JP2019197430A - Information processing device, information processing method, program and information processing system - Google Patents

Abstract

To provide an information processing device or the like capable of appropriately selecting the content.SOLUTION: An information processing device 1 includes: a storage part for storing the content corresponding to each of a plurality of articles; an acquisition part for acquiring the property information indicating the product owned by a person and the attribute information indicating the attribute of the person; a classification part for classifying the article purchase tendency for each attribute based on the article corresponding to the product and the attribute information; and a selection part for selecting the content according to the attribute information by referring to the classification result.SELECTED DRAWING: Figure 1

Description

  The present invention relates to an information processing apparatus, an information processing method, a program, and an information processing system.

  In recent years, with the widespread use of display devices called digital signage, various content display methods using digital signage have been proposed. For example, there is a technique in which a person browsing digital signage is imaged, attributes of the person are extracted from the captured image, and contents corresponding to the attributes are displayed on the digital signage (see Patent Documents 1 and 2).

JP 2013-205430 A Japanese Unexamined Patent Publication No. 2006-61955

  However, in the inventions according to Patent Documents 1 and 2, a rule that defines the content to be displayed according to the attribute is prepared manually, and the content to be displayed is automatically selected only by selecting the content according to the rule. It has not yet been decided.

  An object of one aspect is to provide an information processing apparatus and the like that can appropriately select content.

  In one aspect, the information processing apparatus acquires a storage unit that stores content corresponding to each of a plurality of products, property information indicating an article owned by the person, and attribute information indicating the attribute of the person A classification unit that classifies a product purchase tendency for each attribute based on the product, the product corresponding to the product, and the attribute information, and selects the content according to the attribute information with reference to a classification result And a selection unit to perform.

  In one aspect, content can be selected appropriately.

It is a schematic diagram which shows the structural example of a content delivery system. It is a block diagram which shows the structural example of a server. It is explanatory drawing which shows an example of the record layout of content DB and passerby DB. It is explanatory drawing regarding a clustering process. It is explanatory drawing regarding a content delivery process. It is a flowchart which shows an example of the process sequence of a content delivery process. It is a flowchart which shows an example of the process sequence of a clustering process. FIG. 6 is an explanatory diagram showing an outline of a second embodiment. 10 is a flowchart illustrating an example of a processing procedure of content distribution processing according to the second embodiment. 10 is a schematic diagram illustrating a configuration example of a content distribution system according to Embodiment 3. FIG. 10 is a block diagram illustrating a configuration example of a server according to Embodiment 3. FIG. It is explanatory drawing which shows an example of the record layout of member DB. 12 is a flowchart illustrating an example of a processing procedure executed by a server according to the third embodiment. It is a functional block diagram which shows operation | movement of the server of the form mentioned above.

Hereinafter, the present invention will be described in detail with reference to the drawings illustrating embodiments thereof.
(Embodiment 1)
FIG. 1 is a schematic diagram illustrating a configuration example of a content distribution system (information processing system). In this embodiment, a content distribution system that distributes content such as product advertisements to digital signage according to the attributes of passers-by who pass before digital signage will be described. The content distribution system includes an information processing device 1, a signage (display device) 2, and a camera (device) 3. Each device is connected for communication via a network N such as the Internet.

  The information processing apparatus 1 is an information processing apparatus capable of various information processing and information transmission / reception, and is, for example, a server apparatus or a personal computer. In the present embodiment, it is assumed that the information processing apparatus 1 is a server apparatus, and in the following description, the information processing apparatus 1 is read as the server 1 for the sake of brevity. The server 1 includes a database that stores content to be displayed by the signage 2, and distributes and displays the content on the signage 2. In the present embodiment, a system is assumed in which content is distributed to signage 2 installed in a large-scale commercial facility such as a department store, and server 1 distributes a product advertisement of each store in the commercial facility to signage 2 as content. As will be described later, the server 1 estimates a plurality of attributes such as the sex, age, and body shape of the passer-by from the image captured by the camera 3, and specifies a product estimated to be purchased by the passer-by. Then, the server 1 performs clustering that classifies the purchase tendency of products based on the attributes of passers-by. When the server 1 newly recognizes a passerby from an image captured by the camera 3, the server 1 selects a product to be advertised with reference to the clustering result according to the attribute of the passerby, and corresponds to the advertisement of the product. Distribute content to signage 2 and display it.

  The signage 2 is a display device that can communicate with the outside, and is a so-called digital signage. As described above, the signage 2 is installed in a commercial facility such as a department store, and displays content by receiving distribution from the server 1.

The camera 3 is an imaging device that images a passerby who passes in front of the signage 2, and is installed on the top of the signage 2, for example, as shown in FIG. 1. In addition, the camera 3 should just be installed in the position which can image a passerby, for example, may be installed in the place away from the signage 2. For example, the camera 3 may be provided inside the signage 2. The camera 3 transmits an image obtained by capturing a passerby to the server 1. The server 1 estimates the passerby's age, sex, and other attributes based on the image acquired from the camera 3, selects content according to the passer's attribute, and distributes it to the signage 2.
In FIG. 1, only one signage 2 and camera 3 are shown for convenience, but it is needless to say that a plurality of signage 2 and camera 3 may be provided.

FIG. 2 is a block diagram illustrating a configuration example of the server 1. The server 1 includes a control unit 11, a main storage unit 12, a communication unit 13, and an auxiliary storage unit 14.
The control unit 11 includes an arithmetic processing unit such as one or a plurality of CPUs (Central Processing Units), MPUs (Micro-Processing Units), and GPUs (Graphics Processing Units), and stores the program P stored in the auxiliary storage unit 14. Various information processing, control processing, and the like related to the server 1 are performed by reading and executing. The main storage unit 12 is a temporary storage area such as a static random access memory (SRAM), a dynamic random access memory (DRAM), or a flash memory, and temporarily stores data necessary for the control unit 11 to execute arithmetic processing. Remember. The communication unit 13 includes a processing circuit for performing processing related to communication, and transmits and receives information to and from the signage 2 and the like.

  The auxiliary storage unit 14 is a large-capacity memory, a hard disk, or the like, and stores a program P and other data necessary for the control unit 11 to execute processing. The auxiliary storage unit 14 stores a content DB 141 and a passer-by DB 142. The content DB 141 is a database that stores content to be distributed to the signage 2. The passer-by DB 142 is a database that stores information on passers-by who have passed in front of the signage 2.

  The auxiliary storage unit 14 may be an external storage device connected to the server 1. Further, the server 1 may be a multi-computer composed of a plurality of computers, or may be a virtual machine constructed virtually by software.

  Further, in the present embodiment, the server 1 is not limited to the above configuration, and may include, for example, a reading unit that reads information stored in a portable storage medium.

  FIG. 3 is an explanatory diagram showing an example of the record layout of the content DB 141 and the passer-by DB 142. The content DB 141 includes a product ID column, a related image column, and a content column. The product ID column is a product related to an advertisement (content) displayed on the signage 2 and stores identification information for identifying a product purchased by a passerby. The related image sequence stores image data of a specific article corresponding to the product (referred to as “specific product” for convenience in the following description) in association with the product ID. The specific item is, for example, a shopping bag of each store that provides products in a commercial facility. As will be described later, the server 1 specifies whether or not a passerby possesses (owns) a shopping bag given at the time of providing a product at each store, thereby determining a product (store) purchased by the passerby. Identify. The content column stores the content corresponding to the product advertisement in association with the product ID.

  The passer-by DB 142 includes a product ID column and an attribute column. The product ID column stores a product ID related to a product estimated to be purchased by a passerby. The attribute column stores attribute information of a passerby who purchased the product indicated by the product ID in association with the product ID. As shown in FIG. 3, the attribute column stores a plurality of attributes of passersby such as sex, age, and body type.

FIG. 4 is an explanatory diagram regarding clustering processing. FIG. 4 illustrates a state in which attributes of passers-by are estimated from an image captured by the camera 3 and product clustering is performed from the estimated attributes. A clustering process executed by the server 1 will be described with reference to FIG.
The server 1 acquires an image of passersby from the camera 3 installed in the signage 2. An example of the captured image is shown in the upper right of FIG. For example, the camera 3 captures a passerby passing in front of the signage 2 in the imaging range in front of the signage 2 and transfers the captured image to the server 1.

  The server 1 performs image recognition on the image, and determines whether or not a passerby possesses (owns) a specific object given by purchasing a product at each store in the commercial facility. This specific item is a property that can specify a product presumed to have been purchased by a passerby, such as a shopping bag that is provided when a product is provided. For example, the server 1 stores image data of shopping bags used in providing products at each store in the content DB 141 in advance. The server 1 recognizes an image area of an article possessed by a passer-by in a captured image, as indicated by a dotted rectangular frame in FIG. Then, the server 1 determines whether or not the article included in the image area matches the image data of the specific object stored in the content DB 141. More specifically, for example, the server 1 determines whether it is a specific object by recognizing the shape of an article (shopping bag) or a mark (not shown) attached to the article. Note that the server 1 may add not only the shape or mark of the article but also the color of the article, for example, to the determination criterion. As described above, the server 1 acquires property information indicating an article possessed (owned) by the passer-by from an image obtained by imaging the passer-by, and specifies a purchased product based on this information.

  The server 1 only needs to be able to determine whether or not a passerby has a specific object corresponding to the product. For example, when the product is a bag, the server 1 may recognize the bag itself. That is, the server 1 may specify the product itself from the captured image.

  Similarly, the server 1 performs image recognition on the captured image and estimates a plurality of attributes of passers-by. The attributes estimated by the server 1 are information such as passersby's gender, age, body type, and clothes, but the contents are not particularly limited. The server 1 estimates the various attributes described above from an image area other than the specific image area indicated by the dotted rectangular frame in FIG. The server 1 stores, in the auxiliary storage unit 14, information that associates attribute information for each feature amount extracted from the image with respect to various attributes, and refers to the auxiliary storage unit 14 from the feature amount extracted from the captured image. To recognize (acquire) attribute information. For example, in the case of gender, the server 1 stores gender distinction in association with the feature quantity of the face image, and recognizes gender distinction from the feature quantity of the face image extracted from the captured image. The same applies to other attributes such as age and body type. Thereby, the server 1 acquires attribute information indicating a plurality of attributes of passers-by from the captured image.

  Based on the property information and attribute information acquired from the captured image, the server 1 associates the purchased product specified from the specific item possessed by the passer-by with the various attributes of the passer-by in the passer-by DB 142. Remember. The server 1 repeats the above-described processing, acquires the information on purchased products and attributes in the same manner from an image obtained by imaging each passerby, and stores it in the passerby DB 142.

  Based on the data stored in the passer-by DB 142, the server 1 clusters the purchase tendency of products by each passer according to the passer-by attributes. As described above, the passer-by DB 142 stores purchased products and attributes in association with each other. That is, in the passerby DB 142, the purchased product is labeled with respect to the attribute information. The server 1 treats this attribute information as one labeled multi-dimensional feature value, and classifies (clusters) the purchase tendency of products according to a plurality of attributes (feature values) of passers-by.

  For example, the server 1 classifies the feature vector using each attribute of the passerby extracted from the captured image as a variable into a plurality of clusters using a SOM (Self-Organizing Maps) technique. SOM is a kind of neural network and is a technique for mapping input data to an arbitrary dimension by unsupervised learning.

  The lower side of FIG. 4 conceptually shows how feature vectors in the feature amount space (shown by hatched circles) are mapped to each unit (shown by hexagons) on the self-organizing map. In the lower left of FIG. 4, a feature amount space representing feature vectors related to the attribute information of each passerby is illustrated. In the lower right of FIG. 4, a two-dimensional self-organizing map in which feature vectors are mapped is illustrated. In the lower left of FIG. 4, the passer-by attributes are represented in three dimensions for the sake of convenience, but are actually represented in more dimensions. In the present embodiment, the self-organizing map is described as being a two-dimensional plane, but the self-organizing map may be expressed in one or three dimensions.

  The server 1 maps a feature vector represented by each attribute such as the passerby's sex, age, and body shape as an input vector to any unit in the self-organizing map shown in the lower right of FIG. Although detailed illustration and description of the configuration of the neural network are omitted, the server 1 is a neural network composed of two layers: an input layer for inputting feature vectors and a competitive layer (output layer) for outputting to which unit it belongs. Build a network. The input layer has, for example, as many neurons for input as the number of variables related to the feature vector. The competitive layer has as many neurons for output as the number of units in the self-organizing map.

  In order to map the feature vector to the self-organizing map, each unit of the self-organizing map is assigned a reference vector (shown by a cross) having the same dimension as the feature amount space. The server 1 compares the feature vector with the reference vector, and converts (maps) the feature vector to a reference vector unit having the closest coordinate in the feature amount space. As a result, a unit of the self-organizing map to be a so-called “winner” is determined. In this case, the server 1 weights the unit (competitive layer neuron) that has become the winner and the units located around the winner unit in the self-organizing map.

  The server 1 maps the above feature vectors for the attribute information of each passerby, and builds a neural network by repeating the update of the self-organizing map. As a result, as represented by the type of hatching in FIG. 4, the feature vectors of passersby whose attribute information is similar to each other are mapped to unit groups at close positions in the self-organizing map. In this way, the server 1 unsupervised learning a plurality of clusters (sets) on the self-organizing map representing merchandise purchase tendency for each attribute based on mutual similarity of passersby (persons) using attribute information. Generate with

  As described above, the server 1 generates a plurality of clusters representing purchase trends of products for each attribute. The server 1 refers to the information (product ID) of the purchased product associated with the attribute information of each passer in the passer-by DB 142, and indicates which passer's attribute each store has purchased the product of. , Label. For example, as shown in FIG. 4, the cluster indicated by hatching on the left diagonal line is a cluster in which the attributes of passers-by who have the shopping bag of the store A are classified. Label store A. Similarly, since the cluster indicated by hatching with dots is a cluster in which passers-by who had the shopping bag of the store B are classified, the server 1 labels the cluster as “store B”. . In this way, the server 1 uses a neural network generated by unsupervised learning, and generates a classification model that classifies the purchase tendency of the product, which store the passerby having each attribute can easily purchase.

  In the above description, the SOM has been described as an example. However, the present embodiment is not limited to this. For example, the server 1 may be a deep learning, an SVM (Support Vector Machine), a Bayesian network, or the like. Classification of merchandise purchase tendency may be learned using other algorithms.

FIG. 5 is an explanatory diagram regarding content distribution processing. On the upper side of FIG. 5, the signage 2 displays content for passers-by. The lower side of FIG. 5 illustrates a conceptual diagram of clustering for selecting display content. Based on FIG. 5, a process of displaying content according to passerby attribute information using the learning result described above will be described.
The server 1 acquires a captured image from the camera 3 and performs image recognition as in the above learning. In this case, for example, when the server 1 recognizes from the captured image that the passerby does not possess the specific item, that is, when the passerby has not finished shopping at the store, the passerby is set as a content output target person. The content corresponding to the product advertisement is presented to the passerby.

  The server 1 estimates a plurality of attributes of passers-by from the captured image. Then, the server 1 refers to the classification model (classification result) generated above and determines to which of the clusters corresponding to each product the attribute information of the passerby belongs.

  Specifically, the server 1 maps the passer-by attribute information to the self-organizing map using the generated neural network. This is conceptually illustrated at the bottom of FIG. In FIG. 5, for convenience of illustration, unlike FIG. 4, each cluster (set) on the self-organization map is illustrated by a thick line frame instead of hatching.

  The server 1 selects content to be distributed to the signage 2 according to the mapping position where the attribute of the passerby is mapped on the map. For example, it is assumed that the image is mapped to the position indicated by the cross in FIG. In this case, for example, the server 1 selects the product advertisement of the store B as the content because the mapping position belongs to the cluster of the store B.

  Further, the server 1 not only selects the content corresponding to the cluster (store) to which the mapping position belongs as described above, but also selects the content corresponding to another cluster (store) whose mapping position is close on the map. May be. For example, in FIG. 5, the position where the attribute of the passerby is mapped is adjacent to the clusters of stores A, C, and D. The server 1 may select not only the store B but also the product advertisements of the stores A, C, and D as contents.

  For example, the server 1 uses the distance on the self-organizing map as an evaluation value indicating the degree of similarity (similarity relationship) for each cluster, and uses the distance between each cluster and the mapping position where the attribute of the passer-by is mapped. select. For example, the server 1 calculates the similarity (distance) between the mapping position of the attribute of the passer-by and each cluster, and determines that the cluster whose similarity is equal to or greater than the threshold is similar to the passer-by's product purchase tendency. The server 1 selects a product advertisement of a cluster determined to be similar as content.

  The server 1 reads content corresponding to the cluster selected as described above from the content DB 141 and distributes (outputs) it to the signage 2. The signage 2 displays the content distributed from the server 1. Thereby, the signage 2 can present the product advertisement of the store where the person whose attribute is similar to the passerby shopped, and can perform effective sales promotion. Further, the server 1 has a similar purchase tendency not only by advertisements of stores where other passersby (persons) whose attributes are similar to those of passersby (content output target persons) but also by self-organizing maps. It is also possible to present advertisements of other stores that are expected to be, and to promote sales more effectively.

  In the above description, the content is displayed to a passerby who does not have a specific item (such as a shopping bag). However, a passerby who owns the specific item as in the third embodiment to be described later. Of course, content may also be displayed.

FIG. 6 is a flowchart illustrating an example of a processing procedure of content distribution processing. Based on FIG. 6, the processing content of the content distribution processing which the server 1 performs is demonstrated.
The control part 11 of the server 1 acquires the captured image which imaged the passerby from the camera 3 (step S11). The control unit 11 performs image recognition on the captured image (step S12).

  As a result of the image recognition, the control unit 11 determines whether or not a passerby possesses (owns) a specific object corresponding to the product (step S13). For example, as described above, the control unit 11 specifies, from the captured image, a shopping bag to be given to a passerby (person) when the product is provided, or the product itself. For example, the control unit 11 recognizes the passerby's possession from a part of the image area of the captured image, and specifies the shape of the possession, the mark attached to the possession, etc. It is determined whether or not it is possessed.

  When it is determined that the specific object is not possessed (S13: NO), the control unit 11 estimates a plurality of attributes such as the sex, age, and body shape of the passerby (content output target person) from the captured image (step) S14). The control part 11 selects the content shown to a passer-by based on several estimated attributes (step S15). Specifically, as described above, the control unit 11 maps the attributes of passers-by who possessed a specific object to the self-organizing map, thereby classifying the purchase tendency of products for each attribute of the passers-by. (Neural network) is generated. The control unit 11 refers to the classification model and maps the attribute of the passerby who does not possess the specific object (content output target person) to the self-organizing map, thereby allowing the passerby to purchase a plurality of merchandise purchase tendencies. Into one of the clusters (sets). The control unit 11 calculates the degree of similarity (similarity relationship) for each cluster by calculating the mapping position on the map where the attribute of the passerby is mapped and the distance between each cluster on the map. The control unit 11 selects content based on the similarity relationship, for example, by selecting a cluster having a similarity greater than or equal to a threshold (distance is less than or equal to a threshold). The control unit 11 reads the selected content from the content DB 141, outputs (distributes) it to the signage 2, and displays it (step S16). The control unit 11 ends the series of processes.

  When it determines with having a specific thing (S13: YES), the control part 11 estimates several attributes of a passerby from image areas other than the image area which specified the specific thing in step S13 in a captured image. (Step S17). The control unit 11 stores information (for example, a product ID) indicating a product presumed to be purchased by a passerby by a specific item and attribute information indicating a plurality of passerby attributes in the passer-by DB 142 ( Step S18). The control unit 11 ends the series of processes.

FIG. 7 is a flowchart illustrating an example of a processing procedure of the clustering process. Based on FIG. 7, the processing content of the clustering process which the server 1 performs is demonstrated.
The control unit 11 of the server 1 reads, from the passer-by DB 142, information on a product estimated to be purchased by the passer-by and attribute information indicating a plurality of attributes of the passer-by (step S31). For example, as described above, the control unit 11 includes a product ID of a product specified from a specific item possessed by a passer-by and attributes such as a passer-by's gender, age, and body shape stored in association with the ID. Read information.

  The control unit 11 performs clustering for classifying the product purchase tendency for each attribute based on the information related to the product and the attribute acquired in step S31 (step S32). For example, the control unit 11 performs clustering using SOM as described above. The control unit 11 maps a feature vector represented by a plurality of attributes of each passer-by to the self-organizing map, thereby generating a plurality of clusters (sets) based on the mutual similarity of each passer-by. And the control part 11 classifies the purchase tendency of the goods by a passerby for every attribute by labeling the purchase goods specified from the specific thing which each passerby possessed as an output value showing each cluster. Generate a model. The control unit 11 ends the series of processes.

  In the above description, the system in which the server 1 distributes content to the signage 2 via the network N has been described. However, the local device (for example, a personal computer) stores the content related to the products of each store described above, and the signage 2 You may make it output a content.

  Moreover, although the form which displays a content in digital signage was described above, this Embodiment is not limited to this, The terminal apparatus which a content output subject owns like Embodiment 3 mentioned later For example, the content may be distributed. Further, the distribution content is not limited to images, and may be, for example, audio.

  As described above, according to the first embodiment, the server 1 acquires property information indicating a specific object (article) owned by a passerby (person) and attribute information indicating a plurality of attributes of the passerby. The product purchase tendency for each attribute is classified (clustered), and the content corresponding to the attribute of the passerby (content output target person) is selected with reference to the classification result. Since the server 1 automatically generates a cluster to be used for content selection from purchased product information and attribute information, it is not necessary to prepare in advance complicated rules created manually, and the appropriate content is selected and passed. Can be presented to a person.

  Further, according to the first embodiment, it is possible to classify products by unsupervised learning by performing clustering using SOM.

  Further, according to the first embodiment, it is possible to calculate the similarity relationship of each cluster (set) by clustering using the SOM, and select content according to the calculated similarity relationship. Accordingly, the server 1 may have similar purchase tendencies based on the self-organizing map as well as the content of the products that other passers-by who have similar attributes to the passers-by (content output target person). The content of other products that are predicted can also be presented.

  Further, according to the first embodiment, the server 1 specifies a specific object (such as a shopping bag or the product itself) corresponding to the product from the image captured by the camera 3, and the attribute of the passerby from the image. Is estimated and clustering is performed. Thereby, the server 1 can appropriately acquire the purchase item information and the attribute information and perform clustering.

  Further, according to the first embodiment, the server 1 can appropriately identify the origin (store) of the product and perform clustering by recognizing the shopping bag into which the product is placed as a specific item.

  Further, according to the first embodiment, the server 1 can present the content in a more appropriate manner by outputting the content to the signage 2 installed at a position corresponding to the camera 3.

(Embodiment 2)
In the present embodiment, a mode will be described in which a content different from that of a passerby who does not possess a specific object is presented to a passerby who possesses a specific object such as a shopping bag. In addition, about the content which overlaps with Embodiment 1, the same code | symbol is attached | subjected and description is abbreviate | omitted.
FIG. 8 is an explanatory diagram showing an outline of the second embodiment. In FIG. 8, in contrast to FIG. 5 in the first embodiment, a passer who has a specific item such as a shopping bag containing a product, that is, a passer who does not make a purchase for a passerby who has finished shopping. A state in which content different from a person is displayed is illustrated.

  In this embodiment, the signage 2 displays content not only for passers-by who do not have a specific item such as a shopping bag, but also for passers-by who have the specific item. In this case, the signage 2 displays different contents even for passers-by with similar attributes based on whether or not a specific object is possessed.

  For example, the signage 2 displays content for guiding the passer-by to the store when the passer-by does not have a shopping bag or the like and is not shopping yet (see FIG. 5). ). On the other hand, for example, the signage 2 displays content for inducing a revisit to a passerby who has a shopping bag or the like. For example, as shown in FIG. 8, the signage 2 displays information such as a future sale schedule of the product. Note that the content is not particularly limited, and may be different depending on whether or not a specific item is possessed.

  For example, the server 1 prepares two or more types of contents in the content DB 141 in association with the product ID of each product in accordance with the possession of a specific item. The server 1 determines whether or not the specific object is possessed based on the captured image acquired from the camera 3, selects different content according to the determination result, and distributes the content to the signage 2. In this way, in this system, it is possible to perform more appropriate sales promotion by changing the content according to not only the attribute of the passer but also the situation of the passer.

  In addition, although the server 1 changed the content based on the presence or absence of a specific thing in the above, this Embodiment is not limited to this. For example, the server 1 may change the content according to the time zone. As described above, the content selection criterion is not limited to whether or not a specific item is possessed, and other information may be used as a criterion.

FIG. 9 is a flowchart illustrating an example of a processing procedure of content distribution processing according to the second embodiment. Based on FIG. 9, the processing content of the content distribution processing in this Embodiment is demonstrated.
After determining that the passerby possesses the specific object (S13: YES) and executing the processing of steps S17 and S18, the control unit 11 of the server 1 executes the following processing. Based on the attribute information of the passerby, the control unit 11 selects content different from the content presented to the passerby who does not possess the specific object (step S201). For example, as described above, the control unit 11 selects, from the content DB 141, content (advertisement) that prompts passers-by to return to the store. The control unit 11 outputs the content to the signage 2 (step S202), and ends a series of processes.

  As described above, according to the present embodiment, different contents are selected depending on whether or not a specific item (for example, a shopping bag in a store) corresponding to a product is possessed and presented to a passerby. As a result, appropriate content can be presented to a passerby who has already purchased the product, and further sales promotion of the product can be promoted.

(Embodiment 3)
In the first embodiment, the content is distributed to the signage 2 and the content is presented to an unspecified number of passersby. In the present embodiment, a mode will be described in which content is distributed not to signage 2 but to a terminal 4 possessed by a member customer and presented to the member customer such as an actual store or an online store.
FIG. 10 is a schematic diagram illustrating a configuration example of a content distribution system according to the third embodiment. The content distribution system according to the present embodiment includes terminals (devices) 4, 4, 4,... Instead of the signage 2 and the camera 3. The terminal 4 is a terminal device possessed by a predetermined member customer who uses an actual store or an online store, and is, for example, a smartphone, a personal computer, a tablet terminal, or the like. In the present embodiment, the server 1 uses the member information including the attribute information pre-registered via the terminal 4 and the member payment information including the purchase history of the product, a product advertisement, etc. Deliver content.

  FIG. 11 is a block diagram illustrating a configuration example of the server 1 according to the third embodiment. In this embodiment, the auxiliary storage unit 14 of the server 1 stores a member DB 143 instead of the passer-by DB 142. The member DB 143 is a database that stores member information and settlement information of each member.

  FIG. 12 is an explanatory diagram showing an example of the record layout of the member DB 143. As shown in FIG. The member DB 143 includes a member ID column, name column, address column, attribute column, and settlement column. The member ID stores identification information for identifying each member. The name column stores the name of the member in association with the member ID. The address column stores the member's mail address in association with the member ID. The attribute column stores attribute information such as the gender and age of the member in association with the member ID. The payment column stores the payment history (settlement information) of the product by the member in association with the member ID.

  As described above, in the present embodiment, the server 1 associates the member information including the member's name, attribute, and the like with the payment information including the product purchased by the member and the payment amount in the member DB 143 in association with the member ID. I remember it. That is, the server 1 stores a product (article) owned by a member by purchase and an attribute of the member in association with each other. Based on this information, the server 1 performs clustering of product purchase trends based on member attributes. Specifically, as in the first embodiment, the server 1 performs unsupervised learning using a technique such as SOM.

  The server 1 distributes content corresponding to the attribute of each member to the terminal 4 based on the clustering result. As described above, the server 1 can not only present contents to passers-by in digital signage but also present contents directly to each member to promote sales of products.

FIG. 13 is a flowchart illustrating an example of a processing procedure executed by the server 1 according to the third embodiment. Based on FIG. 13, the processing content which the server 1 performs in this Embodiment is demonstrated.
The control unit 11 of the server 1 reads the member information and settlement information of each member from the member DB 143 (Step S301). The member information is information registered by each member, and includes attribute information indicating a plurality of attributes of the member. The settlement information is a settlement history of product purchase by each member, and includes information (property information) indicating a product (article) owned by the member by purchase. Based on the member information and the payment information, the control unit 11 classifies (clusters) the purchase tendency of the products provided to the member for each attribute (step S302). Specifically, the control unit 11 performs clustering by SOM or the like as in the first embodiment. The control unit 11 performs machine learning that maps the member attribute information included in the member information as a feature vector to the self-organizing map, and labels the product (article) owned by the member as an output value related to each cluster. By doing so, a neural network that classifies the purchase tendency of the product for each member attribute is constructed.

  The control unit 11 refers to the classification result in step S302, and selects content to be distributed to each member's terminal 4 based on the attribute information of each member (step S303). The control unit 11 outputs (distributes) the selected content to the terminal 4 of each member (step S304), and ends a series of processes.

  As described above, according to the third embodiment, not only the clustering based on the information extracted from the captured image as in the first embodiment, but also the clustering is performed in the same manner from the member information and the payment information of the member, and appropriate content is obtained. You can select and output.

  Further, according to the third embodiment, content can be appropriately presented to individual members by outputting (distributing) the content to the terminal 4 owned by the member.

(Embodiment 4)
FIG. 14 is a functional block diagram showing the operation of the server 1 in the above-described form. When the control unit 11 executes the program P, the server 1 operates as follows.
The storage unit 1401 stores content corresponding to each of a plurality of products. The acquisition unit 1402 acquires property information indicating an article owned by a person and attribute information indicating the attribute of the person. The classifying unit 1403 classifies the product purchase tendency for each attribute based on the product corresponding to the article and the attribute information. The selection unit 1404 refers to the classification result and selects the content according to the attribute information.

  The fourth embodiment is as described above, and the other parts are the same as those of the first to third embodiments. Therefore, the corresponding parts are denoted by the same reference numerals, and detailed description thereof is omitted.

  The embodiment disclosed this time is to be considered as illustrative in all points and not restrictive. The scope of the present invention is defined by the terms of the claims, rather than the meanings described above, and is intended to include any modifications within the scope and meaning equivalent to the terms of the claims.

1 server (information processing equipment)
11 Control Unit 12 Main Storage Unit 13 Communication Unit 14 Auxiliary Storage Unit P Program 141 Content DB
142 Passerby DB
143 Member DB
2 Signage (display device)
3 Camera (device)
4 Terminal (device)

Claims (16)

A storage unit for storing content corresponding to each of a plurality of products;
An acquisition unit that acquires property information indicating an article owned by a person and attribute information indicating an attribute of the person;
Based on the product corresponding to the article and the attribute information, a classification unit that classifies a product purchase tendency for each attribute;
An information processing apparatus comprising: a selection unit that selects a content corresponding to the attribute information with reference to a classification result. An attribute acquisition unit for acquiring attribute information of a content output target person,
The information processing apparatus according to claim 1, further comprising: an output unit that outputs the content selected by the selection unit according to attribute information of the content output target person. The acquisition unit
Obtain an image of the person from an imaging device installed at a predetermined position,
The information processing apparatus according to claim 2, wherein the property information and attribute information are acquired from the image. The storage unit has information that associates the attribute information for each feature amount,
The information processing apparatus according to claim 3, wherein the acquisition unit acquires the attribute information from the storage unit according to a feature amount of the person extracted from the image. The classification unit includes:
From the similar relationship between the persons using the attribute information and the property information, the product purchase tendency is classified into a plurality of sets,
The information processing apparatus according to claim 3, wherein a similarity relationship for each of the classified sets is calculated. The information processing apparatus according to claim 5, wherein the selection unit selects the content based on a similarity relationship for each set. The information processing apparatus according to claim 5, wherein the acquisition unit acquires the property information from a shape of the article or a mark attached to the article. The information processing apparatus according to claim 3, wherein the output unit outputs the content to a display device installed at a position corresponding to the imaging device. The information processing apparatus according to any one of claims 3 to 8, wherein the selection unit selects the different content according to whether the person has the article. The acquisition unit acquires member information of the person registered in advance and payment information of a product by the person,
The said classification | category part classifies the goods purchase tendency for every attribute based on the said person's purchase goods which the said payment information shows, and the said person's attribute information which the said member information shows. Information processing device. The information processing apparatus according to claim 10, wherein the output unit outputs the content to a terminal device owned by the content output target person. Acquiring property information indicating an article owned by a person and attribute information indicating an attribute of the person;
Based on the product corresponding to the article and the attribute information, classify the product purchase tendency for each attribute,
An information processing method for causing a computer to execute a process of selecting a content corresponding to the attribute information from a storage unit that stores content corresponding to each of the plurality of products with reference to a classification result. Acquiring property information indicating an article owned by a person and attribute information indicating an attribute of the person;
Based on the product corresponding to the article and the attribute information, classify the product purchase tendency for each attribute,
A program that causes a computer to execute a process of referring to a classification result and selecting the content according to the attribute information from a storage unit that stores content corresponding to each of the plurality of products. A system having a device that acquires information about a content output target person and an information processing apparatus that outputs content,
The information processing apparatus includes:
A storage unit for storing content corresponding to each of a plurality of products;
An acquisition unit that acquires property information indicating an article owned by a person and attribute information indicating an attribute of the person;
Based on the product corresponding to the article and the attribute information, a classification unit that classifies a product purchase tendency for each attribute;
A target person attribute acquisition unit for acquiring attribute information of the content output target person from the device;
A selection unit that refers to the classification result by the classification unit and selects the content according to the attribute information of the content output target person;
An information processing system comprising: an output unit that outputs the selected content. The device is an imaging device installed at a predetermined position, or a terminal device possessed by the content output target person,
The target person attribute acquisition unit acquires the attribute information from an image obtained by the image capturing device capturing the content output target person or member information of the content output target person registered in advance via the terminal device. The information processing system according to claim 14. An acquisition unit that acquires an image of a person from an imaging device installed at a predetermined position;
A specifying unit that specifies an article that is given to the person at the time of providing a product from a partial image area in the image and that the person has;
An estimation unit that estimates a plurality of attributes of the person from an image region other than the partial image region in the image;
An information processing apparatus comprising: a classification unit that classifies a purchase tendency of the product specified from the article based on the estimated plurality of attributes.

Images