason, in the present embodiment, the advertising effect is measured using the time and the position information of the user for each action in each step among the stepwise actions. For example, an element (anchor) for acquiring a time and a position related to the advertisement content is installed in a real space in each place in advance. Anchors can be thought of as offline versions of cookies for online behavior tracking, and are used to identify the current location and cut out the state of the moment. In the present embodiment, the anchor is a beacon and a script embedded in the advertisement content, but the anchor is not necessarily required. For example, the anchor may be various sensors (for example, a magnetic sensor, an optical sensor, etc.).

  The beacon, which is an anchor, may be, for example, an information processing device that has distributed advertising content, a station, a road (a telephone pole beside a road), or a common part such as a corridor in a facility (for example, a real store) related to the advertising content. , Product shelves, etc.). In the present embodiment, the action of the user is converted into time and location information for each action in each step of the step-wise actions directly or indirectly related to the predetermined advertisement content by the anchor alone or the interaction between the anchors. Specify from the viewpoint of. Specifically, in the present embodiment, a step-by-step action from the advertisement creative submission to the conversion is defined, and the advertising effect is measured using time and location information throughout all phases of the step-by-step action. In the following embodiments, a stepwise action or an action at each step may be referred to as a “funnel”.

  Then, based on the above assumption, the information processing apparatus 100 according to the embodiment performs the first information processing shown in FIG. Specifically, the information processing apparatus 100 acquires position information indicating the position of the user, and specifies an action performed by the user among step-by-step actions leading to a predetermined action based on the acquired position information. I do. Then, the information processing device 100 determines the advertising effect based on the specified behavior.

  More specifically, the information processing apparatus 100 performs the step-by-step behavior from the user's contact with the predetermined advertising content to the conversion related to the advertising content as the step-wise behavior until the predetermined behavior is reached. Among the actions, the action performed by the user is specified. In addition, the information processing apparatus 100 is a probability that is output by inputting position information and time information to a model generated based on a step-by-step action leading to a predetermined action. Based on the probability of the user performing the step-by-step action up to the predetermined action, the action performed by the user is specified among the step-by-step actions until the predetermined action.

  Hereinafter, an example of the first information processing according to the embodiment will be described with reference to FIG. Although FIG. 1 shows an example in which only position information is input to the model, time information is actually input.

  First, the overall image of FIG. 1 will be briefly described. First, it is assumed that the user U1 has the terminal device 10 and starts moving after making contact with the advertisement content AD1 (viewing the advertisement content AD1). The advertising content AD1 is advertising content for advertising the product PD1. In the shop SH1, which is an actual store, a product PD1 is sold. Therefore, the shop SH1 can be said to be a store related to the advertisement content AD1.

  Also, it is assumed that a beacon is installed in each area and place from the home HP1, which is the home of the user U1, to the shop SH1. In the example of FIG. 1, the area AR1 including the home HP1, the area AR2 including the station ST1, the area AR3 including the facility BL, the area AR4 including the shop SH1, the entrance G of the shop SH1, and the predetermined sales area AR5 in the shop SH1. A beacon is installed on the product shelf M1, the product shelf M2, and the cash register M3 to be placed.

  In such a state, the information processing apparatus 100 first defines a step-wise action (funnel) (step S11). By setting the beacons in various places as described above, the information processing apparatus 100 appropriately obtains, from the beacon, the behavior information indicating the behavior of the user, which is the behavior information detected by the beacon, and acquires the behavior information storage unit 121. (FIG. 4). For this reason, the information processing apparatus 100 performs machine learning based on the behavior information stored in the behavior information storage unit 121, and uses the behavior tendency obtained by machine learning (for example, deep learning) as one funnel. Define. More specifically, the information processing apparatus 100 extracts a series of relevant behavior trends from the behavior trends obtained by machine learning, and defines each extracted behavior tendency as one funnel.

  Here, an example in which the information processing apparatus 100 defines a funnel by machine learning has been described, but the information processing apparatus 100 may define the funnel using an arbitrary method. Further, the funnel may not be defined by the information processing apparatus 100 but may be manually defined hypothetically. In such a case, a funnel defined manually is input to the information processing apparatus 100.

  In the example of FIG. 1, the information processing apparatus 100 defines the following seven funnels as a stepwise action from when the user U1 comes into contact with the advertising content AD1 to when the user U1 purchases (converts) the product PD1. I do. Specifically, the information processing apparatus 100 includes a funnel F1 indicating a gradual action such as “leaving home HP1 and heading for station ST1”, a funnel F2 indicating a gradual action such as “waiting for a train at station ST1”, “ A funnel F3 indicating a gradual action such as “coming before the facility BL”, a funnel F4 indicating a gradual action such as “coming to the shop SH1”, and a gradual action such as “coming before the product shelf M1”. It is assumed that a funnel F41, a funnel F42 indicating a gradual action such as "come before the commodity shelf M2", and a funnel F43 indicating a gradual action such as "come before the cash register M3" are defined.

  Subsequently, the information processing apparatus 100 generates a prediction model for each funnel defined in step S11 (step S12). Although it has been described above that the information processing apparatus 100 defines a funnel by machine learning, the information processing apparatus 100 can generate a prediction model by machine learning at this time. In the example of FIG. 1, the information processing apparatus 100 includes, as prediction models corresponding to the funnel F1, a model M1, a model M2 corresponding to the funnel F2, a model M3 corresponding to the funnel F3, a model M4 corresponding to the funnel F4, and a funnel F41. A corresponding model M41, a prediction model M42 corresponding to the funnel F42, and a model M43 corresponding to the funnel F43 are generated.

  Taking the model M1 corresponding to the funnel F1 as an example, in the model M1, when the position information indicating the current position of the user and the time information indicating the time at which the user is at the current position are input, at this time, the "home" This is a model that outputs the probability that the user is performing an action such as “going out of HP1 and heading for station ST1”. The information processing apparatus 100 generates such a model by performing machine learning on the behavior information stored in the behavior information storage unit 121 and acquiring a behavior tendency. Therefore, the prediction model generated by the information processing device 100 is a model that predicts a user's behavior at the position and the time based on the position and the time of the user.

  In such a state, the information processing apparatus 100 acquires position information indicating the current position of the user U1 and time information indicating the time at which the user U1 is at the current position (step S13). At this time, it is assumed that the user U1 is located at the position PT1 away from the home HP1. In the example of FIG. 1, the position PT1 is included in the area AR1. Therefore, the position information “PT1” of the user U1 and the time information at this time are detected by the beacon in the area AR1. Therefore, in such an example, the information processing apparatus 100 acquires the position information “PT1” and the time information at this time from the beacon in the area AR1. Hereinafter, the time information is omitted.

  It is assumed that the user U1 has moved from the position PT1 to a position PT2 where the station ST1 is located. In such a case, the information processing apparatus 100 acquires the position information “PT2” from the beacon in the area AR2. It is assumed that the user U1 has moved from the position PT2 to a position PT3 in front of the facility BL. In such a case, the information processing apparatus 100 acquires the position information “PT3” from the beacon in the area AR3. Further, it is assumed that the user U1 has moved from the position PT3 to the position PT4 of the entrance G of the shop SH1. In such a case, the information processing apparatus 100 acquires the position information “PT4” from the beacon in the area AR4.

  Thereafter, it is assumed that the user U1 enters the shop SH1 and reaches the sales area AR5. It is also assumed that the user U1 has arrived at the position PT41 in front of the product shelf M1. In such a case, the information processing apparatus 100 acquires the position information “PT41” from the beacon installed on the product shelf M1. It is also assumed that the user U1 has arrived at the position PT42 in front of the product shelf M2. In such a case, the information processing apparatus 100 acquires the position information “PT42” from the beacon installed on the product shelf M2. Further, it is assumed that the user U1 has come before the cash register M3. In such a case, the information processing apparatus 100 acquires the position information “PT43” from the beacon installed in the cash register M3.

  Next, the information processing device 100 specifies the behavior of the user U1 based on the probability output by inputting the position information and the time information to the prediction model (Step S14). For example, the information processing apparatus 100 inputs position information to each of the seven prediction models shown in FIG. 1 and, if the highest probability among the output probabilities is equal to or higher than a predetermined probability (for example, 80%), the most The action of the user U1 is specified based on the funnel corresponding to the prediction model that has output a high probability. For example, the information processing apparatus 100 calculates seven probabilities by inputting the position information “PT1” to each of the seven prediction models. For example, the information processing apparatus 100 outputs a probability “90%” from the model M1, a probability “75%” from the model M2, a probability “50%” from the model M3, a probability “20%” from the model M4, and a probability “5” from the model M41. %, The probability "5%" is calculated from the model M42, and the probability "5%" is calculated from the model M43.

  Then, since the model M1 that has output the probability “90%” (predetermined probability of 80% or more) corresponds to the funnel F1, the information processing apparatus 100 determines that the user U1 exits the home HP1 and exits the station ST1 at the position PT1. Head to ”. More specifically, since there is a premise that the user U1 has come into contact with the advertising content AD1, the information processing apparatus 100 determines that the user U1 "goes out of the home HP1 to the station ST1 (to cover the product PD1)" at the position PT1. Heading ". Although the time information has been omitted, in each prediction model, a higher probability is calculated as the time from contact with the advertisement content AD1 to reaching the position PT1 is shorter. For example, if the user U1 is at the position PT1 5 minutes after contacting the advertising content AD1, even if the probability “90%” is calculated from the model M1, 24 hours after contacting the advertising content AD1. When the user U1 is at the position PT1, a probability “10%” may be calculated from the model M1.

  By the way, in the above example, the information processing apparatus 100 shows an example in which the position information “PT1” is input to each of the seven prediction models, but other position information (position information PT2, PT3, PT4, PT41, PT42, PT43). The action of the user U1 is specified in the same manner for ()). Then, the information processing device 100 determines the advertising effect based on the specified behavior (Step S15).

  Here, for example, if an action indicating a probability of “80%” or more is specified from each prediction model (Pattern 1), the user U1 first purchases the product PD1 by contacting the advertising content AD1 with “ Leaves home HP1 and heads for station ST1 ", then" waits for train at station ST1 ", then" stops at facility BL ", then" arrives in front of shop SH1 ", and then" goods in shop SH1 " It is possible to specify that a step-by-step action such as "browse the product on the shelf M1", then "browse the product on the product shelf M2 in the shop SH1", and finally, "purchase the product on the cash register M3" is performed. For example, if the product PD1 is displayed on the product shelf M1 or M2, it can be confirmed that the user U1 has certainly purchased the product PD1.

  In such a case, the information processing apparatus 100 determines that the user U1 has purchased (converted) the product PD1 due to the contact with the advertisement content AD1, for example, because the advertisement effect of the advertisement content AD1 is “high”. . Note that the information processing device 100 may represent the advertising effect with a predetermined index value. Further, the information processing apparatus 100 can determine that the user U1 takes the stepwise action as described above due to the influence of the advertisement content AD1. Although only the user U1 is illustrated in FIG. 1, for example, when a similar gradual action is specified for another user, the information processing apparatus 100 determines that the user is as described above due to the influence of the advertisement content AD1. It can also be determined that there is a tendency to take a stepwise action. For example, the information processing apparatus 100 may determine that there is a tendency to stop at the facility BL before purchasing the product PD1.

  On the other hand, for example, it is assumed that the behavior indicating the probability “80%” or more is specified from the models M1 and M2, but the other models calculate only a low probability of about 10% and cannot specify the behavior ( Pattern 2). In such a case, even if the user U1 contacts the advertisement content AD1, the user U1 does not go to buy the product PD1, but can predict that he has just headed for the station ST1. Therefore, in such a case, the information processing apparatus 100 determines that the advertisement effect of the advertisement content AD1 is “low”.

  Finally, the information processing apparatus 100 notifies (feeds back) the advertiser of the advertising effect determined in step S15 (step S16). In the example of FIG. 1, the information processing device 100 notifies the advertiser of the advertising content AD1 of the advertising effect. For example, in the case of the above-described pattern 1, the information processing apparatus 100 notifies the advertisement effect “high” and the trend information indicating the tendency. As a result, the advertiser can formulate an advertising strategy such that a further advertising effect can be expected if a billboard advertisement is placed near the facility BL.

  Further, for example, in the case of the above-described pattern 2, the information processing apparatus 100 notifies the user U1 that he or she has traveled to the station ST1 together with the advertisement effect “low”. In this case, the advertiser can formulate an advertising strategy that, if the advertisement content AD1 is posted at the station ST1, the advertiser can go to the shop SH1 to buy the product PD1.

  Now, the first information processing according to the embodiment has been described. As described with reference to FIG. 1, the information processing apparatus 100 acquires position information indicating a position of the user, and, based on the acquired position information, among the step-by-step actions leading to a predetermined action, the user performs Identify actions. Then, the information processing device 100 determines the advertising effect based on the specified behavior.

  Thereby, the information processing apparatus 100 can determine with high accuracy how much the advertising content has affected the user. Specifically, the information processing device 100 can determine with high accuracy how much the advertising content has affected the user's offline behavior. In addition, the information processing apparatus 100 may cause a user to perform a conversion when the user touches the advertisement content, and when and where the action is performed. Since it is possible to determine whether or not the advertiser will make the advertiser, it is possible to make the advertiser effectively build up the advertising power.

[2. Outline of second information processing]
Next, the outline of the second information processing of the information processing according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating an example of the second information processing according to the embodiment. The second information processing is also performed by the information processing device 100.

  The second information processing will be described in detail later. However, in a state where the position of the user cannot be determined based on an external signal from outside the facility, the position information acquired based on the feature of a predetermined space in the facility is acquired. Is used to identify the action performed by the user in the facility.

  Here, the assumption that the second information processing is performed by the information processing apparatus 100 will be described. For example, for FMCG (Fast Moving Consumer Goods: daily necessities or consumer goods), it is considered that an important theme in advertising on a market scale is to measure the advertising effectiveness. For example, a manufacturer of FMCG, in a state where advertising content related to its own FMCG is struck, determines whether or not a user has come (contacted) to a product shelf in which a company's FMCG is placed in an actual store. It is set as an indicator.

  However, it may be difficult to detect a user's action such as whether or not the user has come to a product shelf with high accuracy. For example, by using the position information acquired by the GPS function of the terminal device 10 (an example of an external signal from outside the facility), it can be determined whether or not the user has visited a store where the target FMCG is sold. . However, in a store (in a facility), there is a problem that the GPS function cannot be effectively used because the GPS signal is blocked by the building. Specifically, there is a problem that it is not possible to detect where the user is located in the store. Then, it becomes difficult to specify the behavior of the user in the store.

  Therefore, a method of installing a beacon at a predetermined location in a store (for example, a common area such as a corridor, a product shelf, or the like) and acquiring position information of a user in the store based on information acquired by the beacon has been considered. Can be However, since many beacons are required, there is a problem in installation cost. In addition, when many beacons are installed, the operation becomes difficult, and as a result, the operation of each beacon becomes complicated. Further, if the operation becomes complicated, it is naturally difficult to obtain high-accuracy position information, and the accuracy of the beacon itself is not high in the first place. For this reason, a method using a beacon may not be practical just because GPS does not function effectively in a store.

  On the basis of such a premise, the second information processing utilizes geomagnetic positioning by geomagnetism instead of beacon. That is, based on the above assumption, the information processing apparatus 100 according to the embodiment performs the second information processing illustrated in FIG. Specifically, the information processing apparatus 100 is configured to determine the position of the user in the facility based on the characteristics of a predetermined space in the facility in a state where the position of the user cannot be determined based on an external signal from outside the facility. Is obtained. Then, the information processing apparatus 100 specifies an action performed by the user in the facility based on the acquired position information.

  Specifically, the information processing apparatus 100 acquires position information based on magnetic characteristics distributed in the predetermined space as characteristics of the predetermined space in the facility. More specifically, the information processing apparatus 100 determines, based on a change pattern in which magnetism distributed in a predetermined space changes according to the presence of an object in the predetermined space, as a feature of the magnetism distributed in the predetermined space. To obtain location information.

  Hereinafter, an example of the second information processing according to the embodiment will be described with reference to FIG. In FIG. 1, when acquiring the position information of the user in the area AR5 in the shop SH1 (an example of a facility), the information processing apparatus 100 transmits the position information of the user detected by the beacon installed in the area AR5. The example of acquiring is shown. Therefore, similarly in FIG. 2, the area AR5 in the shop SH1 will be described as an example. However, as described in the premise, since the use of the beacon has various problems, the information processing apparatus 100 acquires the position information using geomagnetic positioning instead of the beacon, and performs the action of the user U1 based on the position information. To identify.

  As shown in FIG. 2, in the area AR5, a passage RD1 passes in a mesh shape, and along the passage RD1, there is an area of a merchandise shelf on which merchandise of each company (manufacturer) is displayed. In the example of FIG. 2, in the area AR5, an area AR51 in which a product shelf X1 in which products of the company C1 are displayed is placed, an area AR52 in which a product shelf X2 in which products of the company C2 are displayed, and products in the company C3. Are placed in an area AR53 in which a product shelf X3 in which products of the C4 company are displayed, an area AR54 in which a product shelf X4 in which products of the company C4 are displayed, and an area AR55 in which a product shelf X5 in which products of the company C5 are displayed are located in the companies AR6 and C6. There is an area AR56 where a product shelf X6 on which products are displayed is placed.

  In the example of FIG. 2, the area AR5 includes an area where the merchandise shelves M1 and M2 described in FIG. 1 are placed and an area where the cash register M3 is placed.

  In such a state, first, a predetermined investigator (for example, an employee of a management company managing the information processing apparatus 100) investigates the state of the geomagnetism in the area AR5 to obtain magnetic data. (Step S21). For example, an investigator walks around the passage RD1 using a predetermined measuring device to investigate the state of geomagnetism in the passage RD1 and obtain magnetic data.

  Next, the researcher creates a magnetic map based on the magnetic data (step S22). The magnetic map is represented by a heat map corresponding to the intensity of geomagnetism as shown in FIG. In the example of FIG. 2, the researcher creates a magnetic map MA1 corresponding to the passage RD1. Note that such a magnetic map may be created by the information processing device 100. In such a case, the information processing apparatus 100 creates the magnetic map MA1 by analyzing the magnetic data obtained in step S21. Further, the information processing apparatus 100 stores the created magnetic map MA1 in the magnetic information storage unit 123.

  The magnetic pattern of the geomagnetism changes indoors under the influence of a structure forming a building, an object placed in the room, and the like. Therefore, it can be said that the magnetic pattern in the area AR5 is a pattern unique to the area AR5. For this reason, the magnetic pattern in the area AR5 can be understood as an example of a feature of one space such as the area AR5, more specifically, an example of a feature of magnetism distributed in the area AR5.

  Then, it is assumed that the user U1 has walked around the area AR5. The terminal device 10 has a geomagnetic sensor, and the geomagnetic sensor acquires the geomagnetism around the user U1 in response to the user U1 walking (step S23). For example, the geomagnetic sensor acquires the geomagnetism at the current location of the user U1 every time the user U1 moves. In other words, the geomagnetic sensor measures or detects the geomagnetism around the user U1. Further, the terminal device 10 transmits the measurement result data indicating the magnetism acquired by the geomagnetic sensor to the information processing device 100 (Step S24).

  The information processing apparatus 100 calculates a change pattern in which the geomagnetism changes in the area AR5 based on the measurement result data obtained from the terminal device 10, that is, the (magnetism) that changes according to the movement of the user U1 (step S25). ). Then, the information processing apparatus 100 acquires position information indicating the current location of the user U1 based on the calculated change pattern (Step S26). For example, the information processing apparatus 100 specifies a time-series change in geomagnetism by matching the change pattern with the magnetic map MA1. Then, the information processing apparatus 100 acquires (specifies) the position information of the user U1 by estimating the transition route of the user U1 based on the specified time-series change.

  Next, the information processing apparatus 100 specifies an action performed by the user U1 in the area AR5 based on the position information of the user U1 acquired in Step S26 (Step S27). In this example, it is assumed that the information processing apparatus 100 has specified that the user U1 has performed an action such as after coming in front of the product shelf X2 and then coming in front of the product shelf X1. More specifically, it is assumed that the information processing apparatus 100 has specified that the user U1 has performed an action of browsing the product on the product shelf X2 after browsing the product on the product shelf X2.

  Here, it is assumed that the user U1 has contacted the advertising content of the company C1 as an advertiser (for example, browses the advertising content of the company C1 on the terminal device 10) before coming to the shop SH1. It is also assumed that the company C1 has requested the information processing apparatus 100 (or a business owner that manages the information processing apparatus 100) to measure the advertising effect of its own advertising content. Alternatively, it is assumed that the company C1 has submitted its own advertising content to the information processing apparatus 100 (or a business owner that manages the information processing apparatus 100).

  In such a case, the information processing apparatus 100 determines whether the user U1 has performed a predetermined action based on the action specified in step S27 (step S28). Specifically, the information processing device 100 determines whether the user U1 has come in front of the product shelf X1. According to the above example, the information processing apparatus 100 determines that the user U1 has come in front of the product shelf X1. The user U1 is in contact with the advertisement content of the company C1 before coming to the product shelf X1 where the products of the company C1 are placed. Therefore, it is highly likely that the user U1 has come to the product shelf X1 where the products of the company C1 are placed due to the contact with the advertising content of the company C1.

  For this reason, the information processing apparatus 100 determines that the advertising effect of the advertising content of the company C1 is “high”, and feeds back the determination result to the company C1.

  Now, the second information processing according to the embodiment has been described. As described with reference to FIG. 2, the information processing apparatus 100 is configured to determine the position of the user based on an external signal from outside the facility, and to determine the position of the user based on a predetermined space characteristic within the facility. Acquire position information indicating the position of the user. Then, the information processing apparatus 100 specifies an action performed by the user in the facility based on the acquired position information. Thereby, the information processing apparatus 100 can specify the action performed by the user in a situation where the position of the user cannot be determined with high accuracy.

  In addition, since the information processing apparatus 100 can determine the advertising effect based on the behavior of the user, the information processing apparatus 100 can provide the advertising effect to the advertiser to help the advertiser in the advertising strategy.

[3. Configuration of information processing device]
Next, the information processing apparatus 100 according to the embodiment will be described with reference to FIG. FIG. 3 is a diagram illustrating a configuration example of the information processing apparatus 100 according to the embodiment. As shown in FIG. 3, the information processing device 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

(About the communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 110 is connected to the network N by wire or wirelessly, and transmits and receives information to and from the terminal device 10, for example.

(About the storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) and a flash memory, or a storage device such as a hard disk and an optical disk. The storage unit 120 includes an action information storage unit 121, a model information storage unit 122, and a magnetic information storage unit 123.

(About the behavior information storage unit 121)
The behavior information storage unit 121 stores behavior information indicating the behavior of the user. For example, the behavior information storage unit 121 stores behavior information detected by a beacon. Here, FIG. 4 illustrates an example of the behavior information storage unit 121 according to the embodiment. In the example of FIG. 4, the behavior information storage unit 121 has items such as “user ID”, “area”, and “activity information”.

  “User ID” indicates identification information for identifying the user or the terminal device 10 of the user. “Area” indicates an area where an object (building part) where a beacon is installed is present. In the example of FIG. 4, a conceptual symbol such as “PDA11” is used as the information indicating the area. However, the area is indicated by an address, for example, longitude and latitude or 〇〇chome to 〇 × chome. “Behavior information” is behavior information detected by a beacon, and indicates behavior information indicating a behavior of a user. In the example of FIG. 4, a conceptual symbol such as “ADA11” is used as the action information, but the action information indicates the time and position, for example, “15:00 on July 21, 2017, Station A”. Indicated by identifiable text.

  That is, in the example of FIG. 4, the user (user U11) identified by the user ID “U11” is performing the action indicated by the action information “ADA11” by the beacon present in the location area indicated by “PDA11”. Indicates that

(About the model information storage unit 122)
The model information storage unit 122 stores the prediction model described in FIG. 1 (the prediction model generated by the information processing device 100). Here, FIG. 5 illustrates an example of the model information storage unit 122 according to the embodiment. In the example of FIG. 5, the model information storage unit 122 has items such as “funnel”, “model ID”, and “model”.

  "Funnel" indicates a gradual action. For example, “Funnel” indicates a step-by-step action from advertisement creative submission to conversion. “Model ID” indicates identification information for identifying a prediction model. “Model” indicates a prediction model generated by the information processing apparatus 100. The “model” indicates a model that receives the position information and the time information and outputs the probability that the user is performing the corresponding “funnel” at the position indicated by the position information. Further, in the example of FIG. 5, a conceptual symbol such as “MDA1” is used as the “model”, but the “model” is actually represented by a mathematical expression.

  That is, in the example of FIG. 5, when the position information indicating the current position of the user and the time information indicating the time at which the user at the current position is present are input, at this time, the user performs an action such as a funnel “Leaving home”. 5 shows an example in which a model M1 that outputs the probability of performing is generated.

(About magnetic information storage unit 123)
The magnetic information storage unit 123 stores a magnetic map generated from the geomagnetism of a predetermined area in the facility. As shown in FIG. 2, in this embodiment, the facility is a predetermined store. Here, FIG. 6 shows an example of the magnetic information storage unit 123 according to the embodiment. In the example of FIG. 6, the magnetic information storage unit 123 has items such as “store ID”, “area”, and “magnetic map data”.

  “Store ID” indicates identification information for identifying a store. “Area” indicates an area in the store identified by the “store ID”. “Magnetic map data” indicates magnetic map data indicating the state (intensity) of the geomagnetism in the corresponding area.

  That is, the example of FIG. 6 illustrates an example in which the magnetic map MA1 is generated based on the geomagnetism in “area AR5” which is the area in the store identified by the store ID “SH1”.

(Other storage units)
Although not shown, the information processing apparatus 100 may further include the following storage unit. For example, the information processing apparatus 100 includes a storage unit that stores advertising content submitted by an advertiser, and a storage unit that stores which manufacturer's product is placed on which product shelf in which area in a store. May be provided.

(About the control unit 130)
Referring back to FIG. 3, the control unit 130 executes various programs stored in a storage device inside the information processing apparatus 100 using a RAM as a work area by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. This is achieved by: The control unit 130 is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  As illustrated in FIG. 3, the control unit 130 includes a model generation unit 131, a first acquisition unit 132, a first identification unit 133, an effect determination unit 134, a second acquisition unit 135, and a second identification unit 136. And an action determining unit 137 and a notifying unit 138, and realize or execute the functions and operations of information processing described below. Note that the internal configuration of the control unit 130 is not limited to the configuration illustrated in FIG. 3, and may be another configuration as long as it performs information processing to be described later. Further, the connection relationship between the processing units included in the control unit 130 is not limited to the connection relationship shown in FIG. 3 and may be another connection relationship.

(About the model generation unit 131)
The model generation unit 131 generates a prediction model. Specifically, the model generation unit 131 receives the position information and the time information of the user as input, and performs a corresponding funnel (stepwise action, action at each step) at the position indicated by the position information. Generate a model that outputs the probabilities of existence. That is, the model generation unit 131 generates a prediction model that predicts which of the stepwise actions to perform. For example, the model generation unit 131 first defines a funnel, and generates, for each of the defined funnels, a prediction model that outputs a probability that a user performs an action indicated by the funnel.

  In the example of FIG. 1, the model generation unit 131 performs machine learning based on the behavior information stored in the behavior information storage unit 121, and uses the behavior tendency obtained by machine learning (for example, deep learning) as one funnel. Define. More specifically, the model generation unit 131 extracts a series of relevant behavior trends from the behavior trends obtained by machine learning, and defines each extracted behavior tendency as one funnel. Further, the model generation unit 131 generates a prediction model for each funnel by machine learning that defines the funnel.

  For example, the model generation unit 131 acquires the behavior tendency by performing machine learning on the behavior information stored in the behavior information storage unit 121. Then, when the position information indicating the current position of the user and the time information indicating the time at which the user at the current position is present are input, the model generation unit 131 “exits home HP1 and heads for station ST1”. A model M1 that outputs a probability that the user is performing an action such as (FIG. 1, funnel F1) is generated.

  Note that, when the position information and the time information are input, the model generation unit 131 outputs a prediction model that outputs what kind of stepwise action and how much probability is performed, that is, the stepwise action and the action of the stepwise action. A prediction model that outputs probabilities may be generated. Further, the model generation unit 131 may generate a prediction model for each user. For example, the model generation unit 131 may generate a prediction model for each user.

(About the first acquisition unit 132)
The first obtaining unit 132 obtains position information indicating the position of the user. For example, the first obtaining unit 132 obtains position information indicating the current position of the user as the position information. Further, the first obtaining unit 132 obtains time information indicating the time at which the user is at the position indicated by the position information. For example, the first obtaining unit 132 obtains position information and time information based on detection information that is information detected by a sensor installed at a predetermined position.

  In the example of FIG. 1, beacons as anchors are installed in various places. Therefore, the first obtaining unit 132 appropriately obtains the behavior information and the time information detected by the beacon from the beacon. Further, the first acquisition unit 132 stores the acquired behavior information and time information in the behavior information storage unit 121.

(About the first specifying unit 133)
The first specifying unit 133 specifies an action to be performed by the user based on the positional information and the time information acquired by the first acquiring unit 132, among the stepwise actions leading to a predetermined action. For example, the first specifying unit 133 includes, as a step-by-step action leading to a predetermined action, of a step-by-step action from when a user contacts a predetermined advertisement content to a conversion related to the advertisement content. , Specify the action to be taken by the user.

  For example, the first specifying unit 133 is a probability that is output by inputting position information and time information to a prediction model generated based on a step-by-step action leading to a predetermined action, Based on the probability of the user performing the stepwise action up to the action, the action performed by the user is specified among the stepwise actions up to the predetermined action. Specifically, the first specifying unit 133 outputs, as a prediction model, a probability output by inputting position information and time information to a model generated for each step-by-step action leading to a predetermined action. Then, based on the probability of the user performing the stepwise action, the action performed by the user is specified among the stepwise actions leading to a predetermined action.

  In the example of FIG. 1, the first specifying unit 133 inputs position information to each of the seven prediction models illustrated in FIG. 1, and the highest probability among the output probabilities is equal to or more than a predetermined probability (for example, 80%). If so, the action of the user U1 is specified based on the funnel corresponding to the prediction model that outputs the highest probability.

  Note that the first specifying unit 133 performs, as a step-by-step action until reaching a predetermined action, from when the user contacts the predetermined advertisement content to when the information related to the advertisement content is transmitted using any means. Of the stepwise actions, the action performed by the user may be specified. The arbitrary means is, for example, SNS (Social Networking Service).

(About the effect determination unit 134)
The effect determining unit 134 determines the advertising effect based on the behavior specified by the first specifying unit 133. For example, the effect determination unit 134 determines, as the advertisement effect, the relationship between the behavior specified by the first specification unit 133 and the advertisement content that the user has contacted. In addition, the effect determination unit 134 determines, as the advertisement effect, the influence of the advertisement content touched by the user on the behavior specified by the first specification unit 133.

  For example, the effect determination unit 134 determines the relationship between the action specified by the first specifying unit 133 and the advertising content contacted by the user, as described in FIG. It determines (specifies) the action performed by the user regardless of the action performed and the contact with the advertisement content.

(About the second acquisition unit 135)
The second acquisition unit 135, based on an extraneous signal from outside the facility, cannot determine the position of the user within the facility, and based on the characteristics of a predetermined space within the facility, Obtain location information indicating the location. Specifically, the second acquisition unit 135 acquires position information based on geomagnetic characteristics distributed in a predetermined space as characteristics of the predetermined space in the facility. For example, the second acquisition unit 135 may determine, based on a change pattern in which geomagnetism distributed in the predetermined space changes in response to the presence of an object in the predetermined space, as characteristics of magnetism distributed in the predetermined space, Get location information.

  In the example of FIG. 2, the second acquisition unit 135 performs the change in which the geomagnetism changes in the area AR5 based on the measurement result data obtained from the terminal device 10, that is, the (magnetism) that changes according to the movement of the user U1. Calculate the pattern. Then, the second obtaining unit 135 obtains position information indicating the current location of the user U1, based on the calculated change pattern. For example, the second acquisition unit 135 specifies a time-series change in geomagnetism by matching the change pattern with the magnetic map MA1. Then, the second obtaining unit 135 obtains (specifies) the position information of the user U1 by estimating the transition route of the user U1 based on the specified time-series change.

(About the second specifying unit 136)
The second specifying unit 136 specifies an action performed by the user in the facility based on the position information acquired by the second acquiring unit 135. In the example of FIG. 2, the second specifying unit 136 specifies an action performed by the user U1 in the area AR5 based on the position information of the user U1 acquired by the second acquiring unit 135.

(About action determination unit 137)
The action determining unit 137 determines whether the user has performed a predetermined action in the facility based on the action specified by the second specifying unit 136. For example, the behavior determining unit 137 determines whether or not the user has visited a region where a transaction target (for example, a product) is provided in a predetermined space as a predetermined behavior. Further, for example, the behavior determining unit 137 determines whether or not the user has visited a display shelf (for example, a product shelf) on which a transaction target is displayed in a predetermined space, as the predetermined behavior.

  In the example of FIG. 2, since the information processing apparatus 100 has received the submission of the advertising content from the company C1, it is determined whether or not the user U1 has come in front of the product shelf X1 on which the products of the company C1 are displayed. I do.

(About the notification unit 138)
The notification unit 138 notifies the advertiser of the advertisement effect determined by the effect determination unit 134 (feeds back). The notification unit 138 notifies the advertiser of the determination result determined by the effect determination unit 134 and the advertising effect based on the determination result (feedback).

[4. Processing procedure (1)]
Hereinafter, the contents of the control processing executed and realized by each processing unit of the information processing apparatus 100 according to the embodiment will be described using the flowchart illustrated in FIG. FIG. 7 is a flowchart illustrating an example of the first information processing according to the embodiment. Since the first information processing has been described with reference to FIG. 1, the example of FIG. 1 will be appropriately used.

  First, the model generator 131 determines whether it is time to generate a prediction model (step S101). For example, the model generation unit 131 determines whether sufficient information is stored in the behavior information storage unit 121, and when the information is stored (Step S101; Yes), it is a timing to generate a prediction model. And a funnel is defined as described in FIG. 1 (step S102). On the other hand, when sufficient information is not accumulated in the behavior information storage unit 121 (Step S101; No), the model generation unit 131 determines that it is not the timing to generate the prediction model, and determines the timing to generate the prediction model. Wait until it becomes. Further, the model generation unit 131 generates a prediction model for each funnel defined in step S102 (step S103).

  Next, the first acquisition unit 132 acquires position information indicating the (current) position of the user and time information indicating the time at the position (step S104). For example, the first obtaining unit 132 obtains position information and time information detected by beacons in various places from the beacons.

  Next, the first specifying unit 133 is a probability output by inputting the position information and the time information with respect to the prediction model generated by the model generation unit 131, and is a probability until the predetermined model is reached. Based on the probability of the user performing the stepwise action, the action performed by the user is specified among the stepwise actions leading to a predetermined action (step S105). Then, the effect determining unit 134 determines the advertising effect based on the behavior specified by the first specifying unit 133 (Step S106). Then, the notification unit 138 notifies the advertiser of the determined advertising effect (Step S107).

  The model generation unit 131 performs reinforcement learning by further applying not only the behavior information stored in the behavior information storage unit 121 but also behavior information indicating the behavior specified by the first specifying unit 133. It can generate funnel definitions and prediction models. Thereby, the model generation unit 131 can generate a more accurate prediction model.

[5. Processing procedure (2)]
Hereinafter, the contents of the control processing executed and realized by each processing unit of the information processing apparatus 100 according to the embodiment will be described using the flowchart illustrated in FIG. FIG. 8 is a flowchart illustrating an example of the second information processing according to the embodiment. Since the second information processing has been described with reference to FIG. 2, the example of FIG. 2 will be appropriately used. In the example of FIG. 8, it is assumed that the information processing apparatus 100 already has magnetic map data in the magnetic information storage unit 123.

  First, the second acquisition unit 135 determines whether or not measurement result data (magnetic data) indicating the intensity of geomagnetism measured by the terminal device 10 of the user U1 has been acquired from the terminal device 10 in the area AR5 (Step S10). S201). Next, the second acquisition unit 135 calculates a change pattern in which the geomagnetism changes in the area AR5 based on the measurement result data (Step S202). Next, the second acquisition unit 135 acquires the position information of the user U1 by matching the change pattern with the magnetic map (Step S203). For example, the second obtaining unit 135 obtains the position information of the user U1 by specifying a time-series change of geomagnetism by matching and estimating a transition route of the user U1 based on the specified time-series change.

  Next, the second specifying unit 136 specifies an action performed by the user in the area AR5 based on the position information acquired by the second acquiring unit 135 (Step S204). Then, the action determining unit 137 determines whether the user has performed a predetermined action in the area AR5 based on the action specified by the second specifying unit 136 (Step S205). Then, the notification unit 138 notifies the behavior determined by the behavior determination unit 137 to the advertiser (Step S206).

[6. Modification)
The information processing apparatus 100 according to the above embodiment may be embodied in various different forms other than the above embodiment. Therefore, another embodiment of the information processing apparatus 100 will be described below.

[6-1. Attribute information〕
In the above embodiment, the first specifying unit 133 specifies the action performed by the user among the step-by-step actions leading to the predetermined action based on the position information and the time information acquired by the first acquiring unit 132. An example is shown. However, the first specifying unit 133 may specify an action according to the predetermined attribute information as an action performed by the user among the stepwise actions leading to the predetermined action. Such predetermined attribute information includes, for example, attribute information of the user itself (for example, age, gender, etc.), attribute information of the advertising content contacted by the user, and a transaction target (for example, a product or service, etc.) indicated by the advertising content contacted by the user. ) Is attribute information. Of course, the predetermined attribute information is not limited to these.

  In such a case, when not only the position information and the time information but also the attribute information as described above is input, the model generation unit 131 performs a step-by-step action leading to a predetermined action, and A prediction model that outputs the probability that the user performs a stepwise action according to the information, time information, and attribute information is generated.

  Thereby, the information processing apparatus 100 according to the embodiment can determine with higher accuracy how much the advertising content has affected the user. In addition, the information processing apparatus 100 can specify a tendency according to an attribute such that, for example, when a user of the attribute information “male” comes into contact with advertising content of an attribute, the user stops at a certain facility and then goes to the shop SH1. Therefore, the advertiser can perform a more advanced advertising strategy.

[6-2. Advertising contact)
In addition, the first specifying unit 133 determines, as the action performed by the user among the step-by-step actions leading to the predetermined action, the advertisement content contacted by the user in the step-by-step action until the predetermined action. Identify the corresponding action.

  In the example of FIG. 1, the user U1 first contacts the advertisement content AD1 with the terminal device 10, but, for example, corresponds to the advertisement content AD1 on a route until reaching the shop SH1 or in a train ( (Related) physical advertisements (eg, signboards, etc.) may also be contacted. Whether or not the user has contacted such a physical advertisement can be acquired by, for example, a beacon. Then, because the user first contacts the advertisement content AD1 and, on the way, further contacts the advertisement content related to the advertisement content AD1, the user goes to the target shop and reaches a conversion, or the user has reached a specific facility by then. There may be a tendency to drop in. The first specifying unit 133 specifies an action corresponding to the contact with the advertising content in such a plurality of stages. In such a case, the model generation unit 131 generates a prediction model corresponding to the physical advertisement.

  Thereby, the information processing apparatus 100 according to the embodiment can provide the advertiser with information for determining, for example, what kind of place in the city should place a billboard advertisement or the like.

[6-3. Acquisition of position by sound wave (1)]
In the above embodiment, the second acquisition unit 135 determines, based on a change pattern in which the geomagnetism distributed in the predetermined space changes in accordance with the presence of the object in the predetermined space, as the characteristic of the magnetism distributed in the predetermined space. Thus, an example of acquiring the position information has been described. However, the second acquisition unit 135 may acquire the position information based on a non-audible sound distributed in the predetermined space as a feature of the predetermined space in the facility. Specifically, the second acquisition unit 135 determines the position based on the grid corresponding to the frequency detected by the user terminal device 10 among the grids generated by the inaudible sounds of different frequencies in the predetermined space. Get information. This will be described with reference to the example of FIG.

  For example, in the area AR5, a plurality of speakers (for example, directional speakers) that output non-audible sounds (for example, a 20 kHz band) are provided. These speakers output non-audible sounds of different wavelengths (frequency), and are installed along the walls of the area AR5, for example, so as to make one round of the area AR5. When each speaker outputs a non-audible sound in such a state, a grid of different non-audible sounds is generated in the area AR5. Therefore, a plurality of points where non-audible sounds of different wavelengths intersect occur in the area AR5. At this point, interference of sound waves occurs, which results in the generation of a unique non-audible sound. Then, it is assumed that the information processing apparatus 100 previously has information indicating at which position in the area AR5 the unique inaudible sound is generated.

  Since the microphone incorporated in the terminal device 10 of the user U1 can collect the non-audible sound, the microphone transmits the voice data indicating the collected non-audible sound to the information processing device 100. Here, the second acquisition unit 135 analyzes the audio data received from the terminal device 10 and, for example, when the audio data indicates a unique non-audible sound, determines a position where the unique non-audible sound is generated. It is acquired as the position of the user U1.

  Thereby, the information processing apparatus 100 according to the embodiment can specify, for example, an action performed by a user in the facility with high accuracy even in a situation where geomagnetic positioning cannot be performed in the facility.

[6-4. Position acquisition by sound wave (2)]
In addition, the second acquisition unit 135 acquires the position information based on the timing at which the terminal device of the user detects the inaudible sound output while the output device installed in the predetermined space operates periodically. This will be described with reference to the example of FIG.

  For example, at both ends (both corners) of the area AR5, one speaker (for example, a directional speaker) that outputs a non-audible sound (for example, a 20 kHz band) is installed. These speakers are set to perform periodic actions automatically. For example, the speaker portion is set so as to perform a swing motion at a constant speed. As an example, one speaker faces east at "14:00:00", swings counterclockwise as time passes, and faces north at "14:00:02". And so on. Also, the other speaker faces north at "14:00:00", swings counterclockwise as time passes, and faces west at "14:00:02". Things.

  Then, the microphone of the terminal device 10 of the user U1 collects the non-audible sounds output from the two speakers that make a fixed movement as described above, and collects the non-audible sounds and the collected non-audible sounds. The audio data indicating the time information is transmitted to the information processing device 100. Assuming that the information processing apparatus 100 can know when and in which direction the two speakers are facing, the second acquisition unit 135 outputs the time information based on the time information received from the terminal apparatus 10. It is possible to specify in which direction each speaker is outputting an inaudible sound at the indicated time. Therefore, the second obtaining unit 135 can obtain the position of the intersection formed in the area AR5 as the position of the user U1, which is the intersection of the directions corresponding to the respective speakers.

  Further, for example, when there is one speaker, the second acquisition unit 135 cannot specify the intersection, but estimates that the user U1 is on an extension of the direction corresponding to the one speaker. be able to. Then, based on the volume indicated by the audio data, the second acquisition unit 135 can estimate where on the extension the non-audible sound has been collected, and thus obtains the estimated position as the position of the user U1. can do.

  Thereby, the information processing apparatus 100 according to the embodiment can specify, for example, an action performed by a user in the facility with high accuracy even in a situation where geomagnetic positioning cannot be performed in the facility.

[6-5. Position acquisition with light (1)]
In addition, the second acquisition unit 135 acquires the position information based on invisible light distributed in the predetermined space as a feature of the predetermined space in the facility. Specifically, the second acquisition unit 135 determines the position information based on the grid corresponding to the wavelength detected by the terminal device 10 of the user among the grids generated by invisible light of different wavelengths in a predetermined space. To get. This is an invisible light version of the example described in “Modification 6-3” above.

  For example, in the area AR5, a plurality of output devices (light sources) that output invisible light (for example, infrared light or ultraviolet light) are provided. Such an output device outputs invisible light of different wavelengths, and is installed along a wall or the like of the area AR5, for example, so as to make one round of the area AR5. When each output device outputs invisible light in such a state, grids of invisible light of different wavelengths are generated in the area AR5. For this reason, in the area AR5, a plurality of intersections at which invisible light of different wavelengths intersect occurs. At this intersection, light interference occurs, so that invisible light having a unique wavelength is generated. Then, it is assumed that the information processing apparatus 100 has in advance information indicating at which position in the area AR5 the unique invisible light is generated.

  Since the sensor built in the terminal device 10 of the user U1 can detect invisible light, the sensor transmits optical data indicating the detected invisible light to the information processing device 100. Here, the second acquisition unit 135 analyzes the optical data received from the terminal device 10 and, for example, when the optical data indicates invisible light of a specific wavelength, invisible light of the specific wavelength is generated. The position is acquired as the position of the user U1.

  Thereby, the information processing apparatus 100 according to the embodiment can specify, for example, an action performed by a user in the facility with high accuracy even in a situation where geomagnetic positioning cannot be performed in the facility.

[6-6. Position acquisition with light (2)]
In addition, the second acquisition unit 135 acquires the position information based on the timing at which the terminal device 10 of the user detects the invisible light output while the output device installed in the predetermined space periodically operates. This is an invisible light version of the example described in “Modification 6-4” above.

  For example, at each end (both corners) of the area AR5, one output device that outputs invisible light (for example, infrared light or ultraviolet light) is installed. These output devices are set to automatically and periodically act. For example, the output portion is set so as to perform a swing action at a constant speed. As an example, one of the output devices turns east at "14:00:00" and swings counterclockwise as time passes, and "14:00:02" turns north. It is like that. Also, the other output device turns north at "14:00:00", swings counterclockwise as time passes, and turns west at "14:00:02". And so on.

  Then, the sensor of the terminal device 10 of the user U1 detects the invisible light output from the two output devices performing the predetermined movement as described above, and detects the detected invisible light and the time information at the time of detection. Is transmitted to the information processing apparatus 100. If it is assumed that the information processing apparatus 100 can know when and in which direction the two output devices are facing, the second acquisition unit 135 generates the time information based on the time information received from the terminal device 10. At which time each output device is outputting invisible light. For this reason, the second acquisition unit 135 can acquire the position of the intersection formed in the area AR5 as the position of the user U1, which is the intersection of the directions corresponding to the respective output devices.

  Further, for example, when there is one output device, the second acquisition unit 135 cannot specify the intersection, but when the user U1 is on an extension line in the direction corresponding to the one output device. Can be guessed. Then, based on the intensity indicated by the light data, the second obtaining unit 135 can estimate where the invisible light is detected on the extension line, and thus obtains the estimated position as the position of the user U1. Can be.

  Thereby, the information processing apparatus 100 according to the embodiment can specify, for example, an action performed by a user in the facility with high accuracy even in a situation where geomagnetic positioning cannot be performed in the facility.

[7. Hardware configuration)
Further, the information processing apparatus 100 according to each embodiment described above is realized by, for example, a computer 1000 having a configuration as shown in FIG. Hereinafter, the information processing apparatus 100 will be described as an example. FIG. 9 is a hardware configuration diagram illustrating an example of a computer 1000 that implements the functions of the information processing device 100. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

  The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, a program that depends on hardware of the computer 1000, and the like.

  The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. The communication interface 1500 receives data from another device via the communication network 50, sends the data to the CPU 1100, and transmits the data generated by the CPU 1100 to another device via the communication network 50.

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

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

  For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 implements the function of the control unit 130 by executing a program loaded on the RAM 1200. The HDD 1400 stores data in the storage unit 120. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800. However, as another example, these programs may be obtained from another device via the communication network 50.

[8. Others)
Of the processes described in the above embodiments, all or some of the processes described as being performed automatically may be manually performed, or all of the processes described as being performed manually may be performed. Alternatively, a part thereof can be automatically performed by a known method. In addition, the processing procedures, specific names, and information including various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified.

  Each component of each device illustrated is a functional concept, and does not necessarily need to be physically configured as illustrated. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or a part thereof may be functionally or physically distributed / arranged in arbitrary units according to various loads and usage conditions. Can be integrated and configured.

  Further, the embodiments described above can be appropriately combined within a range that does not contradict processing contents.

  As described above, the embodiments of the present application have been described in detail with reference to some drawings. However, these are exemplifications and various modifications based on the knowledge of those skilled in the art, including the aspects described in the section of the disclosure of the invention. It is possible to implement the invention in other forms with improvements.

  Further, the “section (section, module, unit)” described above can be read as “means”, “circuit”, or the like. For example, the acquiring unit can be replaced with an acquiring unit or an acquiring circuit.

Reference Signs List 10 terminal device 100 information processing device 121 action information storage unit 122 model information storage unit 123 magnetic information storage unit 131 model generation unit 132 first acquisition unit 133 first identification unit 134 effect determination unit 135 second acquisition unit 136 second identification unit 137 Action determination unit 138 Notification unit

Claims (15)

An acquisition unit that acquires position information indicating the position of the user in the facility, based on characteristics of a predetermined space in the facility, in a state where the position of the user cannot be determined based on an external signal from outside the facility; ,
An identification unit configured to identify an action performed by the user in the facility based on the position information acquired by the acquisition unit. The information processing according to claim 1, wherein the acquisition unit acquires the position information based on a feature of geomagnetism distributed in the predetermined space as a feature of the predetermined space in the facility. apparatus. The acquisition unit is configured to determine the position based on a change pattern in which geomagnetism distributed in the predetermined space changes in accordance with the presence of an object in the predetermined space as a feature of magnetism distributed in the predetermined space. The information processing apparatus according to claim 1, wherein the information is acquired. The said acquisition part acquires the said positional information based on the non-audible sound distributed in the said predetermined space as the characteristic of the predetermined space in the said facility. The information processing device according to one of the above. The acquisition unit, in a predetermined space, among the grids generated by the non-audible sound of the non-audible sound and a different frequency, based on a grid corresponding to a frequency detected by the terminal device of the user, The information processing apparatus according to claim 4, wherein the information processing apparatus acquires position information. The acquisition unit acquires the position information based on a timing at which the terminal device of the user detects the inaudible sound output while the output device installed in the predetermined space periodically operates. The information processing apparatus according to claim 4 or 5, wherein The said acquisition part acquires the said positional information based on the invisible light distributed in the said predetermined space as the characteristic of the predetermined space in the said facility. The any one of Claims 1-6 characterized by the above-mentioned. An information processing apparatus according to any one of the above. The acquisition unit, in a predetermined space, among the grids generated by the invisible light of invisible light of a different wavelength, based on a grid corresponding to a wavelength detected by the user terminal device, the position information, The information processing apparatus according to claim 7, wherein: The acquisition unit acquires the position information based on a timing at which the terminal device of the user detects the invisible light output while the output device installed in the predetermined space periodically operates and outputs. The information processing apparatus according to claim 7 or 8, wherein The apparatus according to claim 1, further comprising: a determination unit configured to determine whether the user has performed a predetermined action in the facility based on the action specified by the specifying unit. An information processing apparatus according to claim 1. The information according to claim 10, wherein the determination unit determines whether or not the user has visited an area where a transaction target is provided in the predetermined space, as the predetermined action. Processing equipment. The said determination part determines whether the said user visited the display shelf where the transaction object is displayed in the said predetermined space as the said predetermined action. The said 10 or 11 characterized by the above-mentioned. An information processing apparatus according to claim 1. The information processing apparatus according to claim 11, further comprising: a notification unit configured to notify a seller of the transaction target of information based on a result of the determination by the determination unit. An information processing method executed by an information processing apparatus,
An acquisition step of acquiring position information indicating the position of the user in the facility based on a feature of a predetermined space in the facility in a state where the position of the user cannot be determined based on an external signal from outside the facility; ,
An identification step of identifying an action performed by the user in the facility based on the position information acquired in the acquisition step. An acquisition unit that acquires position information indicating the position of the user in the facility, based on characteristics of a predetermined space in the facility, in a state where the position of the user cannot be determined based on an external signal from outside the facility; ,
An information processing program, which causes a computer to execute, based on the position information acquired by the acquisition unit, an identification unit that identifies an action performed by the user in the facility.