JP2019149058A - Information processing device, information processing method, and information processing program - Google Patents

Abstract

To make it possible to appropriately perform process for a desired person (individual person).SOLUTION: An information processing device according to the present invention includes an acquisition unit and a search unit. The acquisition unit acquires graph information in which a plurality of nodes corresponding to respective persons are connected according to the similarity of the plurality of persons, and personal information on one person. The search unit searches the graph information using as an origin an origin node that is an origin for searching the graph information determined on the basis of a predetermined criterion among the plurality of nodes of the graph information acquired by the acquisition unit, and determines whether the one person is included in the plurality of persons.SELECTED DRAWING: Figure 3

Description

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

  2. Description of the Related Art Conventionally, a technique for determining a correspondence relationship such as identity of various information has been provided. For example, using linear transformation, it is determined whether the correspondence is an effective correspondence such as a correspondence between regions existing on the object, and based on the number of effective correspondences, the first image and A technique for determining the identity of an object appearing in a second image is provided.

Japanese Patent Laid-Open No. 2018-010592

Masajiro Iwasaki "Neighbor Search by Approximate k Nearest Neighbor Graph Using Tree-Structured Index", IPSJ Transactions, 2011/2, Vol. 52, No. 2. pp.817-828.

  However, in the above-described conventional technology, it may be difficult to appropriately perform processing for a desired person (individual). For example, when determining the identity of an object appearing in a first image and a second image, it is necessary to specify two images to be compared. For example, when the first image is an image of an individual (user) captured at an entrance gate or the like, for example, a second image to be compared with the first image is identified (extracted) from many registered images, It is necessary to judge. In such a case, an appropriate image may not be specified as the second image, and it may be difficult to appropriately perform processing for a desired person (individual).

  The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program that can appropriately perform processing on a desired person (individual). To do.

  An information processing apparatus according to the present application includes: a graph unit in which a plurality of nodes corresponding to each of a plurality of individuals are linked according to the similarity of the plurality of individuals; and an acquisition unit that acquires personal information about one individual; Searching for the graph information starting from a starting node that is a starting point for searching for the graph information determined based on a predetermined criterion among the plurality of nodes of the graph information acquired by the acquiring unit. And a search unit for determining whether or not the one individual is included in the plurality of individuals.

  According to one aspect of the embodiment, there is an effect that processing for a desired person (individual) can be appropriately performed.

FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. FIG. 2 is a diagram illustrating a configuration example of the information processing system 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 a personal information storage unit according to the embodiment. FIG. 5 is a diagram illustrating an example of the index information storage unit according to the embodiment. FIG. 6 is a diagram illustrating an example of the graph information storage unit according to the embodiment. FIG. 7 is a diagram illustrating an example of a model information storage unit according to the embodiment. FIG. 8 is a flowchart illustrating an example of information processing according to the embodiment. FIG. 9 is a flowchart illustrating an example of the generation process according to the embodiment. FIG. 10 is a diagram illustrating an example of feature amount extraction according to the embodiment. FIG. 11 is a flowchart illustrating an example of search processing using graph information. FIG. 12 is a diagram conceptually showing individual graph information. FIG. 13 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus.

  Hereinafter, 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 in detail with reference to the drawings. Note that the information processing apparatus, the information processing method, and the information processing program according to the present application are not limited by this embodiment. In the following embodiments, the same portions are denoted by the same reference numerals, and redundant description is omitted.

(Embodiment)
[1. Information processing)
An example of information processing according to the embodiment will be described with reference to FIG. FIG. 1 is a diagram illustrating an example of information processing according to the embodiment. In FIG. 1, the information processing apparatus 100 searches for graph data (graph information) obtained by structuring a plurality of individuals to determine whether one individual is included in the graph information (plural individuals). Show. For example, it is assumed that an individual is a single person. In FIG. 1, the information processing apparatus 100 will be described by taking as an example a case in which graph information obtained by structuring an individual using vector data (“vector information” or simply “vector”) corresponding to each individual is used. .

  Note that the information used by the information processing apparatus 100 is not limited to a vector, and may be information in any format as long as it is information that can express the similarity of each individual. For example, the information processing apparatus 100 may use graph information obtained by structuring an individual using a predetermined data or value corresponding to each individual. For example, the information processing apparatus 100 may use graph information obtained by structuring an individual using a predetermined numerical value (for example, a binary value or a hexadecimal value) generated from each individual. For example, instead of the vector, any form of data may be used as long as the distance (similarity) between the data is defined. In addition, in the example of FIG. 1, as long as an entrance is an example and it is an object, it is not limited to an entrance, and may be an entry into the country or the like. That is, the purpose of information processing may be any purpose as long as it is intended for individuals.

[1-1. About graph information)
The information processing apparatus 100 performs information processing using graph data in which vectors (nodes) are connected by directed edges, as indicated by graph information GR11 in FIG. Note that the graph information as indicated by the graph information GR11 in FIG. 1 may be generated by the information processing apparatus 100, or the information processing apparatus 100 may provide the graph information as indicated by the graph information GR11 in FIG. You may acquire from other external apparatuses, such as the provision apparatus 50 (refer FIG. 2).

  Further, the directed edge here means an edge that can trace data only in one direction. In the following, a source traced by an edge, that is, a node as a starting point is referred to as a reference source, and a destination traced by an edge, that is, a node as an end point is defined as a reference destination. For example, the directed edge connected from the predetermined node “A” to the predetermined node “B” indicates that the reference source is the node “A” and the reference destination is the node “B”. Note that the edge connecting the nodes is not limited to the directed edge, and may be various edges. For example, the edge connecting the nodes may be an edge having no direction to connect the nodes. For example, the edges connecting the nodes may be edges that can be referred to each other. For example, all the edges connecting the nodes may be bidirectional edges.

  For example, an edge having the node “A” as a reference source in this way is referred to as an output edge of the node “A”. Further, for example, an edge with the node “B” as a reference destination in this way is referred to as an input edge of the node “B”. In other words, the output edge and the input edge here are differences in which one of the two nodes connected to the directed edge is regarded as the center, and the one directed edge. Becomes the output edge and the input edge. In other words, the output edge and the input edge are relative concepts, and for one directional edge, when the node as the reference source is regarded as the center, the output edge is regarded as the center, and the node as the reference destination is regarded as the center. The input edge. In the present embodiment, since the edges are directed edges such as output edges and input edges, the directed edges may be simply referred to as “edges” below.

  For example, the information processing apparatus 100 performs processing on nodes corresponding to a huge number of individuals in units of millions to hundreds of millions, but only a part thereof is illustrated in the drawing. In the example of FIG. 1, in order to simplify the description, the outline of the process will be described by illustrating eight nodes. For example, the information processing apparatus 100 acquires graph information including a plurality of nodes (vectors) as indicated by nodes N1, N2, N3, etc., as indicated by the graph information GR11 in FIG. In the example of FIG. 1, each node in the graph information GR11 is connected with edges (output edges) to a predetermined number of nodes from the closest distance to the node. For example, the predetermined number may be various values such as 2, 5, 10, and 100 depending on the purpose and application. For example, when the predetermined number is 2, the output edge is connected from the node N1 to the node having the shortest distance from the node N1 and the two nodes having the second closest distance. The distance as the index indicating the similarity may be any distance as long as it can be applied as the distance between the vectors (N-dimensional vectors), such as the Euclidean distance, the Mahalanobis distance, and the cosine distance. Various distances may be used.

  In addition, when “node N * (* is an arbitrary numerical value)” is described in this way, this indicates that the node is identified by the node ID “N *”. For example, when “node N1” is described, the node is a node identified by the node ID “N1”.

  Further, in the graph information GR11 in FIG. 1, the node N10 is connected to an edge E7 that is a directed edge toward the node N7. That is, the node N10 is connected to the node N7 by the edge E7. Thus, when “edge E * (* is an arbitrary numerical value)” is described, it indicates that the edge is an edge identified by the edge ID “E *”. For example, when “edge E11” is described, the edge is an edge identified by the edge ID “E11”. For example, it is possible to trace from the node N10 to the node N7 by the edge E7 connected with the node N10 as a reference source and the node N7 as a reference destination. In this case, the edge E7 which is a directed edge becomes an output edge when identified with the node N10 as the center, and becomes an input edge when identified with the node N7 as the center. Moreover, the bidirectional arrow in the graph information GR11 in FIG. 1 indicates that the directed edge from both nodes to the other node is connected. For example, the two-way arrow between the node N2 and the node N451 in the graph information GR11 connects two edges, a directed edge from the node N2 to the node N451 and a directed edge from the node N451 to the node N2. Indicates that

  Further, the graph information GR11 in FIG. 1 may be a Euclidean space. Further, the graph information GR11 shown in FIG. 1 is a conceptual diagram for explaining the distance between the vectors and the like, and the graph information GR11 is a multidimensional space. For example, the graph information GR11 illustrated in FIG. 1 is illustrated in a two-dimensional manner to be illustrated on a plane, but is assumed to be a multidimensional space such as 100 dimensions or 1000 dimensions.

  Here, the distance between the vector data indicates individual similarity, and the closer the distance, the more similar. In the present embodiment, the distance between the nodes in the graph information GR11 is set as the similarity between the corresponding objects. For example, it is assumed that the similarity of individuals corresponding to each node is mapped as a distance between nodes in the graph information GR11. For example, it is assumed that the similarity between concepts corresponding to each node is mapped to the distance between the nodes. Here, in the example shown in FIG. 1, the similarity between objects with short distances between nodes in the graph information GR11 is high, and the similarity between objects with long distances between nodes in the graph information GR11 is low. For example, in the graph information GR11 in FIG. 1, the node identified by the node ID “N35” and the node identified by the node ID “N693” are close to each other, that is, the distance is short. Therefore, the object corresponding to the node identified by the node ID “N35” and the object corresponding to the node identified by the node ID “N693” are highly similar.

  Further, for example, in the graph information GR11 in FIG. 1, the node identified by the node ID “N7” and the node identified by the node ID “N2” are remote, that is, the distance is long. Therefore, the similarity between the object corresponding to the node identified by the node ID “N7” and the object corresponding to the node identified by the node ID “N2” is low.

[1-2. Example of vector generation)
Also, each node (vector) here corresponds to each object (individual). If the personal information is numerical data indicating various individual states, it can be handled as it is as vector data. However, when the personal information is text, image, or sound, it is necessary to convert it into vector data. Therefore, in the example of FIG. 1, a multi-dimensional (N-dimensional) vector generated based on the feature amount extracted from the personal information of each individual may be an object.

  For example, the information processing apparatus 100 may generate an N-dimensional vector from the personal information of each individual using a model that extracts the characteristics of the personal information. In the example of FIG. 1, the information processing apparatus 100 uses the model (model M1) identified by the model ID “M1” as shown in the model information storage unit 124 (see FIG. 7) to store the personal information of each individual. Generate a vector from As described above, when “model M * (* is an arbitrary numerical value)” is described, it indicates that the model is a model identified by the model ID “M *”. For example, when “model M1” is described, the model is a model identified by the model ID “M1”. Further, as shown in the model information storage unit 124, the model M1 is a model used for use “feature extraction (entrance)”, that is, a feature extraction from personal data (personal information). The data is “model data MDT1”.

  For example, the information processing apparatus 100 calculates the value of each element (neuron) in the model M1 by inputting personal information of any individual into the model M1, and outputs the same information as the input personal information. For example, the information processing apparatus 100 may extract the value of each element (neuron) in the intermediate layer as a feature amount and generate N-dimensional vector data corresponding to each individual.

  Here, an example of generation of vector data corresponding to each individual is shown using FIG. FIG. 10 is a diagram illustrating an example of feature amount extraction according to the embodiment. FIG. 10 is a conceptual diagram of the model M1. In FIG. 10, illustration of lines indicating the connection relations of the elements (neurons) is omitted. As shown in FIG. 10, the model M1 includes an input layer IL, an intermediate layer CL, and an output layer OL. For example, the input layer IL of the model M1 is a layer into which personal information is input. The output layer OL is a layer that outputs information similar to the input personal information in response to an input to the input layer IL.

  For example, the most compressed compressed layer RP at the center of the intermediate layer CL is a layer that expresses the characteristics of the input personal information. For example, in the intermediate layer CL of the model M1, the portion from the input layer IL to the compression layer RP corresponds to a portion where encoding processing is performed. In the intermediate layer CL of the model M1, the portion from the input layer IL to the compression layer RP corresponds to a portion that performs processing for compressing the characteristics of the input personal information. For example, in the intermediate layer CL of the model M1, the portion from the compression layer RP to the output layer OL corresponds to a portion that performs decoding processing. In the intermediate layer CL of the model M1, the portion from the compression layer RP to the output layer OL corresponds to a portion that performs processing for restoring the compressed personal information.

  For example, the information processing apparatus 100 may use information such as the neuron NL1 and the neuron NL2 included in the compression layer RP as a vector. For example, when the personal information of a certain individual is input, the information processing apparatus 100 uses the value VE1 corresponding to the calculated neuron NL1 and the value VE2 corresponding to the neuron NL2 as vector elements (one-dimensional value). It may be extracted. For example, when personal information of a certain individual is input, the information processing apparatus 100 may extract the value VE1 corresponding to the calculated neuron NL1 as the first dimension element of the individual vector. For example, when personal information of a certain individual is input, the information processing apparatus 100 may extract the value VE2 corresponding to the calculated neuron NL2 as the second-dimensional element of the individual vector. As described above, the information processing apparatus 100 may generate a vector corresponding to each individual by inputting the personal information of each individual to the model M1. Note that the information processing apparatus 100 may acquire a vector corresponding to each individual from another external device such as the information providing apparatus 50. Note that the information processing apparatus 100 may use, as each element of the vector, a value corresponding to each neuron itself, or a value obtained by multiplying a value corresponding to each neuron by a predetermined coefficient. In addition, in the example of FIG. 1, for simplicity of explanation, the case where each element (value) of the vector is an integer is shown, but each element (value) of the vector is a real number including a numerical value after the decimal point. Also good.

  Note that the information processing apparatus 100 may use not only the elements (neurons) of the compression layer RP but also information on other elements (neurons) in the intermediate layer CL as vectors. For example, the information processing apparatus 100 may use information such as the neuron NL3 of the encoding part and the neuron NL4 of the decoding part as a vector. For example, when personal information of a certain individual is input, the information processing apparatus 100 uses the calculated value VE3 corresponding to the neuron NL3 and the value VE4 corresponding to the neuron NL4 as vector elements (one-dimensional value). It may be extracted. Note that the above is an example, and the information processing apparatus 100 may perform feature extraction from personal information using various models without being limited to an auto encoder. For example, a model trained to discriminate between individuals who are suitable for a predetermined purpose such as startup members and those who are not suitable may be generated, and the intermediate layer may be extracted as vector data. For example, the model may be generated by a method of learning similarity such as a triplet loss. Further, the information processing apparatus 100 may perform feature extraction without using a model. For example, the information processing apparatus 100 may generate a vector by extracting information corresponding to features (features) set by an administrator of the information processing apparatus 100 from personal information. For example, the information processing apparatus 100 extracts attribute information such as an individual's age and gender, an image obtained by capturing an image of the face and the whole, information corresponding to features (features) such as voice and behavior from personal information, and generates a vector. May be.

  For example, the information processing apparatus 100 may acquire the model M1 from another external device such as the information providing apparatus 50. Note that the information processing apparatus 100 may generate the model M1 by using the personal information PDT1, PDT2, PDT451, and the like of each individual stored in the personal information storage unit 121 (see FIG. 4). For example, the information processing apparatus 100 may generate the model M1 using personal information PDT1, PDT2, PDT451, and the like of each individual as an input. For example, the personal information PDT1, PDT2, PDT451, and the like may include personal attribute information, images, sounds, actions, and the like. For example, personal information such as personal information PDT1, PDT2, and PDT451 may include various attribute information about the user such as demographic attribute information and psychographic attribute information of the corresponding individual. For example, personal information such as personal information PDT1, PDT2, and PDT451 may include information such as the age, sex, address, and interest of the corresponding individual. Further, for example, the personal information may include image information obtained by imaging the corresponding individual. For example, the personal information may include image information obtained by imaging the corresponding individual's face or the whole (whole body). For example, the personal information may include voice information such as a corresponding individual utterance. For example, the personal information may include various behavior information regarding the behavior of the corresponding individual. For example, the personal information may include action information such as searching for a corresponding individual, browsing content, and purchasing.

  The information processing apparatus 100 includes an input layer to which personal information of an individual is input, an output layer, a first element that belongs to any layer other than the output layer from the input layer to the output layer, A second element whose value is calculated based on the element and the weight of the first element, and for personal information input to the input layer, each element belonging to each layer other than the output layer as a first element, A model M1 that outputs information similar to information input to the input layer from the output layer may be generated by performing an operation based on the first element and the weight of the first element. Note that the information processing apparatus 100 may acquire a model used for vector generation from another external apparatus such as the information providing apparatus 50.

[1-3. Processing example)
From here, the information processing apparatus 100 acquires the personal information of one individual from the user, and the case where it is determined whether one individual is included in the graph information, that is, among a plurality of targeted individuals, is described as an example. To do. Specifically, the information processing apparatus 100 acquires an individual X who is a visitor from an entrance gate EGT provided at an entrance of a predetermined building or the like, and authenticates the individual X based on the acquired personal X information. Whether to open the entrance gate EGT is determined. In the example of FIG. 1, the information processing apparatus 100 acquires personal image information captured at the entrance gate EGT as personal information, and using the acquired personal information, the individual is assigned to a plurality of individuals in the graph information GR11. Determine whether it is included. For example, it is assumed that a plurality of individuals such as the individual # 1 and the individual # 451 included in the graph information GR11 are persons who are permitted to enter a building where the entrance gate EGT is provided. For example, the individual # 1 and the individual # 451 included in the graph information GR11 are registered in a predetermined external device as being permitted to enter a building where the entrance gate EGT is provided. In the example of FIG. 1, it is assumed that the graph information GR11 is generated based on personal information PDT1, PDT2, PDT451, and the like, which are image information of each individual's face.

  In the example of FIG. 1, a case where an individual X enters a building where an entrance gate EGT is provided will be described as an example. First, the entrance gate EGT that acquired the personal information of the individual X transmits the personal information PDT11 of the individual X to the information processing apparatus 100. For example, the entrance gate EGT has a function of communicating with a sensor (image sensor or the like) that captures a predetermined range such as the front, and the information processing apparatus 100 via a network (for example, the network N in FIG. 2). The image information picked up by is transmitted to the information processing apparatus 100. For example, the entrance gate EGT has another sensor (infrared sensor or the like) that detects that a person such as the front is approaching, and when the approach of the person is detected by another sensor, the sensor captures image information. The image information captured by the sensor is transmitted to the information processing apparatus 100. Note that the above is an example, and any configuration may be used as long as the information processing apparatus 100 can acquire image information of a visitor.

  Then, the information processing apparatus 100 acquires personal information related to one individual (step S11). In the example of FIG. 1, the information processing apparatus 100 acquires personal information PDT11 regarding the individual X from the entrance gate EGT. The information processing apparatus 100 acquires personal information PDT11 related to the individual X from the terminal device 10 (see FIG. 3) carried by the individual X.

  Then, the information processing apparatus 100 generates a vector used for searching for graph information from personal information corresponding to one individual. In the example of FIG. 1, the information processing apparatus 100 generates a vector corresponding to the person X by processing as shown in the processing group PS11. The information processing apparatus 100 inputs the personal information PDT11 related to the individual X into the model M1 (step S12). Specifically, the information processing apparatus 100 inputs the personal information PDT11 of the individual X into the model M1. Then, the information processing apparatus 100 generates a vector using information in the model M1 after the input of the personal information PDT11 (Step S13). For example, the information processing apparatus 100 generates vector data using each element in the model M1 to which the personal information PDT11 is input.

  In the example of FIG. 1, the information processing apparatus 100 generates vector data VD11 (also simply referred to as “vector VD11”) using the values of the elements in the model M1 to which the personal information PDT11 is input. For example, the information processing apparatus 100 uses the value VE1 (see FIG. 10) corresponding to the neuron NL1 of the model M1 and the value VE2 (see FIG. 10) corresponding to the neuron NL2 when the personal information PDT11 of the individual X is input. To generate a vector. For example, when the personal information PDT11 of the person X is input, the information processing apparatus 100 may extract the value VE1 corresponding to the calculated neuron NL1 as the first dimension element of the vector VD11. For example, when personal information of a certain individual is input, the information processing apparatus 100 generates the vector VD11 using the value VE2 corresponding to the calculated neuron NL2 as a second-dimensional element of the vector VD11. In the example of FIG. 1, the information processing apparatus 100 generates a vector VD11 in which the first dimension element is “35” and the second dimension element is “63”.

  Then, the information processing apparatus 100 searches for an individual similar to the individual X (hereinafter also referred to as “similar individual”) (step S14). For example, the information processing apparatus 100 may search for a similar person of the person X by appropriately using various conventional techniques such as the technique of neighborhood search disclosed in Non-Patent Document 1. For example, the information processing apparatus 100 uses graph information GR11 in which nodes having high similarity are connected by edges.

  In the example of FIG. 1, the information processing apparatus 100 searches for similar individuals of the individual X using the graph information GR11 and the index information IND11 as shown in the information group INF11. For example, the information processing apparatus 100 acquires graph information GR11 regarding an individual from the graph information storage unit 123 (see FIG. 6). Further, for example, the information processing apparatus 100 uses the index information storage unit 122 (see FIG. 5) to obtain the index information IND11 used to determine the node (hereinafter also referred to as “starting vector”) that is the starting point of the search in the graph information GR11. get. Note that the index information IND11 may be generated by the information processing apparatus 100, or the information processing apparatus 100 may acquire the index information IND11 from another external device such as the information providing apparatus 50.

  The information processing apparatus 100 uses the index information IND11 in order to determine (specify) the starting point vector corresponding to one individual (query). In the example of FIG. 1, the information processing apparatus 100 uses the index information IND11 in order to determine (specify) the starting vector corresponding to the vector VD11 of the person X. That is, the information processing apparatus 100 determines a starting vector in the graph information GR11 using the vector VD11 and the index information IND11.

  The index information IND11 in FIG. 1 has a hierarchical structure shown in the index information storage unit 122 in FIG. For example, the index information IND11 indicates that the first layer nodes (vectors) located immediately below the route RT are the nodes VT1, VT2, and the like. Further, for example, the index information IND11 indicates that the nodes in the second layer immediately below the node VT2 are nodes VT2-1 to VT2-4 (not shown). For example, the index information IND11 indicates that the nodes in the third hierarchy immediately below the node VT2-2 are the node N35, the node N451, and the node N693, that is, the nodes (vectors) in the graph information GR11.

  For example, the information processing apparatus 100 determines a starting point vector in the graph information GR11 using tree structure type index information as indicated by the index information IND11 in FIG. 1 (step S15). In the example of FIG. 1, the information processing apparatus 100 generates the vector VD11 and then traces the index information IND11 from the top to the bottom, thereby efficiently specifying the starting point vector that is a neighborhood candidate for the index information IND11. A starting vector corresponding to the search query (one individual) can be determined.

  For example, the information processing apparatus 100 may determine the starting vector corresponding to the vector VD11 by tracing the index information IND11 from the root RT to the leaf node (node (vector) in the graph information GR11). In the example of FIG. 1, for example, the information processing apparatus 100 determines the node N451 as a starting vector by tracing the index information IND11 from the route RT to the node N451. For example, the information processing apparatus 100 may determine the leaf node that has reached the origin vector by tracing the index information IND11 from the root RT to the leaf node by appropriately using various conventional techniques related to the tree structure. For example, the information processing apparatus 100 may determine the starting point vector by tracing down the index information IND11 based on the similarity with the vector VD11. For example, the information processing apparatus 100 may determine which node such as the nodes VT1 and VT2 is to be traced from the route RT based on the similarity between the vector VD11 and the nodes VT1 and VT2. For example, the information processing apparatus 100 may determine to trace from the route RT to the node VT2 having the highest similarity to the vector VD11 among the nodes VT1, VT2, and the like. Further, for example, the information processing apparatus 100 may determine to trace from the node VT2 to the node VT2-2 having the highest similarity to the vector VD11 among the nodes VT2-1 to VT2-4. Further, for example, the information processing apparatus 100 may determine to follow the node VT2-2 from the nodes N35, N451, N693, etc., to the node node N451 having the highest similarity with the vector VD11. In the example of FIG. 1, a case where one starting point vector is determined is shown for ease of explanation, but the information processing apparatus 100 may determine a plurality of starting point vectors. For example, the information processing apparatus 100 may determine a plurality of vectors (nodes) such as nodes N451, N35, N693, and N2 as the starting vector. Note that one or more nodes may be selected at random from the graph information GR11 at the start of the search without using the index information IND11, and may be used as a starting point vector, or one or more nodes specified in advance may be used as starting points. It can be a vector.

  Then, the information processing apparatus 100 extracts similar individuals of the individual X by searching the graph information GR11 (step S16). For example, the information processing apparatus 100 extracts a node located in the vicinity of the node N451 as a similar individual. For example, the information processing apparatus 100 extracts nodes that are close to the node N451 as similar individuals. For example, the information processing apparatus 100 extracts a node that can be reached from the node N451 as a similar individual by tracing the edge starting from the node N451. For example, the information processing apparatus 100 extracts a predetermined number (for example, 2 or 10) of nodes as similar individuals. For example, the information processing apparatus 100 may extract similar individuals of the individual X by a search process as shown in FIG. In the example of FIG. 1, the information processing apparatus 100 extracts the node N451 and the node N35 as similar individuals by searching the graph information GR11 with the node N451 as a starting point.

  For example, the information processing apparatus 100 determines whether or not an individual is included in a plurality of individuals by comparing a vector of one individual with a vector of similar individuals. In the example of FIG. 1, the information processing apparatus 100 compares the vector VD11 of the person X with the vector VD451 of the node N451 (person # 451) and the vector VD35 of the node N35 (person # 35) as shown in the target list SPL. (Step S17), and a determination process is performed (Step S18).

  For example, the information processing apparatus 100 determines whether the individual X is included in a plurality of individuals in the graph information GR11 by comparing each vector. For example, the information processing apparatus 100 determines whether the error between the vector VD11 of the individual X and the vector VD451 of the node N451 or the vector VD35 of the node N35 is an error within a predetermined threshold. For example, the information processing apparatus 100 determines that a vector node (individual) whose error from the vector X of the individual X is within a predetermined threshold is the individual X. That is, the information processing apparatus 100 determines that the person X is included in a plurality of individuals in the graph information GR11 when there is a vector whose error from the vector VD11 of the person X is within a predetermined threshold. For example, the information processing apparatus 100 may determine a vector node (individual) that matches the personal X vector VD11 as the personal X.

  In the example of FIG. 1, as illustrated in the determination list DRS, the information processing apparatus 100 determines that the vector VD11 of the individual X and the vector VD35 of the node N35 are errors within a predetermined threshold, and the individual X is an individual. It is determined that it is # 35. That is, the information processing apparatus 100 determines that the person X is an individual who is permitted to enter the building where the entrance gate ETG is provided. Then, the information processing apparatus 100 authenticates the individual X as an appropriate visitor.

  In the above example, in order to simplify the description, the case where the information processing apparatus 100 performs a process of extracting a similar individual and a determination based on a comparison between the similar individual and one individual is illustrated. The apparatus 100 may perform determination by comparing the extracted similar person with one individual each time the similar person is extracted. For example, the information processing apparatus 100 may repeat the processes in steps S16 to S18 by extracting similar individuals one by one. In the example of FIG. 1, when the information processing apparatus 100 determines the node N451 as a starting node, the information processing apparatus 100 determines whether the error between the vector VD451 of the node N451 (person # 451) and the vector VD11 of the person X is within a predetermined threshold. You may judge. Then, when the information processing apparatus 100 determines that the error between the vector VD451 of the node N451 (person # 451) and the vector VD11 of the person X is within a predetermined threshold, the information processing apparatus 100 determines that the person X is the person # 451. May be terminated.

  On the other hand, if the information processing apparatus 100 determines that the error between the vector VD451 of the node N451 (person # 451) and the vector VD11 of the person X is not within a predetermined threshold, the information processing apparatus 100 continues the search process and extracts the next similar person The determination process may be repeated. In this case, the information processing apparatus 100 may extract the node N35 as a similar individual next to the node N451. Then, the information processing apparatus 100 may determine whether an error between the vector VD35 of the node N35 (person # 35) and the vector VD11 of the person X is within a predetermined threshold. When the information processing apparatus 100 determines that the error between the vector VD35 of the node N35 (person # 35) and the vector VD11 of the person X is within a predetermined threshold, the information processing apparatus 100 determines that the person X is the person # 35. May be terminated. Further, when the information processing apparatus 100 determines that the error between the vector VD35 of the node N35 (person # 35) and the vector VD11 of the person X is not within a predetermined threshold, another node after the node N35 is regarded as a similar individual. It may be extracted and the same determination process may be performed.

  The information processing apparatus 100 provides a service based on the determination result. In the example of FIG. 1, the information processing apparatus 100 requests the entrance gate EGT to open the gate based on the determination result that the person X is the person # 35 (step S19). The information processing apparatus 100 transmits, to the entrance gate EGT, information that instructs the entrance gate EGT to open the gate, assuming that the entrance of the individual X who is the visitor is OK. Thereby, the gate is opened to the entrance gate EGT, and the individual X can enter the building where the entrance gate ETG is provided.

  Further, the information processing apparatus 100 may provide information regarding the determination result and the authentication result. For example, the information processing apparatus 100 may transmit information indicating that it is determined to permit entry of the individual X to the terminal apparatus 10 used by a manager of a building where the entrance gate ETG is provided. For example, the information processing apparatus 100 may transmit information indicating that the person X is authenticated as an appropriate visitor to the terminal apparatus 10 used by an administrator of a building where the entrance gate ETG is provided.

  On the other hand, the information processing apparatus 100 determines that the individual X is not included in the graph information GR11 when the individual of the vector whose error from the vector VD11 of the individual X is within a predetermined threshold is not included in the graph information GR11. In this case, the information processing apparatus 100 determines that the entry of the individual X is not permitted because the individual X is not included in the graph information GR11. Then, the information processing apparatus 100 does not authenticate the individual X as an appropriate visitor.

  Further, for example, the information processing apparatus 100 may transmit information indicating that it is determined not to permit entry of the individual X to the terminal apparatus 10 used by an administrator of the building where the entrance gate ETG is provided. . For example, the information processing apparatus 100 may transmit information indicating that the individual X is not authenticated as an appropriate visitor to the terminal apparatus 10 used by a manager of a building where the entrance gate ETG is provided.

  Further, the information processing apparatus 100 may transmit the list information of individuals extracted as similar individuals of the individual X to the terminal device 10 used by the manager of the building where the entrance gate ETG is provided. For example, the information processing apparatus 100 may transmit list information including face photographs of individuals similar to the person X to the terminal device 10 used by a manager of a building where the entrance gate ETG is provided. As a result, the administrator who received the list information including the face image of the similar individual confirms whether the individual X is not included in the similar individual by visually comparing the face image of the similar individual and the individual X. can do.

  As described above, the information processing apparatus 100 extracts similar individuals of the individual X using the graph information GR11 and the index information IND11. For example, the information processing apparatus 100 uses the index information IND11 to determine a starting vector in the graph information GR11 when extracting a similar person of the person X. Then, the information processing apparatus 100 extracts similar individuals of the individual X by searching the graph information GR11 using the determined starting point vector as a starting point. Then, the information processing apparatus 100 performs an individual X determination process using information about similar individuals. As a result, the information processing apparatus 100 can appropriately perform processing for a desired person (individual).

  For example, the information processing apparatus 100 uses the graph information as an individual similar to the individual X even if the individual similar to the individual X (similar individual) appears to have no apparent relationship with the individual X, for example. It is possible to perform extraction, and it is possible to appropriately perform processing for a desired person (individual). For example, there is a method of identifying a specific individual such as whether or not Mr. A by a technique such as deep learning, but when there are a wide variety of elements that affect personal identification, examples of each element Therefore, there is a problem that it is difficult to improve identification accuracy because learning is not possible. For example, there is a method of using a model generated by a learning method such as deep learning, inputting personal information into the model, and identifying whether the individual is suitable for a predetermined purpose from the output score. When there are various elements, since there are few examples of each element, it is difficult to improve the accuracy of the model, and it is difficult to improve the identification accuracy. On the other hand, the information processing apparatus 100 performs a search using graph information in which a plurality of vectors are generated based on the features extracted from each individual, thereby comparing similarity between individuals by comparing individual vectors. It is possible to appropriately determine whether one individual is included in a plurality of individuals. Therefore, the information processing apparatus 100 can appropriately perform processing on a desired person (individual).

[1-4. About use)
In the example of FIG. 1, an individual determination at the time of admission is shown as an example of the determination. However, the individual determination is not limited to the admission, and may be performed for various uses (scenes). For example, the information processing apparatus 100 may determine an individual using the graph information when entering the country. For example, the information processing apparatus 100 may determine whether one individual who is undergoing immigration is included in a plurality of individuals in the graph information.

  In the case of determination at the time of immigration as described above, for example, the personal information may include information such as passport information, travel history, and the like possessed by each individual. For example, the personal information may include information such as a corresponding personal passport image and signature. For example, the personal information may include various behavior information regarding the behavior of the corresponding individual. For example, the personal information may include information indicating a history of when and where the corresponding individual traveled. The personal information may include action information such as searching for a corresponding individual, browsing content, and purchasing. The personal information may be only history information (character information) such as personal travel history.

  For example, as with the graph information GR11, the information processing apparatus 100 uses the entry “immigration”, that is, the immigration information using the graph information obtained by structuring the vector generated using the model M2 whose use scene is at the time of entry. You may extract the similar individual of the person who receives (referred to as "Immigration Y"). Then, the information processing apparatus 100 may determine that the immigration person Y is included in the graph information when the difference between the extracted vector of similar individuals and the vector of the immigration person Y is within a predetermined threshold. That is, the information processing apparatus 100 may determine that the immigration person Y is the similar individual when the difference between the extracted similar individual vector and the vector of the immigration person Y is within a predetermined threshold. For example, the information processing apparatus 100 may determine whether the immigration person Y is included in the graph information GR21 using the graph information GR21 as illustrated in FIG. FIG. 12 is a diagram conceptually showing individual graph information.

  For example, when the information processing apparatus 100 acquires personal information about an immigrant Y for a single individual who enters a predetermined country (immigration person Y), the information processing apparatus 100 is similar to the immigration person Y (similar individual). Information may be extracted from the graph information GR21. For example, the information processing apparatus 100 acquires personal information (individual information YDT) regarding the immigrant Y. For example, the information processing apparatus 100 acquires the graph information GR21 whose entry is the entry from the graph information storage unit 123. For example, the information processing apparatus 100 acquires graph information GR21 in which a plurality of nodes corresponding to each individual are connected according to the similarity of the plurality of individuals. Then, the information processing apparatus 100 generates a vector (vector YVD) from the personal information YDT of the immigrant Y using the model M2 stored in the model information storage unit 124.

  Then, the information processing apparatus 100 determines the starting vector as a node (node YNE) corresponding to the immigrant ET5 in FIG. 12 using the generated vector YVD and index information. Then, the information processing apparatus 100 extracts similar individuals (similar groups) of the immigrant Y by searching the graph information GR21 starting from the node YNE that is the starting point vector. For example, the information processing apparatus 100 searches the graph information GR21 starting from the node YNE, thereby extracting a predetermined number (for example, two) of nodes as similar individuals. In the example of FIG. 12, the information processing apparatus 100 extracts the immigration person ET1 (node NET1) and the immigration person ET5 (node NET5) included in the similar individual range SAR11 as similar individuals.

  Then, the information processing apparatus 100 determines whether the individual is included in a plurality of individuals by comparing the extracted vector of similar individuals with the vector of one individual. In this case, the information processing apparatus 100 compares the vector YVD of the immigration person Y with the vector of the immigration person ET1 (vector VDET1) and the vector of the immigration person ET5 (vector VDET5), so that the immigration person ET1 displays the graph information GR21. It is determined whether it is included in. For example, the information processing apparatus 100 determines that the immigration person Y is the immigration person ET5 when the vector YVD of the immigration person Y and the vector VDET5 of the immigration person ET5 are within a predetermined threshold. That is, the information processing apparatus 100 determines that the immigration person Y is included in the graph information GR21.

  In this case, for example, the information processing apparatus 100 acquires information on the immigrant ET5 from the storage unit 120 (see FIG. 3) or an external device. The information processing apparatus 100 permits the entry of the entry ET5 when the information of the entry ET5 does not include information indicating that the entry ET5 should not allow entry of a terrorist or a criminal. judge. Then, the information processing apparatus 100 authenticates the immigration person Y as an appropriate immigration person.

  Further, the information processing apparatus 100 may provide information regarding the determination result and the authentication result. For example, the information processing apparatus 100 may transmit information indicating that it is determined that the entry ET5 is allowed to enter the terminal device 10 used by the examiner who is performing the immigration examination of the immigration person Y. For example, the information processing apparatus 100 may transmit information indicating that the immigration person Y is authenticated as an appropriate immigration person to the terminal apparatus 10 used by the examiner who is performing immigration examination of the immigration person Y.

  On the other hand, the information processing apparatus 100 does not permit entry of the entry ET5 if the information of the entry ET5 includes information indicating that the entry ET5 should not permit entry of a terrorist or a criminal. judge. Then, the information processing apparatus 100 does not authenticate the immigrant Y as an appropriate immigrant.

  For example, if the graph information GR21 does not include an immigrant who has a vector whose error from the vector YVD of the immigrant Y is within a predetermined threshold, the information processing apparatus 100 determines that the immigrant Y is not included in the graph information GR21. judge. In this case, since the immigration person Y is not included in the graph information GR21, the information processing apparatus 100 determines that entry of the immigration person ET5 is not permitted. Then, the information processing apparatus 100 does not authenticate the immigrant Y as an appropriate immigrant.

  In addition, for example, the information processing apparatus 100 transmits information indicating that the entry ET5 is not permitted to enter the terminal apparatus 10 used by the examiner who is performing the immigration examination of the immigration person Y. Good. For example, the information processing apparatus 100 may transmit information indicating that the immigration person Y is not authenticated as a proper immigration person to the terminal apparatus 10 used by the examiner who is performing immigration examination of the immigration person Y.

  Further, the information processing apparatus 100 may transmit the list information of individuals extracted as similar individuals of the immigrant Y to the terminal device 10 used by the examiner who is performing immigration examination of the immigration person Y. For example, the information processing apparatus 100 may transmit list information including a face photograph of a similar individual of the immigrant Y to the terminal device 10 used by the examiner who is performing immigration examination of the immigration person Y. As a result, the examiner who has received the list information including the face photograph of the similar individual visually compares the face photograph of the similar individual and the immigration person Y, so that the immigration person Y is not included in the similar individual. Can be confirmed.

  In the above example, the case where the information processing apparatus 100 separately performs the process of extracting the similar individual and the determination based on the comparison between the similar individual and the one individual is shown. However, the information processing apparatus 100 extracts the similar individual. Each time the determination is made, a determination may be made by comparing the extracted similar individual with one individual. For example, when the information processing apparatus 100 determines the node NET5 of the immigration person ET5 as a starting node, the information processing apparatus 100 determines whether the error between the vector VDET5 of the immigration person ET5 and the vector YVD of the immigration person Y is within a predetermined threshold. Also good. Then, when the information processing apparatus 100 determines that the error between the vector VDET5 of the immigrant ET5 and the vector YVD of the immigrant Y is within a predetermined threshold, the information processing apparatus 100 ends the search process assuming that the immigrant Y is the immigrant ET5. May be.

  On the other hand, if the information processing apparatus 100 determines that the error between the vector VDET5 of the immigrant ET5 and the vector YVD of the immigrant Y is not within a predetermined threshold, the information processing apparatus 100 continues the search process, extracts the next similar individual, and determines The process may be repeated. When the information processing apparatus 100 determines that the error between the vector VDET5 of the immigration person ET5 and the vector YVD of the immigration person Y is not within a predetermined threshold, the information processing apparatus 100 extracts the immigration person ET1 as a similar individual and performs the same determination process. Also good.

[1-5. Index information)
The index information (index data) illustrated in the example of FIG. 1 is an example, and the information processing apparatus 100 may search for graph information using various index information. For example, the information processing apparatus 100 may generate index data used at the time of search. For example, the information processing apparatus 100 generates a search index for searching for a high-dimensional vector as index data. The high-dimensional vector here may be, for example, a vector of several hundreds to thousands of dimensions, or a vector of more dimensions.

  For example, the information processing apparatus 100 may generate a search index related to a tree structure (tree structure) as shown in FIG. 1 as index data. For example, the information processing apparatus 100 may generate a search index related to a kd tree (k-dimensional tree) as index data. For example, the information processing apparatus 100 may generate a search index related to a VP tree (Vantage-Point tree) as index data.

  Further, for example, the information processing apparatus 100 may generate the index data having another tree structure. For example, the information processing apparatus 100 may generate various index data in which leaves of tree-structured index data are connected to graph data. For example, the information processing apparatus 100 may generate various index data in which the leaf of the tree-structured index data corresponds to a node in the graph data. Further, when performing a search using such index data, the information processing apparatus 100 may search for graph data from a leaf (node) that has arrived by tracing the index data.

  Note that the index data as described above is an example, and the information processing apparatus 100 may generate index data of any data structure as long as it can identify a query in the graph data at high speed. . For example, if the information processing apparatus 100 can identify the node in the graph information corresponding to the query at a high speed, the information processing apparatus 100 generates index data by appropriately using various conventional techniques such as a technique related to binary space division. May be. For example, the information processing apparatus 100 may generate index data having any data structure as long as it is an index that can be used to search for a high-dimensional vector. For example, the information processing apparatus 100 may use information related to a graph-type search index as described in Non-Patent Document 1 as index information. By using the index data and graph data as described above, the information processing apparatus 100 can enable more efficient search regarding a predetermined individual.

[2. Configuration of information processing system]
As illustrated in FIG. 2, the information processing system 1 includes a terminal device 10, an information providing device 50, and an information processing device 100. The terminal device 10, the information providing device 50, and the information processing device 100 are connected via a predetermined network N so as to be communicable by wire or wirelessly. FIG. 2 is a diagram illustrating a configuration example of the information processing system according to the embodiment. Note that the information processing system 1 illustrated in FIG. 2 may include a plurality of terminal devices 10, a plurality of information providing devices 50, and a plurality of information processing devices 100. The information processing system 1 may include an entrance gate EGT. For example, the information processing apparatus 100 and the entrance gate EGT are connected to be communicable by wire or wirelessly.

  The terminal device 10 is an information processing device that is used by various users such as an individual X or an administrator of an entrance gate EGT. The terminal device 10 receives various operations by the user. Hereinafter, the terminal device 10 may be referred to as a user. That is, hereinafter, the user can be read as the terminal device 10. The terminal device 10 described above is realized by, 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. For example, the terminal device 10 may be an information processing device in which a manager uses a predetermined server system. For example, the terminal device 10 collects personal information and transmits the personal information to the information processing device 100.

  The information processing apparatus 100 is an information processing apparatus that determines whether or not one individual among a plurality of individuals is included in the plurality of individuals by searching graph information using the starting point vector as a starting point. For example, the information processing apparatus 100 acquires personal information related to one individual, and determines a starting point vector based on the personal information and information related to a starting point vector that is a starting point for searching graph information.

  The information processing apparatus 100 is an information processing apparatus in which information for providing various information to a user or the like is stored. For example, when the personal information of one individual (hereinafter also referred to as “query information” or “query”) is acquired from the terminal device 10, the information processing apparatus 100 searches for an individual (vector information or the like) similar to the query, The search result is provided to the terminal device 10. In the example of FIG. 1, when the information processing apparatus 100 acquires personal information of one individual from the terminal apparatus 10, the information processing apparatus 100 searches for an individual similar to the one individual and provides the search result to the terminal apparatus 10 as a similar individual. . Further, for example, the data provided to the terminal device 10 by the information processing apparatus 100 may be a personal name or personal personal information itself, or refer to corresponding data such as a URL (Uniform Resource Locator). It may be information.

  The information providing apparatus 50 is an information processing apparatus in which information for providing various information to the information processing apparatus 100 is stored. For example, the information providing device 50 may store personal information collected from various external devices such as a web server. For example, the information providing apparatus 50 is an information processing apparatus that provides the information processing apparatus 100 with various types of information such as graph information, index information, and models.

[3. Configuration of information processing apparatus]
Next, the configuration of 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 according to the embodiment. As illustrated in FIG. 3, the information processing apparatus 100 includes a communication unit 110, a storage unit 120, and a control unit 130. The information processing apparatus 100 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator of the information processing apparatus 100 and a display unit (for example, a liquid crystal display) for displaying various types of information. You may have.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to a network (for example, the network N in FIG. 2) by wire or wireless, and transmits and receives information to and from the terminal device 10 and the information providing device 50.

(Storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. As illustrated in FIG. 3, the storage unit 120 according to the embodiment includes a personal information storage unit 121, an index information storage unit 122, a graph information storage unit 123, and a model information storage unit 124.

(Personal information storage unit 121)
The personal information storage unit 121 according to the embodiment stores various types of information regarding an individual (object). For example, the personal information storage unit 121 stores a personal ID and vector data. In the example of FIG. 4, personal information regarding an individual is stored. FIG. 4 is a diagram illustrating an example of a personal information storage unit according to the embodiment. The personal information storage unit 121 illustrated in FIG. 4 includes items such as “personal ID”, “target”, “personal information”, and “vector information”.

  “Personal ID” indicates identification information for identifying an individual (object). The “target” indicates a specific name or content of the individual identified by the personal ID. In the example of FIG. 4, an individual is indicated by an abstract code such as “person # 1”. However, character information or the like for specifying an individual such as “Mr. A” in parentheses may be included. Good.

  “Personal information” indicates information related to the individual identified by the personal ID. In the example of FIG. 4, the personal information is indicated by an abstract code such as “PDT1”. However, each personal information is attribute information such as age and gender of the individual identified by the personal ID and attributes such as age and gender. It may include information about various individuals such as information, a face, an image of the entire image, sound, and behavior. “Vector information” indicates vector information corresponding to an individual (object) identified by a personal ID. That is, in the example of FIG. 4, vector data (vector information) corresponding to an object is registered in association with a personal ID for identifying the individual (object).

  For example, in the example of FIG. 4, the individual (object) identified by the personal ID “PP1” is associated with multidimensional (N-dimensional) vector information of “10, 24, 54, 2. Indicates. For example, for the individual # 1, multi-dimensional (N-dimensional) vector information “10, 24, 54, 2...” Indicating the characteristics of the individual # 1 is extracted from the personal information PDT1 by the model M1 or the like. It shows that.

  The personal information storage unit 121 is not limited to the above, and may store various types of information according to the purpose.

(Index information storage unit 122)
The index information storage unit 122 according to the embodiment stores various types of information related to the index. FIG. 5 is a diagram illustrating an example of the index information storage unit according to the embodiment. Specifically, in the example of FIG. 5, the index information storage unit 122 indicates tree structure index information. In the example of FIG. 5, the index information storage unit 122 includes items such as “root hierarchy”, “first hierarchy”, “second hierarchy”, “third hierarchy”, and the like. In addition to “first hierarchy” to “third hierarchy”, “fourth hierarchy”, “fifth hierarchy”, “sixth hierarchy”, and the like may be included depending on the number of index hierarchies.

  The “root hierarchy” indicates a hierarchy of the root (highest level) that is a starting point for determining an origin node using an index. The “first hierarchy” stores information for identifying (specifying) nodes (nodes or vectors in graph information) belonging to the first hierarchy of the index. The node stored in the “first hierarchy” is a node corresponding to the hierarchy directly connected to the root of the index.

  The “second hierarchy” stores information for identifying (specifying) nodes (nodes or vectors in graph information) belonging to the second hierarchy of the index. The node stored in the “second hierarchy” is a node corresponding to the hierarchy directly below the node of the first hierarchy. The “third hierarchy” stores information for identifying (specifying) a node (a node or a vector in graph information) belonging to the third hierarchy of the index. The node stored in the “third hierarchy” is a node corresponding to the hierarchy directly below the second hierarchy node.

  For example, in the example shown in FIG. 5, the index information storage unit 122 stores information corresponding to the index information IND11 in FIG. For example, the index information storage unit 122 indicates that the first layer nodes are nodes VT1 to VT3 and the like. The numerical value in parentheses below each node indicates a vector value corresponding to each node.

  For example, the index information storage unit 122 indicates that the nodes in the second hierarchy immediately below the node VT2 are the nodes VT2-1 to VT2-4. Further, for example, the index information storage unit 122 indicates that the node in the third hierarchy immediately below the node VT2-2 is a node (vector) in the graph information GR11 of the node N35, the node N451, and the node N693.

  The index information storage unit 122 is not limited to the above, and may store various information according to the purpose.

(Graph information storage unit 123)
The graph information storage unit 123 according to the embodiment stores various types of information regarding the graph information. FIG. 6 is a diagram illustrating an example of the graph information storage unit according to the embodiment. In the example of FIG. 6, the graph information storage unit 123 includes items such as “node ID”, “personal ID”, and “edge information”. The “edge information” includes information such as “edge ID” and “reference destination”.

  “Node ID” indicates identification information for identifying each node (individual) in the graph data. “Personal ID” indicates identification information for identifying an individual (object).

  “Edge information” indicates information related to an edge connected to the corresponding node. In the example of FIG. 6, “edge information” indicates a case where the edge is a directed edge, and indicates information regarding an output edge output from the corresponding node. “Edge ID” indicates identification information for identifying an edge connecting nodes. “Reference destination” indicates information indicating a reference destination (node) connected by an edge. That is, in the example of FIG. 6, with respect to a node ID for identifying a node, information for identifying an object (person) corresponding to the node and a reference destination to which a directed edge (output edge) from the node is linked ( Node) is registered in association with each other.

  For example, in the example of FIG. 6, the node (vector) identified by the node ID “N1” corresponds to the individual (object) identified by the personal ID “PP1”. The node identified by the node ID “N1” indicates that the edge identified by the edge ID “E11” is connected to the node (vector) identified by the node ID “N25”. That is, in the example of FIG. 6, the node (vector) identified by the node ID “N1” can be traced to the node (vector) identified by the node ID “N25”.

  The graph information storage unit 123 is not limited to the above, and may store various types of information according to the purpose. For example, the graph information storage unit 123 may store the length of an edge connecting each node (vector). That is, the graph information storage unit 123 may store information indicating the distance between each node (vector).

(Model information storage unit 124)
The model information storage unit 124 according to the embodiment stores information about the model. For example, the model information storage unit 124 stores model information (model data) generated by the generation process. FIG. 7 is a diagram illustrating an example of a model information storage unit according to the embodiment. The model information storage unit 124 illustrated in FIG. 7 includes items such as “model ID”, “use”, and “model data”. In FIG. 7, only the models M1 and M2 are illustrated, but a large number of model information such as M21 and M22 may be stored according to each application (target of prediction).

  “Model ID” indicates identification information for identifying a model. For example, the model identified by the model ID “M1” corresponds to the model M1 illustrated in the example of FIG. “Use” indicates the use of the corresponding model. “Model data” indicates data of a corresponding model associated with the model data. For example, “model data” includes information including nodes in each layer, functions adopted by the nodes, connection relationships between the nodes, and connection coefficients set for connections between the nodes.

  For example, in the example shown in FIG. 7, the model (model M1) identified by the model ID “M1” has a use of “feature extraction (entrance)” and is used for feature extraction from input personal information. It shows that. The model data of the model M1 is model data MDT1.

  The model M1 (model data MDT1) includes an input layer to which personal information of an individual is input, an output layer, and a first element belonging to any layer from the input layer to the output layer other than the output layer. A first element and a second element whose value is calculated based on the weight of the first element, and for each piece of information belonging to each layer other than the output layer for the personal information input to the input layer, the first element This is a model for causing a computer to function so that information similar to information input to the input layer is output from the output layer by performing calculations based on the first element and the weight of the first element as elements.

  Further, it is assumed that the models M1, M2, etc. are realized by a neural network having one or a plurality of intermediate layers, such as DNN (Deep Neural Network). In this case, for example, the first element included in the models M1 and M2 corresponds to any node of the input layer or the intermediate layer. The second element corresponds to the next node, which is a node to which a value is transmitted from the node corresponding to the first element. The weight of the first element corresponds to a connection coefficient that is a weight considered for a value transmitted from a node corresponding to the first element to a node corresponding to the second element.

  Here, it is assumed that the models M21, M22 and the like are realized by a regression model represented by “y = a1 * x1 + a2 * x2 +... + Ai * xi”. In this case, for example, the first elements included in the models M21 and M22 correspond to input data (xi) such as x1 and x2. The weight of the first element corresponds to the coefficient ai corresponding to xi. Here, the regression model can be regarded as a simple perceptron having an input layer and an output layer. When each model is regarded as a simple perceptron, the first element can correspond to any node of the input layer, and the second element can be regarded as a node of the output layer.

  The model information storage unit 124 is not limited to the above, and may store various model information according to the purpose.

(Control unit 130)
Returning to the description of FIG. 3, the control unit 130 is a controller, and is stored in a storage device inside the information processing apparatus 100 by, for example, a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). Various programs (corresponding to an example of an information processing program) are executed by using the RAM as a work area. The control unit 130 is a controller, and is realized by an integrated circuit such as an application specific integrated circuit (ASIC) or a field programmable gate array (FPGA). The control unit 130 performs an information process according to the models M1, M2, and the like stored in the model information storage unit 124. A first element belonging to any layer other than the output layer, and a second element whose value is calculated based on the first element and the weight of the first element, and is input to the input layer The same information as the information input to the input layer by performing an operation based on the first element and the weight of the first element with each element belonging to each layer other than the output layer as the first element Is output from the output layer.

  As illustrated in FIG. 3, the control unit 130 includes an acquisition unit 131, a generation unit 132, a determination unit 133, a search unit 134, and a provision unit 135. Information processing functions and operations described below Realize or execute. 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 the information processing described below is performed.

(Acquisition part 131)
The acquisition unit 131 acquires various types of information. For example, the acquisition unit 131 acquires various types of information from the storage unit 120. For example, the acquisition unit 131 acquires various types of information from the personal information storage unit 121, the index information storage unit 122, the graph information storage unit 123, the model information storage unit 124, and the like. The acquisition unit 131 acquires various types of information from an external information processing apparatus. The acquisition unit 131 acquires various types of information from the terminal device 10 and the information providing device 50. The acquisition unit 131 acquires various types of information from the entrance gate EGT.

  The acquisition unit 131 acquires graph information in which a plurality of nodes corresponding to each of a plurality of individuals are linked according to the similarity of the plurality of individuals, and personal information regarding one individual. The acquisition unit 131 acquires graph information in which a plurality of vectors indicating the characteristics of a plurality of individuals are connected according to similarity.

  The acquisition unit 131 acquires graph information in which a plurality of vectors whose elements are feature amounts extracted from each of a plurality of individuals using a predetermined model are connected according to similarity. The acquisition unit 131 inputs information about a plurality of individuals into a predetermined model, and thereby graph information in which a plurality of vectors each having the feature amount of each of the plurality of individuals extracted are connected according to similarity. To get. The acquisition unit 131 acquires personal information related to one individual from a terminal device having the personal information of one individual.

  For example, the acquisition unit 131 acquires a plurality of nodes (vectors) that are individuals for data search. For example, the acquisition unit 131 acquires a directed edge group including a plurality of nodes and a plurality of directed edges that connect each of the plurality of nodes.

  For example, the acquisition unit 131 acquires graph information (graph data) from an external information processing apparatus. For example, the acquisition unit 131 acquires graph information from the graph information storage unit 123. For example, the acquisition unit 131 acquires graph information. In the example of FIG. 1, the acquisition unit 131 acquires graph information GR11.

  For example, the acquisition unit 131 acquires index information (index data) from an external information processing apparatus. For example, the acquisition unit 131 acquires index information from the index information storage unit 122. For example, the acquisition unit 131 acquires tree structure type index information. In the example of FIG. 1, the acquisition unit 131 acquires index information IND11.

  Moreover, the acquisition part 131 acquires the personal information regarding one individual from the entrance gate EGT. For example, the acquisition unit 131 acquires personal information of one individual as a search query. For example, the acquisition unit 131 acquires a search query related to an individual. The acquisition unit 131 acquires personal information PDT11 related to the individual X from the entrance gate EGT.

  Moreover, the acquisition part 131 may acquire the personal information regarding one individual from the terminal device 10 used by the user. For example, the acquisition unit 131 may acquire personal information of one individual as a search query. For example, the acquisition unit 131 may acquire a search query related to an individual. The acquisition unit 131 may acquire personal information PDT11 regarding the individual X from the terminal device 10 used by a predetermined user.

  For example, the acquisition unit 131 acquires personal information regarding one individual. For example, the acquisition unit 131 acquires personal information PDT11 related to the individual X from the terminal device 10. For example, the acquisition unit 131 acquires graph information GR11 related to an individual from the graph information storage unit 123. Further, for example, the acquiring unit 131 acquires index information IND11 used for determining a node (starting point vector) serving as a starting point of search in the graph information GR11 from the index information storing unit 122 (see FIG. 5).

(Generator 132)
The generation unit 132 generates various types of information. For example, the generation unit 132 uses the learning data (personal information) stored in the personal information storage unit 121 to generate a model as shown in the model information storage unit 124. For example, the generation unit 132 generates a model (auto encoder) that outputs information similar to the input personal information based on the learning data acquired by the acquisition unit 131. For example, the generation unit 132 generates a model (auto encoder) that outputs the same information as the input personal information, using the input personal information itself as correct information.

  For example, the generation unit 132 generates a model M1 and the like, and stores the generated model M1 and the like in the model information storage unit 124. Note that the generation unit 132 may generate the model M1 using any learning algorithm. For example, the generation unit 132 generates the model M1 using a learning algorithm such as a neural network. As an example, when the generation unit 132 generates a model M1 or the like using a neural network, the model M1 or the like includes an input layer including one or more neurons, an intermediate layer including one or more neurons, and one or more neurons. Including an output layer.

  The generation unit 132 includes an input layer to which personal information of an individual is input, an output layer, a first element belonging to any layer other than the output layer and from the input layer to the output layer, and a first element And a second element whose value is calculated based on the weight of the first element, and with respect to personal information input to the input layer, each element belonging to each layer other than the output layer is defined as a first element. By performing an operation based on the weight of one element and the first element, a model that outputs information similar to information input to the input layer from the output layer is generated.

  For example, the generation unit 132 generates a model based on the learning data. For example, the generation unit 132 generates a model based on the learning data. For example, the generation unit 132 generates a model by performing learning using the personal information PDT1, PDT2 and the like in the personal information storage unit 121 as learning data (teacher data).

  For example, when the personal information PDT1 is input, the generation unit 132 performs a learning process so that the model M1 outputs the same information as the personal information PDT1. For example, when the personal information PDT2 is input, the generation unit 132 performs a learning process so that the model M1 outputs the same information as the personal information PDT2.

  The generation unit 132 is not limited to the model M1 as an auto encoder, and may generate a model M21 corresponding to an individual (entrance), an M22 corresponding to an individual (entrance), and the like using various learning algorithms. For example, the generation unit 132 generates models M21, M22, and the like using a learning algorithm such as a neural network, a support vector machine (SVM), clustering, and reinforcement learning. As an example, when the generation unit 132 generates models M21, M22, and the like using a neural network, the models M21, M22, and the like include an input layer including one or more neurons, an intermediate layer including one or more neurons, and one And an output layer including the above neurons. Note that the information processing apparatus 100 may not include the generation unit 132 when acquiring a model from another external apparatus such as the information providing apparatus 50.

  In the example of FIG. 1, the generation unit 132 generates an N-dimensional vector from the personal information of each individual using a model that extracts the characteristics of the personal information. The generation unit 132 generates a vector from the personal information of each individual using the model M1 shown in the model information storage unit 124 (FIG. 7).

  Further, the generation unit 132 generates a vector used for searching for graph information from personal information corresponding to one individual. In the example of FIG. 1, the generation unit 132 generates a vector corresponding to the person X by processing as shown in the processing group PS11. The generation unit 132 inputs the personal information PDT11 related to the individual X into the model M1. Specifically, the generation unit 132 inputs, to the model M1, personal information PDT11 including attribute information such as the age and sex of the individual X, images of the face and the entire image, and information such as voice and behavior. Then, the generation unit 132 generates a vector using information in the model M1 after the input of the personal information PDT11. For example, the generation unit 132 generates vector data using each element in the model M1 to which the personal information PDT11 is input.

  In the example of FIG. 1, the generation unit 132 generates a vector VD11 using the value of each element in the model M1 to which the personal information PDT11 is input. For example, the generation unit 132 uses the value VE1 (see FIG. 10) corresponding to the neuron NL1 of the model M1 and the value VE2 (see FIG. 10) corresponding to the neuron NL2 when the personal information PDT11 of the individual X is input. To generate a vector. For example, when the personal information PDT11 of the person X is input, the generation unit 132 may extract the value VE1 corresponding to the calculated neuron NL1 as the first dimension element of the vector VD11. Further, for example, when personal personal information is input, the generation unit 132 generates the vector VD11 using the calculated value VE2 corresponding to the neuron NL2 as a second-dimensional element of the vector VD11. In the example of FIG. 1, the generation unit 132 generates a vector VD11 in which the first dimension element is “35” and the second dimension element is “63”.

(Determining unit 133)
The determination unit 133 determines various types of information. The determining unit 133 determines the starting node based on the index information used for determining the starting node. For example, the determination unit 133 determines the starting point vector based on the personal information acquired by the acquiring unit 131 and information on the starting point vector that is a starting point for searching the graph information. For example, the determination unit 133 determines the starting point vector based on the personal information and information that serves as a reference for determining the starting point vector for the search of the graph information. Further, the determination unit 133 determines a starting point vector based on the index information used for determining the starting point vector. Also, the determination unit 133 determines a starting point vector based on the tree structure type index information.

  In the example of FIG. 1, the determination unit 133 uses the index information IND11 in order to determine (specify) the starting point vector corresponding to one individual (query). For example, the determination unit 133 uses the index information IND11 in order to determine (specify) the starting point vector corresponding to the vector VD11 of the person X. The determination unit 133 determines a starting point vector in the graph information GR11 using the vector VD11 and the index information IND11.

  For example, the determination unit 133 determines a starting vector in the graph information GR11 using tree structure type index information as indicated by the index information IND11 in FIG. In the example of FIG. 1, after the determination unit 133 generates the vector VD11, the determination unit 133 traces the index information IND11 from the top to the bottom, thereby specifying the starting point vector that is a neighborhood candidate of the index information IND11, thereby efficiently searching. A starting vector corresponding to the query (one individual) is determined.

  For example, the determination unit 133 determines the starting vector corresponding to the vector VD11 by tracing the index information IND11 from the root RT to the leaf node (the node (vector) in the graph information GR11). In the example of FIG. 1, the determination unit 133 determines the node N451 as a starting vector by tracing the index information IND11 from the route RT to the node N451.

(Search unit 134)
The search unit 134 searches various information. For example, the search unit 134 searches for various types of information using the information acquired by the acquisition unit 131. For example, the search unit 134 extracts various information. For example, the search unit 134 extracts various types of information using the information acquired by the acquisition unit 131. For example, the search unit 134 performs various determination processes. For example, the search unit 134 determines various types of information using the information acquired by the acquisition unit 131. For example, the search unit 134 searches for various information stored in the storage unit 120. For example, the acquisition unit 131 searches various information stored in the personal information storage unit 121, the index information storage unit 122, the graph information storage unit 123, the model information storage unit 124, and the like. For example, the search unit 134 performs calculation processing using various types of information. For example, the search unit 134 calculates the distance between vectors using information about vectors. For example, the search unit 134 may use information on the length (distance) of the edges connecting the nodes (vectors) stored in the graph information storage unit 123, or may calculate each node ( Information on the length (distance) of the edges connecting the vectors) may be calculated, and the information on the calculated length (distance) may be used.

  The search unit 134 searches for graph information starting from a starting node that is a starting point for searching for graph information determined based on a predetermined criterion among a plurality of nodes of the graph information acquired by the acquiring unit 131. Thus, a similar individual that is an individual similar to one individual is extracted from the plurality of individuals. The search unit 134 extracts similar individuals using the starting point node determined by the determining unit 133 as a starting point. The search unit 134 extracts an individual similar to one individual from the plurality of individuals as a similar individual.

  The search unit 134 searches the graph information using a starting point vector as a starting point for searching for the graph information determined based on a predetermined criterion among a plurality of vectors of the graph information acquired by the acquiring unit 131. A similar individual (similar individual) that is an individual similar to one individual is extracted from the plurality of individuals. The search unit 134 extracts various information. For example, the search unit 134 searches for graph information using the starting point vector determined by the determining unit 133 as a starting point, thereby extracting a similar individual that is an individual similar to one individual among the plurality of individuals.

  The search unit 134 searches for graph information starting from a starting node that is a starting point for searching for graph information determined based on a predetermined criterion among a plurality of nodes of the graph information acquired by the acquiring unit 131. Thus, it is determined whether one individual is included in a plurality of individuals. The search unit 134 determines whether one individual is included in a plurality of individuals, starting from the starting node determined by the determining unit 133.

  In the example of FIG. 1, the search unit 134 searches for an individual similar to the individual X. For example, the search unit 134 extracts similar individuals of the person X by searching the graph information GR11. The search unit 134 extracts nodes located in the vicinity of the node N451 as similar individuals. For example, the search unit 134 extracts nodes that are close to the node N451 as similar individuals. For example, the search unit 134 extracts nodes that can be reached from the node N451 as similar individuals by tracing the edges starting from the node N451. For example, the search unit 134 extracts a predetermined number (for example, 2 or 10) of nodes as similar individuals. For example, the search unit 134 extracts similar individuals of the person X by a search process as shown in FIG. In the example of FIG. 1, the search unit 134 extracts the node N451 and the node N35 as similar individuals by searching the graph information GR11 starting from the node N451.

  In the example of FIG. 1, the search unit 134 determines whether an individual is included in a plurality of individuals by comparing a vector of one individual and a vector of similar individuals. The search unit 134 compares the vector VD11 of the person X with the vector VD451 of the node N451 (person # 451) and the vector VD35 of the node N35 (person # 35) as shown in the target list SPL. The search unit 134 compares the vectors and performs a determination process.

  For example, the search unit 134 determines whether the individual X is included in a plurality of individuals in the graph information GR11 by comparing each vector. For example, the search unit 134 determines whether an error between the vector VD11 of the individual X and the vector VD451 of the node N451 or the vector VD35 of the node N35 is within an predetermined threshold. For example, the search unit 134 determines that a vector node (individual) whose error with the vector VD11 of the individual X is within a predetermined threshold is the individual X. The search unit 134 determines that the person X is included in a plurality of individuals in the graph information GR11 when there is a vector whose error with the vector VD11 of the person X is within a predetermined threshold.

  In the example of FIG. 1, the search unit 134 determines that the vector VD11 of the individual X and the vector VD35 of the node N35 are errors within a predetermined threshold as shown in the determination list DRS, and the individual X is the individual # 35. In this case, the search unit 134 determines that the individual X is permitted to enter the building where the entrance gate ETG is provided. Then, the search unit 134 authenticates the individual X as an appropriate visitor.

(Providing unit 135)
The providing unit 135 provides various types of information. For example, the providing unit 135 transmits various types of information to the terminal device 10 and the information providing device 50. For example, the providing unit 135 distributes various types of information to the terminal device 10 and the information providing device 50. For example, the providing unit 135 provides various types of information to the terminal device 10 and the information providing device 50. The providing unit 135 provides a predetermined service based on the similar individual extracted by the search unit 134. The providing unit 135 provides an information providing service related to similar individuals. The providing unit 135 provides information related to similar individuals to the terminal device 10.

  The providing unit 135 provides a predetermined service based on the determination result by the search unit 134. The providing unit 135 provides an information providing service regarding the determination result. The providing unit 135 provides information related to the determination result to the terminal device 10. The providing unit 135 provides an authentication service based on the determination result. The providing unit 135 provides an authentication service for authenticating one individual.

  For example, the providing unit 135 provides an object ID corresponding to the query as a search result. For example, the providing unit 135 provides the object ID selected by the search unit 134 to the information providing apparatus 50. The providing unit 135 provides the information providing apparatus 50 with the object ID selected by the search unit 134 as information indicating a vector corresponding to the query. The providing unit 135 may provide the model generated by the generating unit 132 to an external information processing apparatus.

  In the example of FIG. 1, for example, the providing unit 135 requests the entrance gate EGT to open the gate based on the determination result that the person X is the person # 35. For example, the providing unit 135 transmits, to the entrance gate EGT, information that instructs the entrance gate EGT to open the gate, assuming that the entrance authentication of the individual X who is the visitor is OK.

  In the example of FIG. 1, for example, the providing unit 135 may provide information on similar individuals extracted by the search unit 134. For example, the providing unit 135 sends information indicating that the individual # 451 corresponding to the node N451 and the individual # 35 corresponding to the node N35 are similar individuals of the individual X, the terminal device 10 of the manager of the entrance gate EGT, You may provide to the terminal device 10 grade | etc., Which a visitor (individual X) uses.

[4. Information processing flow)
Next, the procedure of information processing by the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 8 is a flowchart illustrating an example of information processing according to the embodiment.

  As shown in FIG. 8, the information processing apparatus 100 performs personal information regarding one individual (step S101). In the example of FIG. 1, the information processing apparatus 100 acquires personal information PDT11 related to the individual X from the terminal device 10.

  The information processing apparatus 100 acquires graph information regarding a plurality of individuals (step S102). For example, the information processing apparatus 100 acquires graph information GR11 related to an individual from the graph information storage unit 123.

  Then, the information processing apparatus 100 generates a vector from personal information regarding one individual using the model (step S103). In the example of FIG. 1, the information processing apparatus 100 generates a vector VD11 from the personal information PDT11 using the model M1 stored in the model information storage unit 124.

  Then, the information processing apparatus 100 determines a starting point vector using the generated vector and index information (step S104). In the example of FIG. 1, the information processing apparatus 100 determines the starting vector as the node N451 using the vector VD11 and the index information IND11 stored in the index information storage unit 122.

  Then, the information processing apparatus 100 searches the graph information to determine whether the individual is included in a plurality of individuals (step S105). For example, the information processing apparatus 100 searches for graph information and extracts individuals similar to one individual as similar individuals. Then, the information processing apparatus 100 determines whether the individual is included in a plurality of individuals by comparing the vector of one individual with the vector of a similar individual. In the example of FIG. 1, the information processing apparatus 100 extracts the node N451 and the node N35 as similar individuals by searching the graph information GR11 with the node N451 as a starting point. Then, the information processing apparatus 100 determines whether the individual is included in a plurality of individuals by comparing the vector VD11 of the individual X with the vector VD451 of the node N451 and the vector VD35 of the node N35. For example, the information processing apparatus 100 determines that the vector VD11 of the person X and the vector VD35 of the node N35 are within an error within a predetermined threshold, determines that the person X is the person # 35, and the person X is a graph. It is determined that the information is included in a plurality of individuals in the information GR11.

  Then, the information processing apparatus 100 provides a service based on the determination result (step S106). In the example of FIG. 1, the information processing apparatus 100 requests the entrance gate EGT to open the gate based on the determination result that the person X is the person # 35.

[5. Generation process flow)
Next, a generation process procedure performed by the information processing system 1 according to the embodiment will be described with reference to FIG. FIG. 9 is a flowchart illustrating an example of the generation process according to the embodiment.

  As shown in FIG. 9, the information processing apparatus 100 acquires learning data (step S201). For example, the information processing apparatus 100 acquires learning data from the personal information storage unit 121. For example, the information processing apparatus 100 acquires personal information PDT1, PDT2, and the like as learning data from the personal information storage unit 121.

  Thereafter, the information processing apparatus 100 generates a model based on the learning data (step S202). For example, the information processing apparatus 100 generates a model M1 from the personal information storage unit 121 using learning data. For example, the information processing apparatus 100 generates the model M1 so that information (personal information) similar to information (personal information) input to the input layer is output from the output layer. For example, the information processing apparatus 100 generates a model M1 as an auto encoder that receives personal information of an individual.

[6. Search example)
Here, an example of the search using the graph information described above is shown. The search using the graph information (graph data) is not limited to the following, and may be performed by various procedures. This point will be described using FIG. 11 as an example. FIG. 11 is a flowchart illustrating an example of a search process using graph data (graph information). The search process described below is performed by the search unit 134 of the information processing apparatus 100, for example. Further, the object described below may be read as a vector or a node. In the following description, it is assumed that the information processing apparatus 100 performs a search process, but the search process may be performed by another apparatus. For example, the information processing apparatus 100 uses vector data generated from personal information of one individual as a search query. For example, the information processing apparatus 100 searches for graph data using a starting point vector determined based on vector data generated from personal information of one individual and index information as a starting point. In the example of FIG. 1, the information processing apparatus 100 searches the graph information GR11 using a node N451 that is a starting vector determined based on the vector VD11 of the individual X and the index information IND11.

  Here, the neighboring object set N (G, y) is a set of neighboring objects that are related by the edge given to the node y. “G” may be predetermined graph data (eg, graph information GR11). For example, the information processing apparatus 100 performs k neighborhood search processing.

  For example, the information processing apparatus 100 sets the radius r of the hypersphere to ∞ (infinite) (step S300), and extracts the subset S from the existing object set (step S301). For example, the information processing apparatus 100 may extract the object (node) selected as the root node (starting vector) as the subset S. In the example of FIG. 1, the information processing apparatus 100 may extract the starting point vector such as the node N451 as a subset S. Further, for example, a hypersphere is a virtual sphere that indicates a search range. It should be noted that the objects included in the object set S extracted in step S301 are also included in the initial set of the search result object set R at the same time.

  Next, the information processing apparatus 100 extracts, from the objects included in the object set S, an object having the shortest distance from the object y when the search query object is y, and sets it as an object s (step S302). In the example of FIG. 1, the information processing apparatus 100 extracts an object having the shortest distance from the vector VD11 that is a search query object among the objects included in the object set S and sets it as an object s. For example, the information processing apparatus 100 extracts the node N451 having the shortest distance from the vector VD11 from the objects included in the object set S and sets it as the object s. For example, when only the object (node) selected as the root node (starting vector) is an element of the object set S, the information processing apparatus 100 extracts the root node (starting vector) as the object s as a result. . Next, the information processing apparatus 100 excludes the object s from the object set S (step S303).

  Next, the information processing apparatus 100 determines whether or not the distance d (s, y) between the object s and the object y exceeds r (1 + ε) (step S304). Here, ε is an expansion element, and r (1 + ε) is a value indicating the radius of the search range (search only for nodes within this range. The accuracy can be increased by making it larger than the search range). is there. When the distance d (s, y) between the object s and the object y exceeds r (1 + ε) (step S304: Yes), the information processing apparatus 100 outputs the object set R as a neighborhood object set of the object y (step S304). S305), the process is terminated.

  When the distance d (s, y) between the object s and the search query object y does not exceed r (1 + ε) (step S304: No), the information processing apparatus 100 determines the neighborhood object set N (G, s) of the object s. One object that is not included in the object set C is selected from the objects that are the elements of the selected element u, and the selected object u is stored in the object set C (step S306). The object set C is provided for convenience in order to avoid duplicate search, and is set to an empty set at the start of processing.

  Next, the information processing apparatus 100 determines whether or not the distance d (u, y) between the object u and the object y is equal to or less than r (1 + ε) (step S307). When the distance d (u, y) between the object u and the object y is equal to or less than r (1 + ε) (step S307: Yes), the information processing apparatus 100 adds the object u to the object set S (step S308). When the distance d (u, y) between the object u and the object y is not equal to or less than r (1 + ε) (step S307: No), the information processing apparatus 100 performs the determination (processing) in step S309.

  Next, the information processing apparatus 100 determines whether the distance d (u, y) between the object u and the object y is equal to or smaller than r (step S309). When the distance d (u, y) between the object u and the object y exceeds r (step S309: No), the information processing apparatus 100 performs the determination (processing) in step S315. If the distance d (u, y) between the object u and the object y is not equal to or less than r (step S309: No), the information processing apparatus 100 performs the determination (processing) in step S315.

  When the distance d (u, y) between the object u and the object y is equal to or less than r (step S309: Yes), the information processing apparatus 100 adds the object u to the object set R (step S310). Then, the information processing apparatus 100 determines whether or not the number of objects included in the object set R exceeds ks (step S311). The predetermined number ks is a natural number that is arbitrarily determined. For example, various settings such as ks = 2 and ks = 10 may be used. When the number of objects included in the object set R does not exceed ks (step S311: No), the information processing apparatus 100 performs determination (processing) in step S313.

  When the number of objects included in the object set R exceeds ks (step S311: Yes), the information processing apparatus 100 determines an object having the longest (far) object from the object y among the objects included in the object set R. Exclude from the object set R (step S312).

  Next, the information processing apparatus 100 determines whether or not the number of objects included in the object set R matches ks (step S313). When the number of objects included in the object set R does not match ks (step S313: No), the information processing apparatus 100 performs the determination (processing) of step S315. When the number of objects included in the object set R matches ks (step S313: Yes), the information processing apparatus 100 has the longest (far) distance from the object y among the objects included in the object set R. The distance between the object and the object y is set to a new r (step S314).

  Then, the information processing apparatus 100 determines whether all objects have been selected from the objects that are elements of the neighboring object set N (G, s) of the object s and stored in the object set C (step S315). . When all the objects have not been selected and stored in the object set C from the objects that are elements of the neighboring object set N (G, s) of the object s (step S315: No), the information processing apparatus 100 performs step S306. Return to and repeat the process.

  When all the objects are selected from the objects that are elements of the neighboring object set N (G, s) of the object s and stored in the object set C (step S315: Yes), the information processing apparatus 100 determines that the object set S It is determined whether or not is an empty set (step S316). When the object set S is not an empty set (step S316: No), the information processing apparatus 100 returns to step S302 and repeats the process. If the object set S is an empty set (step S316: Yes), the information processing apparatus 100 outputs the object set R and ends the process (step S317). For example, the information processing apparatus 100 determines whether the input object y is included in the predetermined graph data based on the search result corresponding to the search query (input object y) for the object (node) included in the object set R. To do. In the example of FIG. 1, the information processing apparatus 100 assumes that, among the nodes N451 and N35 included in the object set R, the vector of the node N35 is an error within a predetermined range from the search query (person X vector VD11). , It is determined that the individual X is included in the graph information RG11. That is, the information processing apparatus 100 determines that the person X is the person # 35 corresponding to the node N35. For example, the information processing apparatus 100 authenticates that the person X is a user who may open the entrance gate ETG based on the determination result that the person X is the person # 35. Then, the information processing apparatus 100 requests the entrance gate EGT to open the gate.

[7. effect〕
As described above, the information processing apparatus 100 according to the embodiment includes the acquisition unit 131 and the search unit 134. The acquisition unit 131 acquires graph information in which a plurality of nodes corresponding to each of a plurality of individuals are linked according to the similarity of the plurality of individuals, and personal information regarding one individual. The search unit 134 searches for graph information starting from a starting node that is a starting point for searching for graph information determined based on a predetermined criterion among a plurality of nodes of the graph information acquired by the acquiring unit 131. Thus, it is determined whether one individual is included in a plurality of individuals.

  As described above, the information processing apparatus 100 according to the embodiment searches the graph information using the starting point vector as a starting point, and determines whether one of the plurality of individuals is included in the plurality of individuals. It is possible to appropriately perform processing for a person (individual).

  Further, the information processing apparatus 100 according to the embodiment includes a determination unit 133. The determining unit 133 determines the starting node based on the index information used for determining the starting node. The search unit 134 determines whether one individual is included in a plurality of individuals, starting from the starting node determined by the determining unit 133.

  As described above, the information processing apparatus 100 according to the embodiment can appropriately perform processing on a desired person (individual) by determining the starting point vector based on the index information used for determining the starting point vector. can do.

  In the information processing apparatus 100 according to the embodiment, the determination unit 133 determines a starting point vector based on the tree structure type index information.

  As described above, the information processing apparatus 100 according to the embodiment can appropriately perform processing on a desired person (individual) by determining the starting point vector based on the tree structure type index information. Can do.

  Moreover, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires graph information in which a plurality of vectors indicating features of a plurality of individuals are connected according to similarity.

  As described above, the information processing apparatus 100 according to the embodiment acquires graph information in which a plurality of vectors indicating the characteristics of a plurality of individuals are connected according to similarity, thereby obtaining a desired person (individual). It is possible to perform processing appropriately.

  Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 connects a plurality of vectors whose elements are feature quantities extracted from each of a plurality of individuals using a predetermined model according to similarity. Get the graph information.

  As described above, the information processing apparatus 100 according to the embodiment includes graph information in which a plurality of vectors each having a feature amount extracted from each of a plurality of individuals using a predetermined model are connected according to similarity. By acquiring, it is possible to appropriately perform processing for a desired person (individual).

  Further, in the information processing apparatus 100 according to the embodiment, the acquisition unit 131 inputs a plurality of vectors related to a plurality of individuals by inputting information related to the plurality of individuals into a predetermined model. However, the graph information connected according to the similarity is acquired.

  As described above, the information processing apparatus 100 according to the embodiment inputs information related to a plurality of individuals to a predetermined model, so that a plurality of vectors whose elements are characteristic amounts of the plurality of individuals extracted are similar to each other. By acquiring graph information linked according to sex, it is possible to appropriately perform processing for a desired person (individual).

  In addition, the information processing apparatus 100 according to the embodiment includes a providing unit 135. The providing unit 135 provides a predetermined service based on the determination result by the search unit 134.

  As described above, the information processing apparatus 100 according to the embodiment provides a predetermined service based on the determination result of whether one individual is included in a plurality of individuals, thereby providing a service related to a desired person (individual). Can be provided appropriately.

  In the information processing apparatus 100 according to the embodiment, the providing unit 135 provides an information providing service regarding the determination result.

  As described above, the information processing apparatus 100 according to the embodiment can appropriately provide a service related to a desired person (individual) by providing an information providing service related to the determination result.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires personal information related to one individual from a terminal device having the personal information of the one individual. The providing unit 135 provides information related to the determination result to the terminal device 10.

  In this way, the information processing apparatus 100 according to the embodiment acquires personal information about one individual from the terminal device 10 used by the individual (user), and provides the terminal device 10 with information about the determination result. Services relating to individuals (for example, similar individuals) can be appropriately provided.

  In the information processing apparatus 100 according to the embodiment, the providing unit 135 provides an authentication service based on the determination result.

  As described above, the information processing apparatus 100 according to the embodiment can appropriately provide a service related to a desired person (individual) by providing an authentication service based on the determination result.

  In the information processing apparatus 100 according to the embodiment, the acquisition unit 131 acquires personal information related to one individual from a terminal device having the personal information of the one individual. The providing unit 135 provides an authentication service for authenticating one individual.

  As described above, the information processing apparatus 100 according to the embodiment is provided with an authentication service that acquires personal information about one individual from the terminal device 10 used by the individual (user) and authenticates the one individual. Services relating to individuals (for example, similar individuals) can be appropriately provided.

[8. Hardware configuration)
The information processing apparatus 100 according to the embodiment described above is realized by a computer 1000 configured as shown in FIG. 13, for example. FIG. 13 is a hardware configuration diagram illustrating an example of a computer that implements the functions of the information processing apparatus. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 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 is started up, a program depending on the hardware of the computer 1000, and the like.

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

  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 acquires data from the input device via the input / output interface 1600. In addition, the CPU 1100 outputs the generated data to the output device via the input / output interface 1600.

  The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a 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) or PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. Etc.

  For example, when the computer 1000 functions as the information processing apparatus 100 according to the embodiment, the CPU 1100 of the computer 1000 executes a program or data (for example, model M1 (model data MDT1)) loaded on the RAM 1200. The function of the control unit 130 is realized. The CPU 1100 of the computer 1000 reads and executes these programs or data (for example, model M1 (model data MDT1)) from the recording medium 1800. As another example, these programs or data are transmitted from other devices via the network N. May be obtained.

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

[9. Others]
In addition, among the processes described in the above embodiment, all or part of the processes described as being automatically performed can be performed manually, or the processes described as being performed manually can be performed. All or a part 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 document and drawings can be arbitrarily changed unless otherwise specified. For example, the various types of information illustrated in each drawing is not limited to the illustrated information.

  Further, each component of each illustrated apparatus is functionally conceptual, and does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution / integration of each device is not limited to that shown in the figure, and all or a part thereof may be functionally or physically distributed or arbitrarily distributed in arbitrary units according to various loads or usage conditions. Can be integrated and configured.

  In addition, the processes described in the embodiments described above can be appropriately combined within a range in which the process contents are not contradictory.

  In addition, the “section (module, unit)” described above can be read as “means” or “circuit”. For example, the acquisition unit can be read as acquisition means or an acquisition circuit.

DESCRIPTION OF SYMBOLS 1 Information processing system 100 Information processing apparatus 121 Personal information storage part 122 Index information storage part 123 Graph information storage part 124 Model information storage part 130 Control part 131 Acquisition part 132 Generation part 133 Determination part 134 Search part 135 Provision part 10 Terminal apparatus 50 Information provider N network

Claims (14)

A plurality of nodes corresponding to each of a plurality of individuals are connected in accordance with the similarity of the plurality of individuals, graph information, and an acquisition unit for acquiring personal information about one individual,
By searching the graph information starting from a starting node that is a starting point for searching for the graph information determined based on a predetermined criterion among the plurality of nodes of the graph information acquired by the acquiring unit. A search unit for determining whether the one individual is included in the plurality of individuals;
An information processing apparatus comprising: A determination unit that determines the starting node based on index information used to determine the starting node;
Further comprising
The search unit
2. The information processing apparatus according to claim 1, wherein whether or not the one individual is included in the plurality of individuals is determined using the starting node determined by the determining unit as a starting point. The determination unit
The information processing apparatus according to claim 2, wherein the starting node is determined based on the tree structure type index information. The acquisition unit
The graph information in which the plurality of nodes are connected is acquired in accordance with the similarity of a plurality of vectors corresponding to each of the plurality of individuals. Information processing device. The acquisition unit
The information processing apparatus according to claim 4, wherein the graph information obtained by connecting the plurality of vectors indicating the characteristics of the plurality of individuals according to similarity is acquired. The acquisition unit
5. The graph information obtained by connecting the plurality of vectors each having a feature amount extracted from each of the plurality of individuals using a predetermined model according to similarity is obtained. Alternatively, the information processing apparatus according to claim 5. The acquisition unit
By inputting information on the plurality of individuals into a predetermined model, the graph information in which the plurality of vectors each having the feature amount of each of the plurality of individuals extracted are connected according to similarity is obtained. It acquires. The information processing apparatus of any one of Claims 4-6 characterized by the above-mentioned. A providing unit for providing a predetermined service based on a determination result by the search unit;
The information processing apparatus according to claim 1, further comprising: The providing unit includes:
The information processing apparatus according to claim 8, wherein an information providing service regarding the determination result is provided. The acquisition unit
Obtaining the personal information from the terminal device having the personal information of the one individual;
The providing unit includes:
The information processing apparatus according to claim 8, wherein information regarding the determination result is provided to the terminal apparatus. The providing unit includes:
The information processing apparatus according to claim 8, wherein an authentication service based on the determination result is provided. The acquisition unit
Obtaining the personal information from the terminal device having the personal information of the one individual;
The providing unit includes:
The information processing apparatus according to claim 11, wherein the authentication service for authenticating the one individual is provided. An information processing method executed by a computer,
A plurality of nodes corresponding to each of a plurality of individuals connected to each other in accordance with the similarity of the plurality of individuals, and an acquisition step of acquiring personal information about one individual;
By searching the graph information starting from a starting node that is a starting point of the search of the graph information determined based on a predetermined criterion among the plurality of nodes of the graph information acquired by the acquiring step A search step for determining whether the one individual is included in the plurality of individuals;
An information processing method comprising: A plurality of nodes corresponding to each of a plurality of individuals connected to each other in accordance with the similarity of the plurality of individuals, an acquisition procedure for acquiring personal information about one individual;
By searching for the graph information starting from a starting node that is a starting point for searching for the graph information determined based on a predetermined criterion among the plurality of nodes of the graph information acquired by the acquiring procedure A search procedure for determining whether the one individual is included in the plurality of individuals;
An information processing program for causing a computer to execute.

Images