Information processing device, information processing server, information processing method, and computer-readable non-transitory storage medium

Abstract

[Problem] To achieve both privacy protection and high inference accuracy. [Solution] Provided is an information processing device comprising: a learning unit that clusters hierarchical data on the basis of a plurality of inference models distributed from an information processing server and performs learning using the inference model corresponding to each cluster; and a communication unit that transmits, to the information processing server, an intermediate result generated for each cluster in the learning by the learning unit, wherein the hierarchical data includes information specifying a main element and a log collected or generated in association with the main element.

Description

[Technical field]

[0001] The present disclosure relates to an information processing device, an information processing server, an information processing method, and a computer-readable non-transitory storage medium. [Background technology]

[0002] In recent years, models that perform some kind of inference based on collected data have been developed. Also, techniques for improving the accuracy of such inference have been proposed. For example, Patent Document 1 discloses a technique for clustering data used for inference. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-154825 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technique disclosed in Patent Document 1 may not be sufficiently effective depending on the structure of the data used for inference. [Means for solving the problem]

[0005] According to one aspect of the present disclosure, there is provided an information processing device comprising: a learning unit that clusters hierarchical data based on a plurality of inference models distributed from an information processing server and performs learning using the inference model corresponding to each cluster; and a communication unit that transmits intermediate results generated for each cluster in the learning by the learning unit to the information processing server, wherein the hierarchical data includes information identifying main elements and logs collected or generated in association with the main elements.

[0006] According to another aspect of the present disclosure, there is provided an information processing method including: a processor clustering hierarchical data based on a plurality of inference models distributed from an information processing server, performing learning using the inference model corresponding to each cluster, and transmitting intermediate results generated for each cluster in the learning to the information processing server, wherein the hierarchical data includes information identifying a main element, and a log collected or generated in association with the main element.

[0007] According to another aspect of the present disclosure, there is provided a non-transitory storage medium readable by a computer that stores a program to cause a computer to function as an information processing device, comprising: a learning unit that clusters hierarchical data based on a plurality of inference models distributed from an information processing server and performs learning using the inference model corresponding to each cluster; and a communication unit that transmits to the information processing server intermediate results generated for each cluster in the learning by the learning unit, wherein the hierarchical data includes information identifying main elements and logs collected or generated in association with the main elements.

[0008] According to another aspect of the present disclosure, there is provided an information processing server comprising: a learning unit that generates a plurality of inference models corresponding to a plurality of clusters, and a communication unit that transmits information relating to the plurality of inference models generated by the learning unit to a plurality of information processing devices, wherein the communication unit receives intermediate results from the plurality of information processing devices generated by learning based on hierarchical data clustered based on the plurality of inference models and the inference models corresponding to each cluster, and the learning unit updates the plurality of inference models based on the plurality of intermediate results, and the hierarchical data includes information identifying a main element and a log collected or generated in association with the main element.

[0009] According to another aspect of the present disclosure, there is provided an information processing method including: a processor generating a plurality of inference models corresponding to a plurality of clusters, transmitting information relating to the generated plurality of inference models to a plurality of information processing devices; receiving, from the plurality of information processing devices, intermediate results generated by learning based on hierarchical data clustered based on the plurality of inference models and the inference models corresponding to each cluster; and updating the plurality of inference models based on the plurality of intermediate results, wherein the hierarchical data includes information identifying a main element, and a log collected or generated in association with the main element.

[0010] According to another aspect of the present disclosure, there is provided a non-transitory storage medium readable by a computer that stores a program to cause a computer to function as an information processing server, comprising: a learning unit that generates a plurality of inference models corresponding to a plurality of clusters, and a communication unit that transmits information related to the plurality of inference models generated by the learning unit to a plurality of information processing devices, wherein the communication unit receives, from the plurality of information processing devices, intermediate results generated by learning based on hierarchical data clustered based on the plurality of inference models and the inference models corresponding to each cluster, and the learning unit updates the plurality of inference models based on the plurality of intermediate results, and the hierarchical data includes information identifying a main element, and a log collected or generated in association with the main element. [Brief description of the drawings]

[0011] [Figure 1] 1 is a block diagram showing a configuration example of a system 1 according to an embodiment of the present disclosure. [Diagram 2] 2 is a block diagram showing an example of the configuration of an information processing device 10 according to the embodiment. FIG. [Diagram 3] 2 is a block diagram showing an example of the configuration of an information processing server 20 according to the embodiment. FIG. [Figure 4] FIG. 11 is a diagram showing an example of a model corresponding to hierarchical data according to the embodiment. [Diagram 5]2 is a schematic diagram for explaining the flow of processing executed by the system 1 according to the embodiment. FIG. [Figure 6] 10 is a flowchart showing the flow of processing executed by the system 1 according to the embodiment. [Figure 7] FIG. 11 is a diagram showing an example of clustering of hierarchical data according to the embodiment. [Figure 8] 10 is a diagram for explaining the operation of the system 1 in the case where the main element according to the embodiment is an access point 40. FIG. [Figure 9] 11 is a diagram for explaining the operation of the system 1 according to the embodiment when the main element is a product category GC. FIG. [Figure 10] 11 is a diagram for explaining the operation of the system 1 according to the embodiment in a case where the main element is a person and the label y is an index relating to the health condition of the person. FIG. [Figure 11] 11 is a diagram for explaining the operation of the system 1 according to the embodiment in a case where the main element is a person and the label y is the facial expression of the person. FIG. [Figure 12] FIG. 2 is a block diagram showing an example hardware configuration of an information processing device 90 according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In this specification and the drawings, components having substantially the same functional configurations are denoted by the same reference numerals, and redundant description will be omitted.

[0013] The explanation will be given in the following order. 1. Embodiment 1.1. Overview 1.2. System configuration example 1.3. Example of configuration of information processing device 10 1.4. Example of configuration of information processing server 20 1.5. Feature Details 1.6. Application Examples 2. Hardware configuration example 3. Summary

[0014] <1. Embodiment> <<1.1. Overview>> First, an overview of one embodiment of the present disclosure will be described.

[0015] As described above, in recent years, models that perform some kind of inference based on collected data (inference models) have been developed.

[0016] Inference models make it possible to realize various inferences with high accuracy based on unknown data. For this reason, the creation and use of inference models is actively carried out in various fields.

[0017] However, depending on the structure of the data used to generate an inference model and for inference using the inference model, it may be difficult to generate a highly accurate inference model.

[0018] An example of such data is hierarchical data.

[0019] Hierarchical data may be defined as data including, for example, information identifying a main element and logs collected or generated in association with the main element.

[0020] As an example, assume that device 80 communicates with a number of other devices and performs some inference based on the logs collected for each communication partner.

[0021] In this case, the main element may be a device with which device 80 communicates.

[0022] In this case, the generated log may have characteristics according to the communication partner, the pair of the device 80 and the communication partner, and the like.

[0023] Therefore, if learning using logs is performed without distinguishing between communication partners, not only will it be difficult to generate an inference model with high accuracy, but there is also a possibility that the time required for convergence will increase and over-learning will occur.

[0024] On the other hand, as disclosed in Patent Document 1, for example, there is a method in which data is clustered and then learning is performed for each data item belonging to each cluster.

[0025] In this way, a method of classifying data with different feature tendencies into multiple clusters and performing learning on each piece of data belonging to each cluster seems to be useful for hierarchical data as well.

[0026] However, with the method disclosed in Patent Document 1, it is difficult to generate a highly accurate inference model because the clustering result cannot be corrected based on the inference result.

[0027] In addition, for example, when a server collects data from multiple devices and performs learning based on that data, protecting privacy also becomes an issue.

[0028] On the other hand, there is a method called Federated Learning as a method for protecting the privacy of data when learning is performed using data collected from multiple devices.

[0029] However, federated learning in general aims to generate a single inference model from data received from multiple devices.

[0030] For this reason, when data having various tendencies, such as hierarchical data, is used in general associative learning, there is a possibility that the time required for convergence will increase, overlearning, etc. will occur.

[0031] In order to reduce the possibility of the above, for example, a method may be considered in which data is clustered according to the characteristics of the device that collected the data, and learning is performed for each piece of data belonging to each cluster.

[0032] In this case, however, all data collected from a given device will be classified into the same cluster.

[0033] For this reason, when performing inference using logs generated for each of the multiple communication partners described above, it may be difficult to reduce the possibility of an increase in the time required for convergence, overlearning, etc.

[0034] The technical concept of one embodiment of the present disclosure was conceived with a focus on the above-mentioned points, and realizes both privacy protection and high inference accuracy.

[0035] To this end, the information processing device 10 according to one embodiment of the present disclosure includes a learning unit 120 that clusters hierarchical data based on multiple inference models distributed from the information processing server 20, and performs learning using the inference model corresponding to each cluster.

[0036] Moreover, the information processing device 10 according to an embodiment of the present disclosure includes a communication unit 130 that transmits to the information processing server 20 an intermediate result generated for each cluster in the above-mentioned learning by the learning unit 120.

[0037] That is, the information processing device 10 according to one embodiment of the present disclosure clusters hierarchical data held by itself using multiple inference models distributed from the information processing server 20, and transmits intermediate results generated by learning for each cluster to the information processing server 20.

[0038] Here, the intermediate result may be information including values ​​calculated from features and labels included in the hierarchical data, and may be information from which it is difficult to restore the features and labels.

[0039] On the other hand, the information processing server 20 according to one embodiment of the present disclosure includes a learning unit 210 that generates multiple inference models corresponding to multiple clusters, and a communication unit that transmits information related to the multiple inference models generated by the learning unit 210 to multiple information processing devices 10.

[0040] Here, one of the features of the communication unit 220 is that it receives, from multiple information processing devices 10, intermediate results generated by learning based on hierarchical data clustered based on multiple inference models and the above-mentioned inference models corresponding to each cluster.

[0041] Another feature of the learning unit 210 is that it updates multiple inference models based on multiple intermediate results.

[0042] That is, an information processing server 20 according to one embodiment of the present disclosure updates the inference model corresponding to each cluster based on intermediate results for each cluster received from multiple information processing devices 10, and distributes information related to the update to each of the information processing devices 10.

[0043] In this way, in the system 1 according to one embodiment of the present disclosure, clustering and transmission of intermediate results by the information processing device 10, updating of the inference model by the server, and distribution of information related to the update may be repeatedly performed.

[0044] The processing described above makes it possible to ensure the convergence of the inference model and simultaneously improve the clustering accuracy and inference precision.

[0045] Furthermore, according to the above-described processing, it is possible to improve privacy protection performance by using intermediate results that are difficult to restore to the original data.

[0046] An example of a system configuration that realizes the above will be described in detail below.

[0047] <<1.2. System configuration example>> FIG. 1 is a block diagram showing an example configuration of a system 1 according to an embodiment of the present disclosure.

[0048] As shown in FIG. 1, a system 1 according to this embodiment includes a plurality of information processing devices 10 and an information processing server 20.

[0049] Each information processing device 10 and the information processing server 20 are connected to each other via a network 30 so as to be able to communicate with each other.

[0050] Although FIG. 1 illustrates an example in which the system 1 includes the information processing devices 10a and 10b, the number of information processing devices 10 according to the present embodiment is not limited to this example.

[0051] (Information processing device 10) The information processing device 10 according to this embodiment performs clustering of hierarchical data using an inference model distributed from the information processing server 20.

[0052] In addition, the information processing device 10 according to this embodiment performs learning using data belonging to each cluster and an inference model corresponding to the cluster, and transmits an intermediate result to the information processing server 20.

[0053] The information processing device 10 according to the present embodiment may be, for example, a personal computer, a smartphone, a tablet, a game console, a wearable device, or the like.

[0054] (Information processing server 20) The information processing server 20 according to this embodiment generates an inference model corresponding to the set cluster and distributes it to multiple information processing devices 10.

[0055] In addition, the information processing server 20 according to this embodiment receives intermediate results corresponding to each cluster from multiple information processing devices 10, and updates each inference model based on the intermediate results.

[0056] The information processing server 20 according to this embodiment distributes information relating to updates to each inference model to multiple information processing devices 10.

[0057] (Network 30) The network 30 according to the present embodiment mediates communication between the information processing device 10 and the information processing server 20.

[0058] <<1.3. Configuration example of information processing device 10>> Next, a configuration example of the information processing device 10 according to the present embodiment will be described in detail.

[0059] FIG. 2 is a block diagram showing an example of the configuration of the information processing device 10 according to the present embodiment.

[0060] As shown in FIG. 2, the information processing device 10 according to this embodiment may include a sensor unit 110, a learning unit 120, and a communication unit .

[0061] (Sensor unit 110) The sensor unit 110 according to this embodiment collects various types of sensor information.

[0062] The sensor information collected by the sensor unit 110 may be used as one element (feature amount) of hierarchical data.

[0063] For this purpose, the sensor unit 110 may include various sensors for collecting sensor information that can be used as one element of hierarchical data.

[0064] On the other hand, if the hierarchical data does not include sensor information, the information processing device 10 does not need to include the sensor unit 110.

[0065] (Learning Section 120) The learning unit 120 according to this embodiment clusters hierarchical data based on a plurality of inference models distributed from the information processing server 20.

[0066] Furthermore, the learning unit 120 according to this embodiment performs learning using an inference model corresponding to each cluster.

[0067] As described above, the hierarchical data according to this embodiment may include information identifying the main component and logs collected or generated in association with the main component.

[0068] Furthermore, the learning unit 120 may cluster the hierarchical data relating to different principal elements based on a plurality of inference models.

[0069] The functions of the learning unit 120 according to this embodiment are realized by various processors.

[0070] The functions of the learning unit 120 according to this embodiment will be described in detail separately.

[0071] (Communication unit 130) The communication unit 130 according to this embodiment communicates with the information processing server 20 via the network 30 .

[0072] The communication unit 130 receives, for example, inference models, information related to updates to the inference models, etc. from the information processing server 20.

[0073] In addition, the communication unit 130 transmits the intermediate result generated by the learning unit 120 to the information processing server 20.

[0074] The communication unit 130 according to the present embodiment may communicate with devices other than the information processing server 20.

[0075] In this case, the communication unit 130 may generate and store a log relating to communication with other devices.

[0076] Logs relating to communications with other devices may be used as part of the hierarchical data.

[0077] The configuration example of the information processing device 10 according to the present embodiment has been described above. Note that the above configuration described with reference to Fig. 2 is merely an example, and the configuration of the information processing device 10 according to the present embodiment is not limited to this example.

[0078] The information processing device 10 according to the present embodiment may further include, for example, an input unit that accepts information input by a user, a display unit that displays various types of information, and the like.

[0079] Furthermore, if the information processing device 10 includes an input unit, the input information may be used as part of the hierarchical data.

[0080] The configuration of the information processing device 10 according to this embodiment can be flexibly modified according to the specifications and operation.

[0081] <<1.4. Example of configuration of information processing server 20>> Next, a configuration example of the information processing server 20 according to the present embodiment will be described in detail.

[0082] FIG. 3 is a block diagram showing an example of the configuration of the information processing server 20 according to the present embodiment.

[0083] As shown in FIG. 3, the information processing server 20 according to the present embodiment may include a learning unit 210 and a communication unit 220.

[0084] (Learning section 210) The learning unit 210 according to this embodiment generates a number of inference models corresponding to the multiple clusters, respectively.

[0085] In addition, the learning unit 210 in this embodiment updates the above-mentioned multiple inference models based on multiple intermediate results received by the communication unit 220.

[0086] The functions of the learning unit 210 according to this embodiment are realized by various processors.

[0087] The functions of the learning unit 210 according to this embodiment will be described in detail separately.

[0088] (Communication unit 220) The communication unit 220 according to this embodiment communicates with a plurality of information processing devices 10 via the network 30 .

[0089] The communication unit 220 transmits, for example, the inference model generated by the learning unit 210 and information related to updates to the inference model to multiple information processing devices 10.

[0090] Moreover, the communication unit 220 receives intermediate results from a plurality of information processing devices 10.

[0091] The configuration example of the information processing server 20 according to the present embodiment has been described above. Note that the above configuration described with reference to Fig. 3 is merely an example, and the configuration of the information processing server 20 according to the present embodiment is not limited to this example.

[0092] The information processing server 20 according to the present embodiment may further include, for example, an input unit that accepts information input by a user, a display unit that displays various types of information, and the like.

[0093] The configuration of the information processing server 20 according to this embodiment can be flexibly modified according to the specifications and operation.

[0094] <<1.5. Feature Details>> Next, the functions of the information processing device 10 and the information processing server 20 according to this embodiment will be described in detail.

[0095] As described above, the information processing device 10 according to this embodiment clusters hierarchical data held by itself using multiple inference models distributed from the information processing server 20, and transmits intermediate results generated by learning for each cluster to the information processing server 20.

[0096] In addition, the information processing server 20 of this embodiment updates the inference model corresponding to each cluster based on the intermediate results for each cluster received from multiple information processing devices 10, and distributes information related to the update to each information processing device 10.

[0097] In order to realize the above-mentioned processing, it is required that the information processing device 10 and the information processing server 20 share a model corresponding to hierarchical data.

[0098] FIG. 4 is a diagram showing an example of a model corresponding to hierarchical data according to the present embodiment.

[0099] The left side of FIG. 4 shows an example of a graphical model corresponding to hierarchical data, and the right side of FIG. 4 shows an example of a generative model corresponding to hierarchical data.

[0100] In each model shown in FIG. 4, η, θ, and κ correspond to a set of information processing devices 10 (global), an information processing device 10, and a principal element, respectively.

[0101] However, each model shown in FIG. 4 is merely an example, and the graphical model and generative model according to this embodiment may be designed appropriately depending on the characteristics of the hierarchical data, the characteristics of the label (objective variable) to be inferred, etc.

[0102] Next, the flow of processing executed by the system 1 according to this embodiment will be described in detail with reference to FIGS.

[0103] FIG. 5 is a schematic diagram for explaining the flow of processing executed by the system 1 according to this embodiment.

[0104] FIG. 6 is a flowchart showing the flow of processing executed by the system 1 according to this embodiment.

[0105] Although FIG. 5 illustrates the processing by the information processing devices 10a and 10b, the system 1 according to the present embodiment may include three or more information processing devices 10 as described above.

[0106] In addition, Figure 5 illustrates an example in which the information processing server 20 generates three inference models M1 to M3 corresponding to the three clusters C1 to C3, respectively, but the number of clusters and inference models in this embodiment is not limited to this example.

[0107] The number of clusters and inference models in this embodiment may be appropriately designed depending on the characteristics of the hierarchical data, the characteristics of the labels (objective variables) to be inferred, etc.

[0108] First, as shown in FIG. 6, the information processing server 20 initializes the inference model (S100).

[0109] In the example shown in FIG. 5, the information processing server 20 initializes the inference models M1 to M3.

[0110] Next, the information processing server 20 distributes information related to the inference model (S101).

[0111] In the example shown in FIG. 5, the information processing server 20 may transmit all of the information constituting the inference models M1 to M3.

[0112] Next, each of the information processing devices 10 clusters the hierarchical data using an inference model (S102).

[0113] In the example shown in FIG. 5, the information processing device 10a classifies the hierarchical data D1 into any one of clusters C1 to C3 corresponding to the distributed inference models M1 to M3, respectively, using the distributed inference models M1 to M3.

[0114] Similarly, the information processing device 10b classifies the hierarchical data D2 into any one of clusters C1 to C3 corresponding to the distributed inference models M1 to M3, respectively, using the distributed inference models M1 to M3.

[0115] Next, each of the information processing devices performs learning for each cluster (S103).

[0116] In the example shown in FIG. 5, the information processing device 10a performs learning for each of the clusters C1 to C3, and outputs the intermediate results w 11 ~w 31 Generate.

[0117] Similarly, the information processing device 10b performs learning for each of the clusters C1 to C3, and obtains the intermediate results w 12 ~w 32 Generate.

[0118] Next, each of the information processing devices 10 transmits the intermediate result to the information processing server 20 (S104).

[0119] In the example shown in FIG. 5, the information processing device 10a outputs the intermediate result w 11 ~w 31 is transmitted to the information processing server.

[0120] Similarly, the information processing device 10b receives the intermediate result w 12 ~w 32 is transmitted to the information processing server 20.

[0121] Next, the information processing server 20 organizes the received intermediate results by cluster, and updates the inference models corresponding to each cluster (S105).

[0122] In the example shown in FIG. 5, the information processing server 20 receives the intermediate result w 11 and w 12 Calculate w1 from and update the inference model M1.

[0123] Similarly, the information processing server 20 receives the intermediate result w 21 and w 22 Calculate w2 from and update the inference model M2.

[0124] Similarly, the information processing server 20 receives the intermediate result w 31 and w 32 Calculate w3 from and update the inference model M3.

[0125] Next, the information processing server 20 determines whether each inference model has converged (S106).

[0126] If the information processing server 20 determines that each inference model has converged (S106: Yes), the system 1 ends the series of processes.

[0127] On the other hand, if the information processing server 20 determines that each inference model has not converged (S106: Yes), the information processing server 20 returns to step S101 and distributes information related to the inference model.

[0128] In the example shown in FIG. 5, the information processing server 20 may transmit, for example, w1, w2, and w3 to the information processing devices 10a and 10b.

[0129] When the information processing server 20 returns to step S101, the information processing device 10 and the information processing server 20 repeatedly execute the subsequent processes.

[0130] The flow of processing by the system 1 according to this embodiment has been described in detail above with reference to an example.

[0131] Next, information transmitted and received between the information processing device 10 and the information processing server 20 according to the present embodiment will be described in more detail.

[0132] FIG. 7 is a diagram showing an example of clustering of hierarchical data according to the present embodiment.

[0133] In the example shown in FIG. 7, hierarchical data having main element ID: ME1, main element ID: ME2, and main element ID: ME3 is classified in cluster C1.

[0134] In addition, in cluster C2, hierarchical data having main element ID: ME4 and main element ID: ME5 is classified.

[0135] In addition, in cluster C2, hierarchical data having main element ID: ME6, main element ID: ME7, and main element ID: ME8 is classified.

[0136] Here, the main element ID is an example of information for identifying a main element.

[0137] In addition to the main element ID, the hierarchical data includes logs collected or generated in association with the main element.

[0138] The log may include, for example, features and labels (objective variables).

[0139] In the example shown in FIG. 7, the feature amount is x n1 ~x n5 However, this is merely an example, and the number of elements that the feature amount according to this embodiment has is not limited to this example.

[0140] The intermediate result according to this embodiment may be a value calculated from the features and labels included in the hierarchical data.

[0141] When the information processing device 10 performs clustering on hierarchical data as shown in FIG. 7, the intermediate results w corresponding to the clusters C1 to C3 are 11 , w 21 , w 31 may be set as follows:

[0142] w 11 ={A1,b1} w 21 ={A2,b2} w 31 ={A3,b3}

[0143] Here, A in the above k and b k may be values ​​calculated based on the features and labels belonging to the cluster Ck.

[0144] Below, A k and b k A calculation example is shown below.

[0145] A1 = A(x 11 ,x 12 ,x 13 ,x 14 ,x 15 ,y1, x 21 ,x 22 ,x 23 ,x 24 ,x 25 ,y2, x 31 ,x 32 ,x 33 ,x 34 ,x35 ,y3) b1=b(x 11 ,x 12 ,x 13 ,x 14 ,x 15 ,y1, x 21 ,x 22 ,x 23 ,x 24 ,x 25 ,y2, x 31 ,x 32 ,x 33 ,x 34 ,x 35 ,y3)

[0146] A2=A(x 41 ,x 42 ,x 43 ,x 44 ,x 45 ,y4, x 51 ,x 52 ,x 53 ,x 54 ,x 55 ,y5) b2=b(x 41 ,x 42 ,x 43 ,x 44 ,x 45 ,y4, x 51 ,x 52 ,x 53 ,x 54 ,x 55 ,y5)

[0147] A3=A(x 61 ,x 62 ,x 63 ,x 64 ,x 65 ,y6, x 71 ,x 72 ,x 73 ,x 74 ,x 75 ,y7, x 81 ,x 82 ,x 83 ,x 84 ,x 85 ,y8) b3 = b(x 61 ,x 62 ,x 63 ,x 64 ,x 65 ,y6, x 71 ,x 72 ,x 73 ,x 74 ,x 75 ,y7, x 81 ,x 82 ,x 83 ,x 84 ,x 85 ,y8)

[0148] As described above, the information processing device 10 according to the present embodiment may calculate the intermediate result without using information that identifies the main element.

[0149] In addition, according to the above calculation, the more hierarchical data that belong to cluster Ck, the higher A k and b k From the original feature x ij and label y i It becomes difficult to restore.

[0150] For these reasons, the generation of intermediate results according to this embodiment makes it possible to effectively improve privacy protection performance.

[0151] Next, we will explain in more detail the information related to updating the inference model that the information processing server 20 transmits to the information processing device 10.

[0152] Here, it is assumed that inference models M1 to M3 corresponding to clusters C1 to C3, respectively, are generated.

[0153] In this case, the information processing server 20 may calculate the information w1 to w3 relating to the updates of the inference models M1 to M3, respectively, as follows, for example.

[0154] w1=(w 11 ,w 12 ,w 13,…,w 1n ) w2=(w 21 ,w 22 ,w 23 ,…,w 2n ) w3=(w 31 ,w 32 ,w 33 ,…,w 3n )

[0155] According to the above calculation, the greater the number n of information processing devices that have calculated the intermediate results, the greater the w k From the original feature x ij and label y i This makes it difficult to restore the original image, thereby effectively improving privacy protection performance.

[0156] On the other hand, the information processing device 10 receives the information w1 to w3 related to the updates of the inference models M1 to M3, respectively, thereby enabling more accurate inference.

[0157] For example, when inferring a label y9 of a feature amount x9 that belongs to a cluster C3, the information processing device 10 may calculate f(w3, x9).

[0158] In this manner, the learning section 120 of the information processing device 10 according to this embodiment is capable of inferring a label based on the feature amount and the inference model.

[0159] <<1.6. Application Examples>> Next, a specific example of application of the system 1 according to this embodiment will be described.

[0160] For example, the main components according to the present embodiment may be various devices that communicate with the information processing device 10.

[0161] In this case, the information processing device 10 may use various logs collected in association with communication with the device as hierarchical data.

[0162] In the following, an example in which the main element according to the present embodiment is an access point that communicates with the information processing device 10 will be described.

[0163] FIG. 8 is a diagram for explaining the operation of the system 1 in the case where the main element according to this embodiment is the access point 40. In FIG.

[0164] In addition, FIG. 8 illustrates an example of the operation when the information processing device 10 is a smartphone.

[0165] In this example, the information processing device 10 collectively holds a communication log L40 for each access point 40.

[0166] The communication log L40 is associated with information for identifying the access point 40 and is used as hierarchical data.

[0167] In this case, each communication log L40 includes features x1 to x n and a label y.

[0168] Feature quantity x1~x n For example, received radio wave strength, CCA (Clear Channel Assessment) busy time, etc. may be adopted.

[0169] As the label y, an index representing the communication quality related to the access point 40 may be used.

[0170] Each of the information processing devices 10 calculates the above-mentioned feature quantities x1 to x2 by using a plurality of inference models distributed from the information processing server 20. n and cluster the communication log L40 including the label y.

[0171] For example, in the example shown in FIG. 8, the information processing device 10a classifies a communication log L40a with three records corresponding to the access point 40a and a communication log L40b with two records corresponding to the access point 40b into a cluster C1.

[0172] Furthermore, the information processing device 10a classifies two records of the communication log L40c corresponding to the access point 40c into a cluster C2.

[0173] Similarly, the information processing device 10b classifies the two records of the communication log L40a corresponding to the access point 40a into cluster C1, and classifies the two records of the communication log L40c corresponding to the access point 40c into cluster C2.

[0174] In this manner, the information processing device 10 according to the present embodiment may perform clustering so that hierarchical data relating to the same main element is classified into the same cluster.

[0175] This makes it possible to learn features according to a predetermined type of access point 40, a pair of a predetermined type of information processing device 10 and a predetermined type of access point 40, and the like, and to achieve more accurate inference.

[0176] At the same time, the information processing device 10 may perform clustering so that hierarchical data relating to different main elements are classified into the same cluster.

[0177] This allows the number of clusters to be reduced, making learning more efficient.

[0178] After performing the above-mentioned clustering, each of the information processing devices 10 according to this embodiment transmits the intermediate results calculated as described above to the information processing server 20 and receives information related to updating the inference model.

[0179] After that, each of the information processing devices 10 according to this embodiment infers a label y using the collected feature amount x and an inference model.

[0180] For example, the information processing device 10 can use an inference model to infer the communication quality when a certain access point 40 is used from the received radio wave intensity from that access point 40.

[0181] In this case, the information processing device 10 may perform control such as connecting to an access point 40 whose inferred communication quality satisfies a predetermined condition, or connecting to the access point 40 whose inferred communication quality is the highest among the multiple access points 40.

[0182] The above describes the operation when the main element according to the present embodiment is a device that communicates with the information processing device 10.

[0183] Next, an example in which the main element according to this embodiment is a product category will be described.

[0184] The main element according to this embodiment does not necessarily have to be an apparatus.

[0185] FIG. 9 is a diagram for explaining the operation of the system 1 in the case where the main element according to the present embodiment is a product category GC.

[0186] Note that FIG. 9 illustrates an example of an operation in the case where the information processing device 10 is a game device and the product is a game.

[0187] In this example, the information processing device 10 collectively holds the purchase log Lgc for each game category GC.

[0188] The purchase log Lgc is associated with information specifying the game category GC and is used as hierarchical data.

[0189] In this case, each purchase log Lgc has features x1 to x n and a label y.

[0190] Feature quantity x1~x n For example, game makers, sales rankings, etc. may be used.

[0191] Furthermore, as the label y, an index relating to the purchase of a game belonging to the category GC (for example, whether or not it has been purchased, whether or not it has been reserved) may be used.

[0192] Each of the information processing devices 10 calculates the above-mentioned feature quantities x1 to x2 by using a plurality of inference models distributed from the information processing server 20. n Cluster the purchase log Lgc containing the label y.

[0193] For example, in the example shown in FIG. 9, the information processing device 10a classifies three records of purchase logs Lgc1 corresponding to the game category GC1 and two records of purchase logs Lgc2 corresponding to the game category GC2 into cluster C1.

[0194] Furthermore, the information processing device 10a classifies two records of the purchase log Lgc3 corresponding to the game category GC3 into a cluster C2.

[0195] Similarly, the information processing device 10a classifies two purchase log records Lgc1 corresponding to the game category GC1 into cluster C1, and classifies two purchase log records Lgc3 corresponding to the game category GC3 into cluster C3.

[0196] After performing the above-mentioned clustering, each of the information processing devices 10 according to this embodiment transmits the intermediate results calculated as described above to the information processing server 20 and receives information related to updating the inference model.

[0197] After that, each of the information processing devices 10 according to this embodiment infers a label y using the collected feature amount x and an inference model.

[0198] For example, the information processing device 10 can use an inference model to infer the likelihood that a user will purchase a certain game.

[0199] In this case, the information processing device 10 may perform control such as explicitly presenting the game whose purchase possibility exceeds a threshold value to the user, or arranging the game in an online shop so that it is easily noticeable to the user.

[0200] Next, an example in which the main element according to this embodiment is a person will be described.

[0201] In this case, the label y may be, for example, an indicator representing a person's physical or mental state.

[0202] FIG. 10 is a diagram for explaining the operation of the system 1 in the case where the main element according to this embodiment is a person and the label y is an index related to the person's health condition.

[0203] In addition, FIG. 10 illustrates an example of the operation when the information processing device 10 is installed in a medical institution.

[0204] In this example, the information processing device 10 collectively holds the examination log Lpe for each person P.

[0205] Feature quantities x1 to x included in the medical examination log Lpe n Examples of such information include various test results such as blood pressure and heart rate, and symptoms.

[0206] The label y may also be a diagnosis by a doctor.

[0207] Each of the information processing devices 10 calculates the above-mentioned feature quantities x1 to x2 by using a plurality of inference models distributed from the information processing server 20. n and cluster the medical examination log Lpe containing label y.

[0208] For example, in the example shown in FIG. 10, the information processing device 10a classifies three records of a medical examination log Lpe1 corresponding to a person P1 and two records of a medical examination log Lpe2 corresponding to a person P2 into a cluster C1.

[0209] Furthermore, the information processing device 10a classifies two records of the examination log Lpe3 corresponding to the person P3 into the cluster C2.

[0210] Similarly, the information processing device 10a classifies two records of the examination log Lpe4 corresponding to the person P4 into a cluster C1, and classifies two records of the examination log Lpe5 corresponding to the person P5 into a cluster C3.

[0211] After performing the above-mentioned clustering, each of the information processing devices 10 according to this embodiment transmits the intermediate results calculated as described above to the information processing server 20 and receives information related to updating the inference model.

[0212] After that, each of the information processing devices 10 according to this embodiment infers a label y using the collected feature amount x and an inference model.

[0213] For example, the information processing device 10 can use an inference model to infer the health condition of a person based on new test results for the person.

[0214] This makes it possible to provisionally determine a person's health condition without an actual diagnosis by a doctor.

[0215] Next, a case where the label y is an index representing a person's emotion will be described.

[0216] The indicators representing the person's emotions include, for example, the user's facial expression.

[0217] FIG. 11 is a diagram for explaining the operation of the system 1 in the present embodiment when the main element is a person and the label y is the facial expression of the person.

[0218] In addition, FIG. 11 illustrates an example of the operation when the information processing device 10 is a robot that communicates with a user.

[0219] In this example, the information processing device 10 collectively holds the shooting log Lpp for each person P.

[0220] Feature quantities x1 to x included in the shooting log Lpp nExamples of such information include the captured image, the position of each feature on the face, and the size of each feature.

[0221] Also, the label y may be various inferred facial expressions.

[0222] Each of the information processing devices 10 calculates the above-mentioned feature quantities x1 to x2 by using a plurality of inference models distributed from the information processing server 20. n and cluster the shooting log Lpp containing label y.

[0223] For example, in the example shown in FIG. 11, the information processing device 10a classifies three records of a shooting log Lpp1 corresponding to a person P1 and two records of a shooting log Lpp2 corresponding to a person P2 into a cluster C1.

[0224] Furthermore, the information processing device 10a classifies three records of the shooting log Lpp3 corresponding to the person P3 into the cluster C2.

[0225] Similarly, the information processing device 10a classifies three records of the shooting log Lpp4 corresponding to the person P4 into cluster C1, and classifies three records of the shooting log Lpp5 corresponding to the person P5 into cluster C3.

[0226] After performing the above-mentioned clustering, each of the information processing devices 10 according to this embodiment transmits the intermediate results calculated as described above to the information processing server 20 and receives information related to updating the inference model.

[0227] After that, each of the information processing devices 10 according to this embodiment infers a label y using the collected feature amount x and an inference model.

[0228] For example, the information processing device 10 can use an inference model to infer the facial expression of a person from an image in which the person is a subject.

[0229] Furthermore, each of the information processing devices 10 according to the present embodiment may perform control such as changing behavior toward the user depending on the inferred facial expression.

[0230] <2. Hardware configuration example> Next, an example of a hardware configuration common to the information processing device 10 and the information processing server 20 according to an embodiment of the present disclosure will be described.

[0231] FIG. 12 is a block diagram showing an example hardware configuration of an information processing device 90 according to an embodiment of the present disclosure.

[0232] The information processing device 90 may be a device having the same hardware configuration as the information processing device 10 and the information processing server 20.

[0233] 19, the information processing device 90 includes, for example, a processor 871, a ROM 872, a RAM 873, a host bus 874, a bridge 875, an external bus 876, an interface 877, an input device 878, an output device 879, a storage 880, a drive 881, a connection port 882, and a communication device 883. Note that the hardware configuration shown here is an example, and some of the components may be omitted. Also, the information processing device 90 may further include components other than those shown here.

[0234] (Processor 871) The processor 871 functions, for example, as an arithmetic processing device or control device, and controls all or part of the operation of each component based on various programs recorded in the ROM 872, the RAM 873, the storage 880, or the removable storage medium 901.

[0235] (ROM 872, RAM 873) The ROM 872 is a means for storing the programs read into the processor 871, data used in calculations, etc. The RAM 873 temporarily or permanently stores, for example, the programs read into the processor 871 and various parameters that change appropriately when the programs are executed.

[0236] (host bus 874, bridge 875, external bus 876, interface 877) The processor 871, ROM 872, and RAM 873 are connected to one another via, for example, a host bus 874 capable of high-speed data transmission. On the other hand, the host bus 874 is connected to an external bus 876 having a relatively low data transmission speed via, for example, a bridge 875. In addition, the external bus 876 is connected to various components via an interface 877.

[0237] (Input Device 878) The input device 878 may be, for example, a mouse, a keyboard, a touch panel, a button, a switch, a lever, etc. Furthermore, a remote controller capable of transmitting a control signal using infrared rays or other radio waves may be used as the input device 878. The input device 878 may also include an audio input device such as a microphone.

[0238] (Output Device 879) The output device 879 is a device capable of visually or audibly notifying the user of acquired information, such as a display device such as a CRT (Cathode Ray Tube), LCD, or organic EL, an audio output device such as a speaker or a headphone, a printer, a mobile phone, a facsimile, etc. The output device 879 according to the present disclosure also includes various vibration devices capable of outputting tactile stimuli.

[0239] (Storage 880) The storage 880 is a device for storing various types of data. For example, a magnetic storage device such as a hard disk drive (HDD), a semiconductor storage device, an optical storage device, or a magneto-optical storage device may be used as the storage 880.

[0240] (Drive 881) The drive 881 is a device that reads information recorded on a removable storage medium 901 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, or writes information to the removable storage medium 901 .

[0241] (Removable storage media 901) The removable storage medium 901 is, for example, a DVD medium, a Blu-ray (registered trademark) medium, an HD DVD medium, various semiconductor storage media, etc. Of course, the removable storage medium 901 may be, for example, an IC card equipped with a non-contact type IC chip, an electronic device, etc.

[0242] (Connection port 882) The connection port 882 is a port for connecting an external device 902, such as a Universal Serial Bus (USB) port, an IEEE 1394 port, a Small Computer System Interface (SCSI), an RS-232C port, or an optical audio terminal.

[0243] (External connection device 902) The external connection device 902 is, for example, a printer, a portable music player, a digital camera, a digital video camera, or an IC recorder.

[0244] (Communication Device 883) The communication device 883 is a communication device for connecting to a network, such as a communication card for wired or wireless LAN, Bluetooth (registered trademark), or WUSB (Wireless USB), a router for optical communications, a router for ADSL (Asymmetric Digital Subscriber Line), or a modem for various types of communications.

[0245] <3. Summary> As described above, the information processing device 10 according to one embodiment of the present disclosure includes a learning unit 120 that clusters hierarchical data based on multiple inference models distributed from the information processing server 20, and performs learning using the inference model corresponding to each cluster.

[0246] Moreover, the information processing device 10 according to an embodiment of the present disclosure includes a communication unit 130 that transmits to the information processing server 20 an intermediate result generated for each cluster in the above-mentioned learning by the learning unit 120.

[0247] According to the above configuration, it is possible to achieve both privacy protection and high inference accuracy.

[0248] Although the preferred embodiment of the present disclosure has been described in detail above with reference to the attached drawings, the technical scope of the present disclosure is not limited to such examples. It is clear that a person having ordinary knowledge in the technical field of the present disclosure can conceive of various modified or amended examples within the scope of the technical ideas described in the claims, and it is understood that these also naturally belong to the technical scope of the present disclosure.

[0249] Furthermore, the steps of the processes described in this specification do not necessarily have to be processed in chronological order according to the order described in the flowchart or sequence diagram. For example, the steps of the processes of each device may be processed in an order different from the order described, or may be processed in parallel.

[0250] Furthermore, the series of processes performed by each device described in this specification may be realized using any of software, hardware, and a combination of software and hardware. The programs constituting the software are provided, for example, inside or outside each device and stored in advance in a non-transitory computer readable medium that can be read by a computer. Then, each program is, for example, loaded into a RAM when executed by a computer and executed by various processors. The storage medium is, for example, a magnetic disk, an optical disk, a magneto-optical disk, a flash memory, etc. Furthermore, the computer programs may be distributed, for example, via a network, without using a storage medium.

[0251] In addition, the effects described in this specification are merely descriptive or exemplary and are not limiting. In other words, the technology according to the present disclosure may achieve other effects that are apparent to a person skilled in the art from the description of this specification, in addition to or in place of the above effects.

[0252] Note that the following configurations also fall within the technical scope of the present disclosure. (1) a learning unit that clusters the hierarchical data based on a plurality of inference models distributed from an information processing server, and performs learning using the inference model corresponding to each cluster; a communication unit that transmits to the information processing server an intermediate result generated for each cluster in the learning by the learning unit; Equipped with The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing device. (2) The learning unit clusters the hierarchical data relating to different main elements based on a plurality of the inference models. The information processing device according to (1). (3) the learning unit performs clustering so that the hierarchical data relating to the same main element are classified into the same cluster. The information processing device according to (1) or (2). (4) the learning unit performs clustering so that the hierarchical data relating to different main elements are classified into the same cluster. The information processing device according to any one of (1) to (3). (5) The log includes features and labels. The information processing device according to any one of (1) to (4). (6) the intermediate result includes a value calculated from the feature and the label; The information processing device according to (5). (7) The learning unit infers the label based on the feature amount and the inference model. The information processing device according to (5) or (6). (8) The communication unit receives information related to the inference model that has been updated based on the intermediate results received by the information processing server from the multiple devices, and transfers the information to the learning unit. The information processing device according to any one of (1) to (7). (9) The main element includes a device for communicating with the communication unit. The information processing device according to any one of (5) to (7). (10) The main element includes an access point that communicates with the communication unit. The information processing device according to (9). (11) The label includes an index representing a communication quality related to the access point. The information processing device according to (10). (12) The main elements include a category of goods; The information processing device according to any one of (5) to (7). (13) The label includes an indication of a purchase of a product belonging to the category. The information processing device according to (12). (14) The main element includes a person. The information processing device according to any one of (5) to (7). (15) The label includes an indicator representing a physical or mental state of a person. The information processing device according to (14). (16) The label includes an indicator representing an emotion of a person. The information processing device according to (14). (17) The processor: clustering the hierarchical data based on a plurality of inference models distributed from an information processing server, and performing learning using the inference model corresponding to each cluster; transmitting an intermediate result generated for each cluster in the learning to the information processing server; Including, The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing methods. (18) Computer, a learning unit that clusters the hierarchical data based on a plurality of inference models distributed from an information processing server, and performs learning using the inference model corresponding to each cluster; a communication unit that transmits to the information processing server an intermediate result generated for each cluster in the learning by the learning unit; Equipped with The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing device, A non-transitory storage medium readable by a computer that stores a program for causing the device to function as a (19) a learning unit that generates a plurality of inference models corresponding to the plurality of clusters, respectively; a communication unit that transmits information related to the multiple inference models generated by the learning unit to multiple information processing devices; Equipped with the communication unit receives, from the information processing devices, intermediate results generated by learning based on hierarchical data clustered based on the plurality of inference models and the inference models corresponding to each cluster; The learning unit updates the inference models based on the intermediate results; The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing server. (20) The processor: generating a plurality of inference models corresponding to the plurality of clusters, respectively; Transmitting information relating to the generated inference models to a plurality of information processing devices; receiving intermediate results generated by learning based on hierarchical data clustered based on the plurality of inference models and the inference models corresponding to each cluster from the plurality of information processing devices; updating the inference models based on the intermediate results; and Including, The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing methods. (twenty one) Computer, a learning unit that generates a plurality of inference models corresponding to the plurality of clusters, respectively; a communication unit that transmits information related to the multiple inference models generated by the learning unit to multiple information processing devices; Equipped with the communication unit receives, from the information processing devices, intermediate results generated by learning based on hierarchical data clustered based on the plurality of inference models and the inference models corresponding to each cluster; The learning unit updates the inference models based on the intermediate results; The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing server, A non-transitory storage medium readable by a computer that stores a program for causing the device to function as a [Explanation of symbols]

[0253] 1 System 10. Information processing device 110 Sensor section 120 Learning Department 130 Communications Department 20. Information Processing Server 210 Learning Department 220 Communications Department 40 Access Points

Claims

1. a learning unit that clusters the hierarchical data based on a plurality of inference models distributed from an information processing server, and performs learning using the inference model corresponding to each cluster; a communication unit that transmits to the information processing server an intermediate result generated for each cluster in the learning by the learning unit; Equipped with The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing device.

2. The learning unit clusters the hierarchical data relating to different main elements based on a plurality of the inference models. The information processing device according to claim 1 .

3. the learning unit performs clustering so that the hierarchical data relating to the same main element are classified into the same cluster. The information processing device according to claim 1 .

4. the learning unit performs clustering so that the hierarchical data relating to different main elements are classified into the same cluster. The information processing device according to claim 1 .

5. The log includes features and labels. The information processing device according to claim 1 .

6. the intermediate result includes a value calculated from the feature and the label. The information processing device according to claim 5 .

7. The learning unit infers the label based on the feature amount and the inference model. The information processing device according to claim 5 .

8. The communication unit receives information related to the inference model that has been updated based on the intermediate results received by the information processing server from the multiple devices, and transfers the information to the learning unit. The information processing device according to claim 1 .

9. The main element includes a device for communicating with the communication unit. The information processing device according to claim 5 .

10. The main element includes an access point that communicates with the communication unit. The information processing device according to claim 9.

11. The label includes an index representing a communication quality related to the access point. The information processing device according to claim 10.

12. The main elements include a category of goods; The information processing device according to claim 5 .

13. The label includes an indication of a purchase of a product belonging to the category. The information processing device according to claim 12.

14. The main element includes a person. The information processing device according to claim 5 .

15. The label includes an indicator representing a physical or mental state of a person. The information processing device according to claim 14.

16. The label includes an indicator representing an emotion of a person. The information processing device according to claim 14.

17. The processor: clustering the hierarchical data based on a plurality of inference models distributed from an information processing server, and performing learning using the inference model corresponding to each cluster; transmitting an intermediate result generated for each cluster in the learning to the information processing server; Including, The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing methods.

18. Computer, a learning unit that clusters the hierarchical data based on a plurality of inference models distributed from an information processing server, and performs learning using the inference model corresponding to each cluster; a communication unit that transmits to the information processing server an intermediate result generated for each cluster in the learning by the learning unit; Equipped with The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing device, A non-transitory storage medium readable by a computer that stores a program for causing the device to function as a

19. a learning unit that generates a plurality of inference models corresponding to the plurality of clusters, respectively; a communication unit that transmits information related to the multiple inference models generated by the learning unit to multiple information processing devices; Equipped with the communication unit receives, from the information processing devices, intermediate results generated by learning based on hierarchical data clustered based on the plurality of inference models and the inference models corresponding to each cluster; The learning unit updates the inference models based on the intermediate results; The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing server.

20. The processor: generating a plurality of inference models corresponding to the plurality of clusters, respectively; Transmitting information relating to the generated inference models to a plurality of information processing devices; receiving intermediate results generated by learning based on hierarchical data clustered based on the plurality of inference models and the inference models corresponding to each cluster from the plurality of information processing devices; updating the inference models based on the intermediate results; and Including, The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing methods.

21. Computer, a learning unit that generates a plurality of inference models corresponding to the plurality of clusters, respectively; a communication unit that transmits information related to the multiple inference models generated by the learning unit to multiple information processing devices; Equipped with the communication unit receives, from the information processing devices, intermediate results generated by learning based on hierarchical data clustered based on the plurality of inference models and the inference models corresponding to each cluster; The learning unit updates the inference models based on the intermediate results; The hierarchical data includes information identifying a main component and a log collected or generated in association with the main component. Information processing server, A non-transitory storage medium readable by a computer that stores a program for causing the device to function as a

Images