JP6703572B2 - Information processing apparatus, information processing method, and information processing program - Google Patents

Description

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

Conventionally, for example, there is an information processing apparatus that estimates various characteristics of a user by providing various services to the user and analyzing the attributes of the user obtained by using the service. In this type of information processing apparatus, the service provided by itself may be optimized based on the estimated characteristics of the user.

JP, 2008-032252, A

However, the above-mentioned technology analyzes the characteristics of the user individually for each service and applies the analysis result to the optimization of its own service. Considering the use of the analysis results of other services, Was not done.

The present application has been made in view of the above, and an object of the present invention is to provide an information processing device, an information processing method, and an information processing program that can integrate and use individual analysis results of different services.

The information processing device according to the present application includes an acquisition unit and an integration unit. The acquisition unit acquires, from different services, characteristic information including at least one of a model that estimates a characteristic of the user using an attribute of the user and an estimation result regarding the characteristic of the user estimated using the attribute. To do. The integration unit integrates the feature information based on the similarity of the feature information acquired by the acquisition unit.

According to one aspect of the embodiment, it is possible to integrate and use individual analysis results of different services.

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 block diagram showing a configuration example of the information processing apparatus according to the embodiment. FIG. 4 is a diagram showing an example of shared information according to the embodiment. FIG. 5 is a diagram showing an example of service information according to the embodiment. FIG. 6 is a diagram showing an example of model program information according to the embodiment. FIG. 7 is a diagram showing an example of integrated information according to the embodiment. FIG. 8A is a process explanatory diagram (part 1) of the integration process according to the embodiment. FIG. 8B is a process explanatory diagram (part 2) of the integration process according to the embodiment. FIG. 8C is a process explanatory diagram (part 3) of the integration process according to the embodiment. FIG. 8D is a process explanatory diagram (part 4) of the integration process according to the embodiment. FIG. 8E is a process explanatory diagram (5) of the integration process according to the embodiment. FIG. 8F is a process explanatory diagram (part 6) of the integration process according to the embodiment. FIG. 9 is a diagram showing a specific example of the designation method by feature designation. FIG. 10 is a flowchart (No. 1) showing a processing procedure executed by the information processing apparatus according to the embodiment. FIG. 11 is a flowchart (No. 2) showing the processing procedure executed by the information processing apparatus according to the embodiment. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment.

Hereinafter, modes (hereinafter, referred to as “embodiments”) for implementing an information processing device, an information processing method, and an information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited by this embodiment. Further, the respective embodiments can be appropriately combined within the range in which the processing content is not inconsistent. Also, in each of the following embodiments, the same parts are designated by the same reference numerals, and duplicate description will be omitted.

[1. Example of information processing]
First, 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, a model in which the information processing apparatus 1 according to the present application included in the information processing system S estimates the characteristics of the user U by using the attributes of the user U, and the characteristics of the user U estimated by using the above attributes An example is shown in which the characteristic information including at least one of the estimation results regarding is acquired from each of different services, and the processing of integrating the characteristic information is executed based on the similarity of the acquired characteristic information.

As shown in FIG. 1, the information processing system S according to the embodiment includes an information processing device 1, a service providing server 10 (10-1, 10-2, 10-3), and a user terminal 100.

The user terminal 100 is a terminal device owned by the user U. The user U uses the service Y (Y1, Y2, Y3) provided by each service providing server 10 by operating the user terminal 100 to access the service providing server 10 (steps S1-1, S1-2). , S1-3).

The service providing server 10 is a server device that provides various services Y to the user U. The service Y provided by the service providing server 10 is, for example, a service that delivers information via various applications installed in the user terminal 100. Such services include, for example, news service, auction service, weather forecast service, shopping service, financial transaction (stock trading, etc.) service, route search service, map provision service, travel service, restaurant introduction service, blog. There are services etc. The service Y is not limited to the service in which information is distributed via the application, and may be, for example, a service in which information is provided to the user U via a browser.

Further, each service providing server 10 estimates the characteristics of the user U by analyzing the attributes of the user U who used the service Y. Specifically, each service providing server 10 uses at least one of a model for estimating the characteristics of the user U by using the attributes of the user U and an estimation result regarding the characteristics of the user U estimated by using the attributes of the user U. The characteristic information including is generated (steps S2-1, S2-2, S2-3).

The attribute referred to here is a fixed attribute of the user U or a characteristic of the user U. For example, action information regarding the action of the user U when using the service Y such as a search log and a purchase history, It is a concept including demographic attributes such as sex, age, and address, and psychographic attributes such as life cycle, values, individuality, purchase motive, and the like.

The characteristic of the user U is the property of the user U estimated by including various attributes of the user U, or the estimated attribute, and, for example, the interest of the user U, hobbies and preferences, behavior Includes patterns (search behavior, purchasing behavior, etc.).

Further, the above model in the characteristic information can input the attribute of the user U and output the characteristic of the user U as a score, for example. Further, the above-mentioned estimation result in the characteristic information is, for example, a score output by the model. The estimation result may be information that does not depend on the model, for example, information in which the attribute of the user U is simply quantified (for example, a score that increases or decreases according to the number of searches). In the example illustrated in FIG. 1, the service Y1 as a shopping service generates characteristic information including the model “fishing rod” of the user U who purchased the fishing rod by online shopping and the score “5.3” which is the estimation result.

Further, the service Y2 as a search service generates characteristic information including the model “fishing spot” of the user U who has searched for the fishing spot and the score “7.6” which is the estimation result. The service Y3 as a mountaineering tour service generates characteristic information including the model “climbing” of the user U who browsed the information related to the mountaineering tour and the score “2.1” which is the estimation result. It should be noted that in FIG. 1, the higher the score, the more the user U has the characteristic that he or she has a strong interest or preference for the thing represented by the model.

Moreover, although the above-mentioned score has shown the case where it is a continuous value, it may be a discrete value, for example. Specifically, whether or not a fishing spot has been searched may be expressed by a score of a discrete value (that is, a Boolean value) of either "1" (present) or "0" (none). Alternatively, the estimation result is not limited to the score shown as an example, and may be text information.

Here, conventionally, the feature information individually generated by the services Y1, Y2, and Y3 is only used for optimizing its own service, and use of the feature information of other services has not been considered.

For this reason, the characteristic information of other services cannot be used by each other, and the characteristic information of different services cannot be integrated and used.

Therefore, the information processing apparatus 1 according to the embodiment is configured so that the feature information generated by each service Y can be shared by other services Y. Specifically, the information processing apparatus 1 according to the embodiment acquires the above-described characteristic information from each of the different services Y (steps S3-1, S3-2, S3-3) and links the characteristic information for each user. The attached shared information is generated. Note that the information processing apparatus 1 according to the embodiment is not limited to the case of acquiring the above-described model and the characteristic information including the score as the estimation result, and the characteristic information including only the model or the characteristic information including only the score. May be obtained.

Subsequently, the information processing device 1 integrates the feature information based on the acquired similarity of the feature information (step S4). For example, the information processing apparatus 1 uses a method such as machine learning or clustering to group feature information having a high degree of similarity, in other words, characteristics having similar characteristics, into one group, and gives a group name. Further, for example, the information processing device 1 associates feature information having a high degree of similarity with each other if there is an inclusive relation.

For example, in the example of FIG. 1, the feature information models “fishing rod” and “fishing spot” have different detailed features, but their theme is common to the features related to “fishing”. That is, the model “fishing rod” and the “fishing spot” of the characteristic information are similar to each other. Furthermore, it can be inferred that the high scores of the model “fishing rod” and the “fishing spot” in the feature information indicate “like fishing” as the feature of the user U. Therefore, the example of FIG. 1 shows that the model “fishing rod” and the “fishing spot” of the characteristic information are integrated and the group name “like fishing” is given. A specific example of such an integration process of the information processing device 1 will be described later in the description using FIGS. 8A to 8F.

Then, when there is a request from each service Y side, the information processing device 1 provides the provided information based on the feature information that is shared and integrated as shared information (steps S5-1, S5-2, S5-). 3). Note that, for example, there are the following two methods of providing the additional information.

The first is a method in which the service providing server 10 side specifies a specific user U and provides the characteristics (estimation result) of the user U based on the shared information. The second is a method in which the service providing server 10 side specifies a specific characteristic and provides the user U having the characteristic as a list based on the shared information. The above-mentioned group name can be designated as the specific feature. For example, in the example of FIG. 1, if "like fishing" is specified as a feature from the service providing server 10 side, a list of users U having a score of a predetermined value or more is provided from the feature information models "fishing rod" and "fishing spot". To be done.

That is, in the information processing method according to the embodiment, the characteristic information generated by including the attributes of the user U is accumulated as the analysis result, and these are integrated based on the similarity, for example. As a result, the attribute associated with the user U or the information of the user U associated with the attribute can be comprehensively acquired by the other service Y. That is, according to the information processing method of the embodiment, it is possible to integrate and use individual analysis results of different services.

Hereinafter, the information processing apparatus 1 that performs the above-described information processing and the information processing system S including the information processing apparatus 1 will be described in detail.

[2. Configuration of Information Processing System S]
Next, the configuration of the information processing system S according to the embodiment will be described with reference to FIG. FIG. 2 is a diagram illustrating a configuration example of the information processing system S according to the embodiment. As illustrated in FIG. 2, the information processing system S according to the embodiment includes an information processing device 1, a plurality of service providing servers 10-1 to 10-n, a plurality of operator terminals 20, and a plurality of user terminals. 100-1 to 100-n.

These various devices are communicably connected to each other via a network N in a wired or wireless manner. The network N is a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), a telephone network (a mobile telephone network, a fixed telephone network, etc.), a regional IP (Internet Protocol) network, and the Internet. The network N may include a wired network or a wireless network.

In addition, in FIG. 2, the plurality of operator terminals 20 are illustrated as being directly connected to the service providing servers 10-1 to 10-n, but the operator terminals 20 are connected to the service providing servers 10-1 to 10-n. 10-n is shown as being under the control of 10-n, and does not limit the connection form.

The user terminal 100 is a terminal device used by the user U, as described above. The user terminal 100 is an information processing device such as a mobile phone including a smartphone, a tablet terminal, a desktop PC, a notebook PC, or a PDA (Personal Digital Assistant). The user terminal 100 also includes a wearable device that is an eyeglass-type or clock-type information processing terminal.

The user terminal 100 acquires and obtains various kinds of information according to an operation performed by the user U and a function of the user terminal 100 (for example, a function for executing an application for using the service Y, a browser function, etc.). Generates and sends information according to the information. For example, the user terminal 100 accesses the site of the service Y provided by the service providing server 10 via the network N. Then, the user terminal 100 sends a service providing request to the service providing server 10 by designating the information necessary for the user U to receive the service, for example.

The information processing device 1 is a server device that functions as a host server of the service providing server 10. The information processing device 1 acquires the characteristic information from each service providing server 10 to generate the shared information, and integrates the characteristic information in the shared information based on the similarity of the characteristic information. In addition, the information processing device 1 uses the generated shared information to provide various information to the service providing server 10 side.

The service providing server 10 is a server device that provides the service Y to the user U as described above. The service providing server 10 analyzes the attribute of the user U who has used the service Y, and generates the characteristic information, for example. The service providing server 10 also requests the information processing device 1 for the additional information. The request for additional information is transmitted from the service providing server 10 when the operator of the service Y operates the operator terminal 20 connected to the service providing server 10, for example.

The business operator terminal 20 is a terminal device used by a business operator who operates the service Y. The business entity terminal 20 is, for example, a desktop PC, a notebook PC, or the like, but may be a mobile phone, a tablet terminal, a PDA, a wearable device, or the like. The business entity terminal 20 requests the information to be provided to the information processing apparatus 1 by designating a specific user U, a specific feature, or the like from the shared information use service screen provided by the information processing apparatus 1.

In the information processing system S, the information processing device 1, the plurality of service providing servers 10-1 to 10-n, and the plurality of operator terminals 20 are configured to be owned by one operator, for example. That is, one business operator can provide a plurality of services Y. In addition, one business operator collects the characteristic information generated by each service Y as shared information in the information processing device 1 and integrates the information, and acquires the provided information based on the shared information to, for example, a user in each service Y. Used for U marketing research.

The information processing device 1 and the plurality of service providing servers 10-1 to 10-n may be configured to be owned by different companies. That is, the other service Y viewed from a certain service Y of a certain business operator may be the other service Y of the same business operator or the service Y of another business operator. Further, the plurality of service providing servers 10-1 to 10-n may be configured to be owned by different businesses. Further, in addition to the information processing system S described above, a server of a company that only uses the provided information may be connected.

Although the information processing apparatus 1 is configured separately from the service providing server 10 in FIG. 2 and has a function of generating, integrating, and providing shared information, for example, one of the service providing servers is provided. 10 may be performed by substituting some or all of the functions of the information processing device 1.

Further, in FIG. 2, the information processing apparatus 1 has shown a case where it has all the functions of generation, integration and provision of shared information, but, for example, a plurality of information processing apparatuses 1 share the above-mentioned functions. May be.

[3. Information processing device 1]
Next, a configuration example of the information processing device 1 will be described with reference to FIG. FIG. 3 is a block diagram showing a configuration example of the information processing device 1 according to the embodiment. It should be noted that FIG. 3 shows only the components necessary for explaining the information processing apparatus 1, and omits the description of general components.

As shown in FIG. 3, the information processing device 1 includes a communication unit 2, a storage unit 3, and a control unit 4. The information processing apparatus 1 includes an input unit (for example, a keyboard and a mouse) that receives various operations from an administrator who uses the information processing apparatus 1 and a display unit (for example, a liquid crystal display, etc.) for displaying various information. ) May be included.

(About communication unit 2)
The communication unit 2 is realized by, for example, a NIC (Network Interface Card) or the like. The communication unit 2 is connected to the network N in a wired or wireless manner, and transmits/receives information to/from the service providing server 10, the business entity terminal 20 and the user terminal 100 connected to the service providing server 10 via the network N. I do.

(About storage unit 3)
The storage unit 3 is realized by, for example, a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory (Flash Memory), or a storage device such as a hard disk or an optical disc. In the example of FIG. The shared information 31, the service information 32, the model program information 33, and the integrated information 34 are stored.

(About shared information 31)
The shared information 31 is information including the characteristic information acquired from the service providing server 10. FIG. 4 is a diagram showing an example of the shared information 31. As shown in FIG. 4, the shared information 31 is, for example, a table in which the column item is “UID” and the row item is “feature information”. In addition, a score that is an output of the model in the characteristic information is input to the data item of each set of the column item and the row item.

“UID” is identification information for identifying the user U. The “feature information” is information including at least one of a model and a score generated by each service providing server 10, and is information indicating the feature of the user U. In the example illustrated in FIG. 4, a model name such as “fishing rod” is input to each item of “feature information”.

As shown in FIG. 4, the shared information 31 is information including the scores of “UID” and “feature information”. In the example illustrated in FIG. 4, the user U whose UID is “U1” indicates that the score of the model “fishing rod” in the characteristic information is “5.3”.

Moreover, the score of the model “fishing rod” in the characteristic information of the user U whose UID is “U2” is “not input”. This indicates that the score of the model “fishing rod” of the user U who is “U2” has not been acquired from the service providing server 10.

For example, as the score, the score calculated by the service providing server 10 may be directly input as the score of the shared information 31, or the score calculated by the service providing server 10 may be normalized according to a predetermined standard. You may input as shared information 31.

Further, in FIG. 4, the shared information 31 is shown as a score, but the shared information 31 is not limited to the score, and is divided into stages such as “○, Δ and ×” and “excellent, good and acceptable”. It may be the information provided.

(About service information 32)
Next, the service information 32 is information regarding the service Y provided by each service providing server 10. FIG. 5 is a diagram showing an example of the service information 32. As shown in FIG. 5, the service information 32 includes items such as “service ID”, “provided service”, and “number of registered models”.

The "service ID" is identification information that identifies the service Y (or the service providing server 10). The “provided service” is information indicating the content of the service Y. The “number of registered models” is information indicating the number of models of the characteristic information registered in the shared information 31.

(About model program information 33)
Next, the model program information 33 is information including model program data in the feature information. FIG. 6 is a diagram showing an example of the model program information 33. The model program information 33 is information including the program data of the model in the characteristic information acquired by the acquisition unit 41 described later. As shown in FIG. 6, the model program information 33 includes items such as “model ID”, “model name”, “service ID”, and “model data”.

The “model ID” is identification information that identifies the model in the characteristic information. The “model name” is identification information indicating the name of the model in the characteristic information. The "service ID" is identification information that identifies the service Y (or the service providing server 10). The “model data” is model program data in the feature information.

The “model data” is, for example, a regression model in which the attribute of the user U is an explanatory variable. For example, “model data” is a regression model shown in the following formula. That is, it can be represented as a regression model of y=ω1·x1+ω2·x2+... +ωn·xn.

In the above formula, “x” is an explanatory variable corresponding to the attribute of the user U. “Y” is an objective variable corresponding to the score indicating the characteristics of the user U. Further, “ω” is a coefficient of “x” and indicates a predetermined weight value. Specifically, “ω1” is a weight value of “x1”, “ω2” is a weight value of “x2”, and “ωn” is a weight value of “xn”. As described above, the above formula is created by combining the explanatory variable “x” corresponding to the attribute of the user U and the variable including the predetermined weight value “ω” (for example, “ω1·x1 _” ). ..

The “model data” may be feature information generated using SVM (Support Vector Machine) or other machine learning method. Further, the characteristic information may be generated using a deep learning technique. For example, the service Y can generate feature information by appropriately using various deep learning techniques such as DNN (Deep Neural Network), RNN (Recurrent Neural Network), and CNN (Convolutional Neural Network).

Further, the “model data” may include data indicating a tree structure of categories used for each service Y.

(About integrated information 34)
Next, the integrated information 34 is information related to the integration of the characteristic information registered in the shared information 31, and is generated by the integration unit 42 described later. FIG. 7 is a diagram showing an example of the integrated information 34. As shown in FIG. 7, the integrated information 34 includes items such as “group ID”, “group name”, and “affiliation characteristic information ID”.

The “group ID” is identification information that identifies each group when the characteristic information is grouped. The “group name” is information indicating the name of the group assigned for each group ID. The “affiliation characteristic information ID” is information indicating the characteristic information included in each group. In the example described below, the "model ID" described above is input to the "affiliation characteristic information ID".

For example, in the example shown in FIG. 7, the group with the group ID “G1” has a group name “like fishing” and includes model IDs “M1” and [M2], that is, models “fishing rod” and “fishing spot”. It is shown that.

The group with the group ID "G2" has a group name of "I like the outdoors" and has model IDs "M1", "M2" and [M3], that is, models "fishing rod", "fishing spot" and "climbing". It indicates that others are included.

Here, the group name of each group is a generalization of each model to which it belongs, and corresponds to a higher category.

(About control unit 4)
Returning to the description of FIG. 3, the control unit 4 will be described next. The control unit 4 is a controller, and includes, for example, various programs (of information processing programs) stored in a storage device inside the information processing device 1 by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like. (Corresponding to an example) is implemented by using the RAM as a work area. The control unit 4 is, for example, a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As illustrated in FIG. 3, the control unit 4 includes an acquisition unit 41, an integration unit 42, a reception unit 43, an extraction unit 44, an estimation unit 45, and a provision unit 46, and information described below. Realize or execute processing functions and actions. Note that the internal configuration of the control unit 4 is not limited to the configuration shown in FIG. 3, and may be another configuration as long as the information processing described below can be performed. The connection relationship between the processing units included in the control unit 4 is not limited to the connection relationship illustrated in FIG. 3 and may be another connection relationship.

The control unit 4 registers the characteristic information acquired from the service providing server 10 in the shared information 31 and integrates the registered characteristic information. Further, the control unit 4 provides various information to the service Y based on the registered and integrated characteristic information.

(About acquisition unit 41)
The acquisition unit 41 uses a model that estimates the characteristics of the user U using the attributes of the user U, and a different feature information that includes at least one of the estimation results regarding the characteristics of the user U estimated using the attributes of the user U. Obtain from each Y. For example, the acquisition unit 41 acquires the characteristic information generated for the service Y in a format designated in advance. As a result, the format of the characteristic information can be made uniform among the services Y, so that the characteristic information having a unified standard can be acquired.

Further, the acquisition unit 41 acquires, as the characteristic information, information including the above model and the initial value of the score output from the model. The initial value of the score may be calculated in advance by the service providing server 10, or may be calculated by the acquisition unit 41 acquiring the model data. When the acquisition unit 41 calculates the initial value, only the model data of the characteristic information is first acquired, and then the attribute of the user U is acquired from the service providing server 10 to calculate the score.

It should be noted that the acquisition unit 41 may have a check function of checking whether or not the characteristic information is generated according to the specified format when the characteristic information is acquired.

In addition, the acquisition unit 41 registers the acquired characteristic information as the shared information 31 and performs an update process of updating the registered characteristic information as necessary. Specifically, at the first time, the acquisition unit 41 first acquires the model data of the feature information and the initial value of the score, and registers the model information as the shared information 31, and for the second and subsequent times, the service Y requests the user The attribute of U is acquired, and the score of the shared information 31 is updated based on this. When the model data is changed, new model data is acquired from the service Y and the model itself of the shared information 31 is updated.

In addition, the acquisition unit 41 may acquire the attribute of the user U, which is the input of the model in the characteristic information, from the service Y different from the service Y from which the model is acquired. That is, the attribute of the user U may be acquired from the service Y of the acquisition source of the model registered as the shared information 31 and the score may be output, or the user U acquired from the service Y different from the service Y of the acquisition source. The score may be output using the attribute of. Thereby, for example, the models registered in the shared information 31 can be shared between the services Y of different businesses.

(About the integration unit 42)
The integration unit 42 integrates the feature information based on the similarity of the acquired feature information. For example, using the integration unit 42, a machine learning method, a clustering method, or the like, feature information having a high degree of similarity, that is, feature information having a short distance in the feature vector space is collected into one group and a group name is given. Further, if there is an inclusive relation between the feature information having a high degree of similarity, the integration unit 42 associates the feature information with each other.
(Specific example of integrated processing)

Here, the integration process executed by the integration unit 42 will be specifically described with reference to FIGS. 8A to 8F. 8A to 8F are process explanatory diagrams of the integration process according to the embodiment.

FIG. 8A schematically shows each piece of feature information mapped in the feature vector space. In addition, below, as shown in FIG. 8A, each characteristic information may be identified by the above model name ("fishing rod", "fishing spot", etc.). The integration unit 42 executes, for example, machine learning using data in which the user ID and the score for each feature information are serialized as a data set, and as illustrated in FIG. 8A, each feature vector space having the extracted feature as the number of dimensions is used. Map feature information.

Then, the integration unit 42 clusters each mapped feature information using, for example, a clustering method, collects feature information having a short distance in the feature vector space, in other words, feature information having a high degree of similarity, into the same group, and assigns a group name. wear. That is, the integration unit 42 derives the similarity based on the feature vector of each of the feature information based on the feature amount (here, user ID+score) of the feature information, and integrates the feature information based on the similarity. The group name corresponds to the upper category of each piece of characteristic information that is grouped in the same group. The generation of the group name will be described later with reference to FIG. 8F.

Here, a very simple specific example of a case in which the integration unit 42 estimates that the degree of similarity is large when the user ID and the score are used as a data set will be described. For example, as shown in FIG. 8B, when different feature information has a “similar score for the same user”, it is easy to show a tendency that these feature information are close to each other in the feature vector space, that is, the degree of similarity is large. Become.

Further, for example, as shown in FIG. 8C, when “there are correlations in the score distributions among different users”, and the score ratios are almost the same as one example, these feature information items are close in distance in the feature vector space, that is, similar. It tends to show a tendency that the degree is high.

The integrating unit 42 collects feature information items within a predetermined distance in such a feature vector space into the same group. In FIG. 8A, the models “fishing rod” and “fishing spot” belong to the group “fishing like”, the models “mountain climbing” and “running” belong to the group “sports like”, and the models “vehicle type A” and “vehicle type B”. Shows an example in which each group is grouped into the group “I like cars”.

8A to 8C show an example in which the user ID and the score are used as a data set, but as shown in FIG. 8D, for example, a word included in the model name of the feature information is used as a data set. The feature information may be integrated based on the closeness of the distances between the feature information in the feature vector space, that is, “similarity based on word analysis”. In such a case, natural language processing such as Word2Vec can be used. Further, the number of words common to the model names and the function of calculating the degree of word overlap based on the number of words of each model name may be used as the distance function of the feature information.

As another example different from the above, a so-called nearest neighbor search, in other words, a similarity search algorithm or the like may be used. Specifically, as illustrated in FIG. 8E, the integrating unit 42 sets arbitrary feature information (here, “fishing rod”) in the feature vector space as a query point, and the distance is close to the query point by a similarity search algorithm. That is, it is possible to search for characteristic information within a predetermined distance from the query point. Then, the integration unit 42 integrates the feature information within these predetermined distances into the same group as the feature information set as the query point.

In FIG. 8E, the model “fishing rod” is used as a query point, and the models “fishing spot”, “climbing”, “running”, and “vehicle type A” that are close to the query point by the similarity search algorithm are used as the model “model”. An example is shown together with a "fishing rod" as a group "loves the outdoors".

By the way, as described above, the “model data” of the model program information 33 may include data indicating the tree structure of the categories used for each service Y, but the integration unit 42 uses the group name as the group name. Such a tree structure can be used to generate.

For example, as shown in FIG. 8F, it is assumed that there is a tree structure used for each of “service Y1” and “service Y2”. Then, searching for upper categories from "fishing rods" for "service Y1" and "fishing spots" for "service Y2", the upper categories using the common word "outdoor" in the name It was assumed that there was

In such a case, the integration unit 42 generates a group name including “outdoor” (for example, “outdoor favorite”) and registers it in the integrated information 34. Then, the ID (for example, model ID) of the characteristic information belonging to the group “like outdoor” is registered in the integrated information 34.

Here, the example in which the integration unit 42 generates the group name has been described, but the integration unit 42 performs the grouping without generating the group name, and the group name is handled manually according to the nature of the group. May be specified by In addition, the inclusive relationship between the feature information items may be determined by the integration unit 42 according to, for example, the number of layers up to the upper category using a common word in the tree structure.

(Regarding the reception section 43)
Returning to the description of FIG. 3, the receiving unit 43 will be described next. The reception unit 43 receives various requests from the service providing server 10. For example, the reception unit 43 receives from the service Y a request for specifying a characteristic that specifies a specific characteristic. In the feature designation, the model ID, model name, etc. of the feature information included in the shared information 31 are designated. The designation by the feature designation may be one feature information or a plurality of feature information. Alternatively, the feature designation may be a designation including a plurality of feature information such as a field designation.

(Specific example of feature specification)
Here, a specific example of designation by feature designation will be described with reference to FIG. FIG. 9 is a diagram showing a specific example of the designation method by feature designation. Note that FIG. 9 shows a part of the input screen image of the “inter-service crossing extraction service” displayed on the business entity terminal 20, for example.

For example, the designation method by the feature designation is performed by checking the check box of each feature displayed as a category as shown in FIG. For example, the reception unit 43 refers to the integrated information 34, generates an input screen in which each registered group can be designated by a check box, transmits the input screen to the service providing server 10 side, and displays the input screen on the business entity terminal 20.

The upper part of the input screen of FIG. 9 shows an example in which the group “outdoor lover” illustrated in FIG. 8E can be designated. For example, in the business entity terminal 20, when the check box of "like outdoor" is checked and the "extract" button is pressed, the extraction unit 44 described later causes the extraction unit 44 to be described later to include each feature information included in the group "like outdoor" in FIG. 8E. To be comprehensively extracted.

Further, in the middle part of the input screen of FIG. 9, an example is shown in which the groups “like fishing”, “like sports”, and “like car” can be designated as illustrated in FIG. 8A. For example, when at least one of these check boxes is checked and the “extract” button is pressed on the business entity terminal 20, the extraction unit 44, which will be described later, causes each of the groups in FIG. 8A with the check box checked. Each included feature information is comprehensively extracted.

As shown in the lower part of the input screen of FIG. 9, characteristic information for each service Y such as “fishing rod”, “fishing spot”, and “climbing” may be individually designated. This allows the business entity terminal 20 to specify an arbitrary estimation model that is not limited to the category of the group.

Returning to the explanation of FIG. Further, the reception unit 43 receives a user designation request for designating a specific user U from the service Y. The user U designated by the user designation may be one or plural. Alternatively, the user designation may be a user group designation including a plurality of users U.

Further, the reception unit 43 may include a period designation in the above request. For example, in the case of feature designation, the feature information registered in the period designated by the period designation may be the target of feature designation. In the case of user designation, the user U who used the service Y during the period designated by the period designation may be the user designated target.

(About the extraction unit 44)
The extraction unit 44 extracts the user U corresponding to the specific feature designated by the feature designation. For example, the extraction unit 44 extracts the user U whose score of the specified characteristic is equal to or more than a predetermined value.

(About the estimation unit 45)
The estimation unit 45 estimates the characteristics of the specific user U designated by the above user designation. For example, the estimation unit 45 estimates that among the pieces of characteristic information on the specified user U, the characteristic information having a score of a predetermined value or more is the characteristic of the user U.

Note that the estimation unit 45 estimates that if there is feature information with a score less than a predetermined value among the feature information of the designated user U, the user U does not have the feature corresponding to the feature information. You may.

(About providing unit 46)
The provision unit 46 provides the provision information based on the feature information acquired by the acquisition unit 41 and integrated by the integration unit 42 to the other service Y. For example, the providing unit 46 provides the provided information based on the score to the other service Y. Specifically, the provision unit 46 generates the provision information based on the information acquired from the extraction unit 44 or the estimation unit 45, and provides the provision information to the service Y.

For example, the providing unit 46 generates the providing information including the list of the user U extracted by the extracting unit 44 based on the feature specification, and provides the providing information to the service Y. The list may be sorted in any order such as score order, Japanese syllabary order, or alphabetical order.

Alternatively, the providing unit 46 may provide only some of the users U among the users U extracted by the extracting unit 44 to the service Y as providing information. Specifically, the providing unit 46 may provide the provision information in which only the user U having the highest score or the users U having the highest scores are selected.

Further, the providing unit 46 provides the other service Y with the providing information including the information indicating the characteristics of the user U estimated by the estimating unit 45 based on the user designation. For example, the providing unit 46 provides the providing information including the information in which the characteristics of the user U estimated by the estimating unit 45 are arranged in a list.

Further, the providing unit 46 may provide the providing information including only some of the features of the user U estimated by the estimating unit 45. For example, the providing unit 46 may provide the provided information in which only the features indicated by the feature information having the highest score or only the features indicated by the feature information having the highest score are selected.

[4. Processing procedure of information processing apparatus 1]
Next, a processing procedure executed by the information processing device 1 according to the embodiment will be described. FIG. 10 is a flowchart (No. 1) showing the processing procedure executed by the information processing apparatus 1 according to the embodiment. FIG. 11 is a flowchart (part 2) showing the processing procedure executed by the information processing apparatus 1 according to the embodiment. Note that FIG. 10 shows a processing procedure until the characteristic information is acquired and integrated. Further, FIG. 11 shows a processing procedure of the providing processing.

As shown in FIG. 10, first, the acquisition unit 41 uses at least one of a model for estimating the characteristics of the user U by using the attributes of the user U and an estimation result regarding the characteristics of the user U estimated by using the attributes. The characteristic information including the is acquired from each of the different services Y (step S101).

Then, the integration unit 42 integrates the feature information based on the similarity of the feature information acquired by the acquisition unit 41 (step S102), and the process ends.

Further, in the providing process, as shown in FIG. 11, first, the reception unit 43 determines whether or not a feature designation request has been received from the service Y (step S201). When the accepting unit 43 accepts the feature designation (Yes in step S201), the extracting unit 44 extracts the user U having the particular feature designated by the feature designation (step S202).

Subsequently, the providing unit 46 provides the providing information including the list of the user U extracted by the extracting unit 44 to the service Y (step S203), and ends the process.

On the other hand, when the reception unit 43 does not receive the feature designation request (No in step S201), the reception unit 43 determines whether the user designation request has been received (step S204). The order of the processes of steps S201 and S204 may be exchanged.

When the accepting unit 43 accepts the request designated by the user (Yes at Step S204), the estimation unit 45 estimates the characteristics of the user U designated by the designation by the user (Step S205).

Subsequently, the providing unit 46 provides the providing information including the information indicating the characteristics of the user U estimated by the estimating unit 45 to the service Y (step S206), and ends the process.

On the other hand, when the accepting unit 43 does not accept the request designated by the user (No in step S204), the process proceeds to step S201.

[5. Hardware configuration]
The information processing device 1, the service providing server 10, the business entity terminal 20, and the user terminal 100 according to the above-described embodiments are realized by, for example, a computer 1000 configured as shown in FIG. Hereinafter, the information processing apparatus 1 will be described as an example. FIG. 12 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device 1 according to the embodiment. The computer 1000 includes a CPU (Central Processing Unit) 1100, a RAM (Random Access Memory) 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I/F) 1500, and an input/output interface (I). /F) 1600 and a media interface (I/F) 1700.

The CPU 1100 operates based on a program stored in the ROM 1300 or the HDD 1400, and controls each unit. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 starts up, a program dependent 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 another device via the communication network 500 (corresponding to the network N shown in FIG. 2) and sends the data to the CPU 1100, and the data generated by the CPU 1100 is transmitted via the communication network 500 to another device. Send to device.

The CPU 1100 controls output devices such as a display and a printer and input devices 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. The CPU 1100 also 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 the program or data to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) 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 1 according to the embodiment, the CPU 1100 of the computer 1000 realizes each function of the control unit 4 by executing the program loaded on the RAM 1200. Further, the HDD 1400 stores the data in the storage unit 3. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the communication network 500.

[6. Other]
Further, of the processes described in the above embodiment, all or part of the processes described as being automatically performed may be manually performed, or the processes described as being manually performed may be performed. All or part of the process can be automatically performed by a known method. In addition, the processing procedures, specific names, information including various data and parameters shown in the above-mentioned documents and drawings can be arbitrarily changed unless otherwise specified. For example, the various kinds of information shown in each drawing are not limited to the illustrated information.

Further, each constituent element of each illustrated device is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of distribution/integration of each device is not limited to that shown in the figure, and all or a part of the device may be functionally or physically distributed/arranged in arbitrary units according to various loads or usage conditions. It can be integrated and configured.

For example, the acquisition unit 41 and the integration unit 42 illustrated in FIG. 3 may be integrated. Further, for example, the information stored in the storage unit 3 may be stored in a predetermined storage device provided outside via the network N.

Further, in the above-described embodiment, the information processing apparatus 1 may, for example, at least a model that estimates the characteristics of the user U using the attributes of the user U, and an estimation result regarding the characteristics of the user U estimated using the attributes. An example has been shown in which the acquisition process for acquiring the feature information including one from different services Y and the integration process for integrating the feature information based on the similarity of the feature information acquired by the acquisition process are performed. However, in the information processing device 1 described above, the acquisition device that performs the acquisition process and the integration device that performs the integration process may be separated. In this case, the acquisition device has at least the acquisition unit 41. The integration device has at least an integration unit 42. Then, the processing by the information processing apparatus 1 is realized by the information processing system S including the acquisition apparatus and the integrated apparatus.

Further, the above-described embodiments and modified examples can be appropriately combined within a range in which the processing content is not inconsistent.

[7. effect〕
The information processing device 1 of the information processing system S according to the embodiment includes an acquisition unit 41 and an integration unit 42. The acquisition unit 41 includes different models of feature information including at least one of a model for estimating the characteristics of the user U using the attributes of the user U and an estimation result regarding the characteristics of the user U estimated using the attributes. To get from. The integration unit 42 integrates the feature information based on the similarity of the feature information acquired by the acquisition unit 41. As a result, individual analysis results of different services Y can be integrated and used.

The integration unit 42 also derives the degree of similarity based on the feature vector of each of the feature information based on the feature amount of the feature information. That is, the feature information is mapped to the feature vector space based on the feature amount (feature) of each feature information, and the degree of similarity is derived. This makes it possible to accurately classify and integrate the feature information.

Further, the integration unit 42 integrates the feature information by classifying the feature vectors using a clustering algorithm. With this, the feature information can be integrated using a known and highly reliable method, so that the integration unit 42 can be easily and highly reliably mounted.

In addition, the integration unit 42 sets any feature information as a query point, and integrates the feature information based on the distance from the query point measured by using the similarity search algorithm. As a result, since the feature information can be integrated by using a known and highly reliable method as well, the integrating unit 42 can be easily and reliably mounted.

In addition, the model of the feature information outputs the feature of the user U as a score by inputting the attribute, and the integration unit 42 sets the attribute and the score as the feature amount. As a result, it becomes possible to integrate the characteristic information based on the attribute and score of the user U.

In addition, the model of the feature information has a model name, and the integration unit 42 sets the word included in the model name as the feature amount. This makes it possible to integrate the feature information based on the model name.

The embodiments of the present application have been described in detail above with reference to the drawings. However, this is an example, and various modifications and improvements are made based on the knowledge of those skilled in the art, including the modes described in the section of the disclosure of the invention. The present invention can be carried out in other forms described above.

Also, the above-mentioned "section (module, unit)" can be read as "means" or "circuit". For example, the acquisition unit can be read as an acquisition unit or an acquisition circuit.

1 Information processing device 2 Communication unit 3 Storage unit 4 Control unit 10 Service providing server 20 Business terminal 31 Shared information 32 Service information 33 Model program information 34 Integrated information 41 Acquisition unit 42 Integration unit 43 Reception unit 44 Extraction unit 45 Estimating unit 46 Provider 100 User terminal S Information processing system

Claims (8)

A model that estimates the characteristics of the user using the attributes of the user, and an acquisition unit that acquires characteristic information including at least one of estimation results regarding the characteristics of the user estimated using the attributes from different services,
An information processing apparatus, comprising: an integration unit that integrates the feature information based on the similarity of the feature information acquired by the acquisition unit. The integration unit is
The information processing apparatus according to claim 1, wherein the similarity is derived based on a feature vector of each of the feature information based on a feature amount of the feature information. The integration unit is
The information processing apparatus according to claim 2, wherein the feature information is integrated by classifying the feature vector using a clustering algorithm. The integration unit is
The information processing apparatus according to claim 2, wherein the feature information is integrated based on a distance from the query point measured using a similarity search algorithm with the arbitrary feature information as a query point. The model of the feature information is
By inputting the attribute, the characteristic of the user is output as a score,
The integration unit is
The information processing device according to claim 2, 3 or 4, wherein the attribute and the score are used as the feature amount. The model of the feature information has a model name,
The integration unit is
The information processing apparatus according to any one of claims 2 to 5, wherein a word included in the model name is used as the feature amount. An information processing method executed by a computer,
A model for estimating the characteristics of the user by using the attributes of the user, and an acquisition step of acquiring characteristic information including at least one of estimation results regarding the characteristics of the user estimated by using the attributes from different services,
An integration step of integrating the feature information based on the degree of similarity of the feature information acquired by the acquisition step. A model for estimating the characteristics of the user by using the attributes of the user, and an acquisition procedure for acquiring characteristic information including at least one of estimation results regarding the characteristics of the user estimated by using the attributes from different services,
An information processing program for causing a computer to execute an integration procedure for integrating the feature information based on the similarity of the feature information acquired by the acquisition procedure.

Images