JP7104219B1 - Information processing equipment, information processing methods and information processing programs - Google Patents

Abstract

The present invention provides an information processing device that enables data area member companies to promote the provision of their own data. Kind Code: A1 In an information processing system in which a plurality of client terminals and a mother server are communicably connected to each other via a network, wired or wirelessly, a mother server 100, which is an information processing device, includes an acquisition unit 131 acquires anonymous information obtained by vectorizing customer data from each of a plurality of companies. The learning unit 132 performs AI machine learning using the acquired anonymous information from each company. The estimating unit 133 estimates a customer who matches the purpose of a specific company among a plurality of companies by AI that has undergone machine learning by the learning unit 132 . The providing unit 134 provides information based on the estimation result by the estimating unit 133 . [Selection drawing] Fig. 9

Description

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

In the data sharing system, the technology for safely utilizing the contents of the data held by each company without disclosing it to other companies is disclosed.

Japanese Patent No. 6803598

However, the above-mentioned prior art is a predetermined encryption method (an encryption method capable of performing operations including search and analysis while the encrypted state is maintained) for sensitive data provided by an organization or the like participating in a data sharing system. On the other hand, the key used for encryption and decryption is only managed by each organization that provided the sensitive data.

In addition, if all clients are forced to integrate IDs with a common ID (ID Connect), there is a problem that the number of data area member companies does not increase. Moreover, even if a company joins the data area, it is unrealistic to have each company send all customer data (personal information) to the mother server side (many companies should not agree with this). Therefore, it is necessary to design the data area member companies so that they do not produce much of their own data and cannot utilize marketing by relying only on the data of other companies. In other words, it is necessary to have a mechanism that does not allow free riding and a mechanism that makes you want to publish your own data.

The present application has been made in view of the above, and an object of the present application is to provide a mechanism for a data area member company to want to output its own data.

The information processing device according to the present application includes an acquisition unit that acquires anonymous information obtained by vectorizing customer data from each of a plurality of companies, a learning unit that performs machine learning of AI using anonymous information from each company, and the above. The providing unit includes an estimation unit that estimates a customer that suits the purpose of a specific company among the plurality of companies by AI that has undergone machine learning, and a providing unit that provides information based on the estimation result by the estimation unit. , The client-side AI for vectorizing the customer data is provided to each of the plurality of companies, and the acquisition unit receives anonymous information obtained by vectorizing the customer data from each of the plurality of companies by the client-side AI. It is characterized by acquiring .

According to one aspect of the embodiment, it is possible to provide a mechanism by which a data area member company wants to output its own data.

FIG. 1 is an explanatory diagram showing an outline of an information processing method according to an embodiment. FIG. 2 is an explanatory diagram showing an outline of AI learning on the server side. FIG. 3 is an explanatory diagram showing an example of learning from the purpose of the campaign. FIG. 4 is an explanatory diagram showing an outline of vectorization of customer data. FIG. 5 is an explanatory diagram showing an outline of inference on the server side. FIG. 6 is a schematic diagram that simplifies inference on the server side. FIG. 7 is an explanatory diagram showing an outline of vector neighborhood customer expansion. FIG. 8 is a conceptual diagram showing an image of the 1st Party data area concept. FIG. 9 is a diagram showing a configuration example of the mother server according to the embodiment. FIG. 10 is a diagram showing an example of a user information database. FIG. 11 is a diagram showing an example of a history information database. FIG. 12 is a diagram showing an example of an anonymous information database. FIG. 13 is a flowchart showing a processing procedure according to the embodiment. FIG. 14 is a diagram showing an example of a hardware configuration.

Hereinafter, the information processing apparatus, the information processing method, and the mode for carrying out the information processing program (hereinafter, referred to as “the embodiment”) according to the present application will be described in detail with reference to the drawings. The information processing apparatus, information processing method, and information processing program according to the present application are not limited by this embodiment. Further, in the following embodiments, the same parts are designated by the same reference numerals, and duplicate description is omitted.

[1. Information processing method overview]
First, with reference to FIG. 1, an outline of an information processing method performed by the information processing apparatus according to the embodiment will be described. FIG. 1 is an explanatory diagram showing an outline of an information processing method according to an embodiment. In FIG. 1, a case where a data area member company provides a mechanism for wanting to output its own data will be described as an example.

As shown in FIG. 1, the information processing system 1 according to the embodiment includes a client terminal 10 and a mother server 100. The client terminal 10 and the mother server 100 are connected to each other via a network N so as to be able to communicate with each other by wire or wirelessly. The network N is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet.

Further, the client terminal 10 includes a wireless communication network such as LTE (Long Term Evolution), 4G (4th Generation), 5G (5th Generation: 5th generation mobile communication system), Bluetooth (registered trademark), and wireless LAN (Local). It is possible to connect to the network N via short-range wireless communication such as Area Network) and communicate with the mother server 100.

The client terminal 10 is an information processing device used by each company on the client side (data area member company). For example, the client terminal 10 is a PC (Personal Computer), a server device, a smart device such as a smartphone or a tablet terminal, or the like. It is preferable that each company on the client side is a company in a different industry. Of course, competitors (competitors in the same industry) may be included in the data area member companies.

The client terminal 10 of each company collects customer data regarding each user U (user) who is a customer (Customer) of the company. For example, the client terminal 10 of each company collects registration information, store visit records, product purchase history / service usage history, questionnaire responses, and the like of each user U who purchased or used the company's product as customer data.

In the example shown in FIG. 1, the client terminal 10 used by company A is "client terminal 10A", the client terminal 10 used by company B is "client terminal 10B", and the client used by company C for identification. The terminal 10 is referred to as a "client terminal 10C".

The mother server 100 is, for example, a PC, a server device, a mainframe, a workstation, or the like. The mother server 100 may be realized by cloud computing. Further, the mother server 100 may collect customer data (data on the mother side) regarding each user U as a customer who uses the service on the mother side, separately from the client terminal 10 of each company.

For example, the mother server 100 cooperates with the terminal device of each user U, and for each user U's terminal device, API (Application Programming Interface) service for various applications (hereinafter, applications) and various data. May be provided.

Further, the mother server 100 may be an information processing device that provides some kind of Web service online to the terminal device of each user U. For example, the mother server 100 has Internet connection, search service, SNS (Social Networking Service), electronic commerce, electronic payment, online game, online banking, online trading, accommodation / ticket reservation, video / music distribution, news as Web services. , Maps, route search, route guidance, route information, operation information, weather forecast, and other services may be provided. Actually, the mother server 100 may cooperate with various servers that provide the above-mentioned Web service to mediate the Web service, or may be in charge of processing the Web service.

The mother server 100 can acquire user information regarding the user U. For example, the mother server 100 acquires information on the attributes of the user U such as the gender, age, and residential area of the user U. Then, the mother server 100 stores and manages information related to the attributes of the user U together with the identification information (user ID and the like) indicating the user U.

Further, the mother server 100 acquires various historical information (log data) indicating the behavior of the user U from the terminal device of the user U or from various servers and the like based on the user ID and the like. For example, the mother server 100 acquires a position history, which is a history of the position and date and time of the user U, from the terminal device. Further, the mother server 100 acquires the search history, which is the history of the search query input by the user U, from the search server (search engine). Further, the mother server 100 acquires a browsing history, which is a history of the contents browsed by the user U, from the content server. Further, the mother server 100 acquires the purchase history (payment history), which is the history of the user U's product purchase and payment processing, from the electronic commerce server or the payment processing server. Further, the mother server 100 may acquire the listing history and the sales history, which are the listing histories of the user U in the marketplace, from the electronic commerce server or the settlement server. Further, the mother server 100 acquires the posting history, which is the posting history of the user U, from the posting server or the SNS server that provides the word-of-mouth posting service.

The number of each device included in the information processing system 1 shown in FIG. 1 is not limited to that shown in the figure. For example, in FIG. 1, for simplification of the illustration, only three client terminals 10 are shown, but this is merely an example and is not limited, and may be four or more. Further, the mother server 100 may also be distributed to a plurality of server devices.

For example, as shown in FIG. 1, the mother server 100 uses the client terminals 10 (10A, 10B, 10C) of each company that joins the data area via the network N in advance (when each company joins the data area, etc.). , ...), AI (Artificial Intelligence) for anonymizing (vectorizing) customer data is distributed (step S1).

At this time, the mother server 100 may customize the AI for each company. That is, the mother server 100 may distribute different AIs to each company. Since the content of information acquired as customer data may differ depending on the type of business and business type of the company, it is possible to change the AI specifications according to the content of the acquired customer data, and it is not the same AI uniformly. You may. It suffices if the mother server 100 (server side) grasps and manages the specifications of the AI distributed to each company.

Subsequently, the mother server 100 collects anonymous information from the client terminals 10 of each company affiliated with the data area, in which the customer data of each company is anonymized (vectorized) by AI (step S2).

In the present embodiment, the client terminal 10 of each company acquires customer data related to its own customer, and generates anonymous information obtained by converting (vectorizing) the acquired customer data into a vector by AI. At this time, the client terminal 10 may perform so-called embedding (embedding) and generate an embedding vector (embedding vector) based on customer data as anonymous information. Then, the client terminal 10 of each company transmits anonymous information in which customer data is anonymized (vectorized) to the mother server 100 in response to a request from the mother server 100 or voluntarily.

For example, the client terminal 10 inputs customer data into a vector conversion model constructed by AI on the mother server 100 (server side) using a machine learning method using a neural network or the like, and the customer data is composed of multiple dimensions. Convert to a real-valued vector. Alternatively, the client terminal 10 may convert the customer data into a vector according to a predetermined conversion rule (rule) (on a rule basis).

The anonymous information is irreversible information, and the original customer data cannot be restored from the vector value of the anonymous information. Here, "cannot be restored" means not only the concept that the original data cannot be definitively calculated from the vector value, but also the original data such as those that cannot be estimated, that is, customer data. It also includes the notion that it is difficult to calculate or estimate what it was like. That is, anonymous information cannot be decrypted like encrypted data. For example, when anonymizing (vectorizing) customer data, it is possible to arrange it in a predetermined group or segment according to common attributes, etc., or to perform rounding (rounding, truncation, etc.) to "round" the numerical value. .. Further, the customer data and the vector value are not limited to a one-to-one relationship in which the same vector value can be obtained from the same data, but also a many-to-one relationship in which the same vector value can be obtained from different data, or in part. In some cases, there is a many-to-many relationship in which different vector values can be obtained depending on the combination of data even if the same data is included. Furthermore, when different AIs are distributed to each company, the meaning of the vector value itself may differ depending on the company. Therefore, one vector value is not always based on the same data. Further, what the mother server 100 (server side) needs is a vector value, not the customer data that is the basis (original) of the vector value.

Moreover, since it is the mother server 100 (server side) that distributes AI that defines the vector value of anonymous information and the content that it means, even if each company and a third party see only the vector value of anonymous information. Since it is not possible to understand what the vector value means, even if anonymous information is leaked, it is safe because customer data will not be leaked. Note that each time a vector is created, even if it is a vector of the same user, it becomes a different vector, and it is not always the same.

Subsequently, the mother server 100 learns the purpose setting data as a correct answer using all the anonymous information collected from the client terminals 10 of each company (step S3). For example, the mother server 100 performs machine learning using anonymous information of all customers of all companies participating in the data area, and generates a customer evaluation model. At this time, the mother server 100 may learn by using the customer data (mother side data) independently acquired by the mother side in addition to all the anonymous information. The mother server 100 may generate anonymized information in which the data on the mother side is anonymized (vectorized) by AI.

Subsequently, the mother server 100 makes an inference for each company from the learning result (step S4). For example, the mother server 100 generates a list of customers who may purchase a specific product of a specific company based on the result of learning using all the anonymous information collected from the client terminals 10 of each company. At this time, the mother server 100 may input anonymous information from the specific company into the customer evaluation model and acquire a list of customers who may purchase a specific product of the specific company as an output.

Subsequently, the mother server 100 provides the client terminal 10 of each company via the network N with the result of the inference corresponding to each company and the information based on the result of the inference (step S5). For example, the mother server 100 provides a client terminal 10 of a specific company with a list of customers who may purchase a specific product of the specific company.

[1-1. AI learning on the server side]
Next, AI learning on the mother server 100 (server side) according to the present embodiment will be described with reference to FIG. FIG. 2 is an explanatory diagram showing an outline of AI learning on the server side.

As shown in FIG. 2, the data area has a configuration of a CDP (Customer Data Platform) on the client side and a server on the mother side. That is, it is configured as a client terminal 10 of each company and a mother server 100.

In the CDP on the client side, the client terminal 10 of each company generates anonymous information obtained by converting (vectorizing) the customer data (1st party data) owned by the company by AI. At this time, the client terminal 10 of each company generates a vector for each company's ID as anonymous information. That is, a combination of the customer ID of each company and the vector data is generated.

The customer data held by each company is different for each company. For example, Company A collects information such as "visit", "purchase", and "request / conversation at the time of business negotiation" as customer data. Company B collects information such as "product purchase", "questionnaire response", and "WEB advertisement contact" as customer data. Company C collects information such as "search", "news contact", and "purchased product" as customer data. However, these are just examples.

Then, the client terminal 10 of each company transmits the generated anonymous information as transmission data to the mother server 100 (server side) in response to a request from the mother server 100 or voluntarily. For security reasons, the client terminal 10 of each company may further encrypt the generated anonymous information and transmit it to the mother server 100 (server side). It is possible to encrypt and transmit data within the scope of common general technical knowledge. In addition, a closed virtual direct connection line may be established between the mother side and the client side by tunneling. For example, a VPN (Virtual Private Network) may be constructed between the mother side and the client side.

At this time, the client terminal 10 of each company transmits only the vector data associated with the common ID as anonymous information. The common ID is a customer ID common in the data area. The vector data associated with the common ID is the vector data of the customer who has licensed the data donation to the data area. Throughout, the cooperation between the mother side and the client side is the exchange of vector data only for the users who have licensed the common ID cooperation. It should be noted that only vector data (anonymous information) is transmitted, and customer data itself is not transmitted. Even if it is vectorized, it may be interpreted as personal information, but it is overwhelmingly safer than raw personal information data. It can be seen from the common ID that they are the same person, but it cannot be determined whether the information about the individual such as the place of residence, age, gender, etc. is included or anonymized (vectorized).

Further, it is not necessary to associate the vector data of all customers with the common ID. For example, if the company only participates in the data area without obtaining a license for the data in the data area to each customer, it is not necessary to associate the common ID with the vector data of the customer.

In the present embodiment, ID connection (ID Connect) with a common ID is set to "arbitrary". That is, the design is such that even if there is a customer who "does not" perform ID integration (ID Connect) with a common ID, it functions as a whole.

In addition, the design will be such that the purpose can be achieved by "not sending raw customer data (personal information) to the mother server" from companies that have joined the data area. That is, the raw customer data (personal information) possessed by each company is not transmitted to the mother server 100. The raw customer data (personal information) possessed by each company is anonymized (vectorized) and transmitted to the mother server 100 together with the ID.

In addition, by introducing a distributed AI that anonymizes (vectorizes) the company's customer data using only the company's data, the targeting accuracy of the company will not improve unless the company's data is produced in large quantities in terms of quality and quantity. And. This prevents freeride that uses only the data of other companies without issuing the company's data.

The greater the quantity and quality of your company's customer data, the greater the benefits your company will receive. That is, the accuracy is improved as the number of vector data associated with the common ID is increased by obtaining the license of the data in the data area for each customer.

Each customer permits "customer data about itself to be anonymized (vectorized) and used within the data area". In addition, each company may give an incentive or a privilege to the permission of each customer. For example, if each customer approves, a discount coupon or the like will be sent from each company in the data area. In addition, rewards will be issued to the licensed customers according to activities within the data area (product purchase / service use of data area participating companies, advertisement contact, questionnaire response, etc.).

The mother server 100 (server side) sets a list of past product purchaser IDs as correct answer data from the CDP of each company and carries out AI learning. For example, if company A wants to create a product purchase probability list (recommendation list) that is a list of customers with a high purchase probability of its own product X, the mother server 100 (server side) uses the past product X from the CDP of company A. AI learning is carried out by setting the purpose of the ID list of the purchaser as the correct answer data.

Here, an example of learning from the purpose of the campaign will be described with reference to FIG. FIG. 3 is an explanatory diagram showing an example of learning from the purpose of the campaign. In addition, AI learning shall be carried out for each campaign. As shown in FIG. 3, the mother server 100 (server side) performs AI learning by setting the purpose of a list of IDs of past purchasers of the product X from the data of the company A.

At this time, the mother server 100 (server side) may set the customer data (data on the mother side) owned by itself in addition to the anonymous information of each company in consideration of the correct answer data. For example, in the mother server 100 (server side), when company A is an automobile manufacturer and product X is a specific vehicle, customer data of "people who are interested in golf" is added to the correct answer data as data on the mother side. May be set.

Then, the mother server 100 (server side) includes all the records of the customer data of the company to which the correct answer data is given and all the records of the other member companies linked by the common ID among all the records of the customer data of the company. AI learning is carried out using and as learning data.

[1-2. Vectorization of customer data]
Next, the vectorization of customer data according to the present embodiment will be described with reference to FIG. FIG. 4 is an explanatory diagram showing an outline of vectorization of customer data. In the present embodiment, by vectorizing the personal information of each customer of each company, it is possible to process the customer characteristics instead of the personal information.

As shown in FIG. 4, for example, when company A is an automobile manufacturer and product X is a specific vehicle, the client terminal 10 of company A uses the purchased product, store visit / conversation content, inquiry / catalog request as customer data. , Owned WEB log, advertising contact, sales promotion contact, etc.

Further, the client terminal 10 of Company A uses any of the following methods (1) and (2) as a method for vectorizing customer data.

(1) The client terminal 10 of the company A vectorizes the product on the assumption that the product (in the case of a car, the vehicle type) that the customer simultaneously negotiates or purchases is a product having a similar purpose. Next, using the product vector, two customers are randomly extracted, and the near and far of the product vector is learned as a positive example and a negative example.

(2) The client terminal 10 of the company A learns in a fill-in-the-blank problem with a BERT (Bidirectional Encoder Representations from Transformers) model and acquires it from the embedding layer. BERT is a Transformer-based machine learning method for pre-learning natural language processing (NLP). Actually, it is not limited to BERT, and other natural language processing may be used. For example, it may be a distributed expression (word vector) such as Word2Vec. Distributed expression is to embed characters / words in a vector space and regard them as one point in the space, which is also called word embedding.

FIG. 4 shows an example of anonymization (vectorization) of customer data of company A. Here, for the sake of simplification of the explanation, the dimension of the vector is expressed in two dimensions, and the vector group is classified into several segments according to the distance of the vector. For example, it is classified into segments such as "luxury sports car oriented", "luxury SUV oriented", and "low price range oriented".

In the example of anonymization (vectorization) of customer data of company A shown in FIG. 4, the dimension of the vector is expressed in two dimensions, but the actual dimension of the vector is not limited to two dimensions and is 100 dimensions. Each customer is expressed in multiple dimensions with all the elements added.

[1-3. Inference on the server side]
Next, the server-side inference according to the present embodiment will be described with reference to FIGS. 5 and 6. FIG. 5 is an explanatory diagram showing an outline of inference on the server side. FIG. 6 is a schematic diagram that simplifies inference on the server side. The inference on the server side may be performed after AI learning on the server side or at the same time.

As shown in FIG. 5, the mother server 100 (server side) inputs the customer data vector (anonymous information) of each company into the AI on the mother side, and the product purchase probability list (recommendation list) of each customer of each company. ) To get.

At this time, the mother server 100 (server side) targets the purchase probability list of the specific product (for example, the product X purchase probability A company ID list) based on the ID of the specific company, which targets only the customers of the specific company, and the customers of all the companies. The purchase probability list of the specific product (for example, the product X purchase probability common ID list) based on the common ID is acquired.

Then, the mother server 100 (server side) transmits a purchase probability list of the specific product by the ID of the specific company targeting only the customers of the specific company only to the client terminal 10 of the specific company. At this time, the client terminal 10 of the specific company executes the process of expanding the customer near the vector, which will be described later, based on the purchase probability list of the specific product by the ID of the specific company targeting only the customers of the specific company.

In addition, the mother server 100 (server side) distributes advertisements and coupons on SNS to customers of all companies based on a list of purchase probability of specific products with a common ID for customers of all companies. Can be done.

As shown in FIG. 6, when the mother server 100 (server side) wants a list of customers who have a high probability of purchasing the product X of the company A, the mother server 100 (server side) has purchased the product X of the company A in the past. Among the customers who have made the purchase, the information of the customer who has licensed the common ID linkage is input to the AI of the mother side as the correct answer data, and the purchase probability list (recommendation list) of the product X of the company A is acquired. Then, the mother server 100 (server side) distributes advertisements, distributes coupons on SNS, and the like based on the purchase probability list of the product X. Further, the mother server 100 (server side) may return the list to the CRM (Customer Relationship Management) of the company A and perform the vector neighborhood expansion in the CDP of the company A, etc., and after the vector neighborhood expansion, A Enables marketing activities in the company's CRM.

[1-4. Vector neighborhood customer expansion]
Next, the vector neighborhood customer expansion according to the present embodiment will be described with reference to FIG. 7. FIG. 7 is an explanatory diagram showing an outline of vector neighborhood customer expansion.

When inferring the correct answer data on the mother server 100 (server side), only the vector data on the mother side (vector data of the ID-connected customer) is used as the basis, so when returning to the client side CDP, there Extend the neighborhood with the vector of the data in the company.

For example, it is assumed that the client terminal 10 of the company A is a candidate for purchasing the product X by the users U1 and U2 who are the customers from the customer data of the company A. Then, the client terminal 10 of the company A executes the learning process of vectorization in the CDP of the company A (see "Customer vector of the company A" in FIG. 7).

At this time, the mother server 100 (server side) utilizes the data of the users U1 and U4 who are performing ID integration (ID Connect) with the common ID among the users U1 to U4, and uses the AI on the mother side. learn. Here, the users U1 to U4 are described as an example, but in reality, the number of data including the customers of other companies (ID Connected users) is much larger.

The mother server 100 (server side) infers a person who has a high purchase probability of the product X of the company A from the vector of all the customers of all the companies on the mother side. At this time, the user U1 is extracted from the data of the company A (the user U2 is not ID Connected).

Then, the mother server 100 (server side) feeds back U1 to the CDP of company A as a product X purchase candidate. Therefore, the client terminal 10 of the company A expands the customer near the vector in response to the feedback from the mother side. Specifically, as shown in the "customer vector of company A" of the client terminal 10 of company A, in the vector of customer data in company A, the user U2 exists in the vicinity of the user U1. , User U2 is also a candidate for purchasing product X.

[1-5.1st Party Data Area Concept]
As mentioned above, when each company joins the 1st Party data area concept, extremely high-precision personal marketing will be possible. FIG. 8 is a conceptual diagram showing an image of the 1st Party data area concept.

For example, it is possible to target with AI that has learned all customer data that has accepted the common ID Connect of all companies affiliated with the data area (high-precision targeting).

In addition, the customer data of each company does not pass to other companies or the mother side. The customer data of each company is learned by AI on the mother side in the state of anonymous information converted (vectorized) into a list of numerical values (it is OK without issuing the customer data of the company itself).

Also, the higher the quantity and quality of your company's vector data (anonymous information based on your company's customer data), the higher your company's targeting accuracy. Therefore, the accuracy improves as the number of in-house vector data provided to the 1st Party data area increases. On the contrary, the smaller the number of vector data of the company, the lower the accuracy (a mechanism that cannot be freeride).

If the company's vector data is not provided at all, there is only vector data of other companies whose contents are unknown in the data area, and the relationship with the company's customer data and the company's vector data is unknown. By providing the vector data of the company, it is possible to connect the vector data of the company and the vector data of other companies for targeting. In addition, as the content and number of vector data of the company increases, the connection with the vector data of other companies increases, and more information can be obtained from the data area.

In order to improve the targeting accuracy of the company, each company actively provides its own vector data, which creates a virtuous cycle in which a large amount of vector data naturally gathers on the mother side.

According to this embodiment, it is possible to improve data area cooperation and targeting accuracy without each company issuing raw personal information. In addition, since there is a mechanism that does not allow freeride, the overall accuracy will improve synergistically. Also, when viewed from each company, even if they get into the data area, their own data and status cannot be seen by other companies (for example, how many customers visit their stores from the perspective of company A, etc., B. Not known to the company). In addition, when the mother side develops a large number of services (portal site, etc.), it can also be used for mass marketing such as advertisement distribution and SNS.

[2. Mother server configuration example]
Next, the configuration of the mother server 100 according to the embodiment will be described with reference to FIG. FIG. 9 is a diagram showing a configuration example of the mother server 100 according to the embodiment. As shown in FIG. 9, the mother server 100 includes a communication unit 110, a storage unit 120, and a control unit 130.

(Communication unit 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card) or the like. Further, the communication unit 110 is connected to the network N by wire or wirelessly.

(Memory unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element 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 disk. As shown in FIG. 9, the storage unit 120 has a user information database 121, a history information database 122, and an anonymous information database 123.

(User information database 121)
The user information database 121 stores user information about the user U (user) independently collected by the mother server 100. For example, the user information database 121 stores various information such as the attributes of the user U. FIG. 10 is a diagram showing an example of the user information database 121. In the example shown in FIG. 10, the user information database 121 has items such as "user ID (Identifier)", "age", "gender", "home", "work location", and "interest".

The "user ID" indicates identification information for identifying the user U. The "user ID" may be the contact information (telephone number, e-mail address, etc.) of the user U, or may be identification information for identifying the client terminal 10 of the user U.

Further, "age" indicates the age of the user U identified by the user ID. The "age" may be information indicating a specific age of the user U (for example, 35 years old) or information indicating the age of the user U (for example, 30s). .. Alternatively, the "age" may be information indicating the date of birth of the user U, or information indicating the generation of the user U (for example, born in the 1980s). Further, "gender" indicates the gender of the user U identified by the user ID.

Further, "home" indicates the location information of the home of the user U identified by the user ID. In the example shown in FIG. 10, "home" is illustrated with an abstract code such as "LC11", but may be latitude / longitude information or the like. Further, for example, "home" may be an area name or an address.

Further, the "work location" indicates the location information of the work location (school in the case of a student) of the user U identified by the user ID. In the example shown in FIG. 10, the "work location" is shown by an abstract code such as "LC12", but may be latitude / longitude information or the like. Further, for example, the "work location" may be a region name or an address.

Further, "interest" indicates the interest of the user U identified by the user ID. That is, "interest" indicates an object in which the user U identified by the user ID is highly interested. For example, "interest" may be a search query (keyword) or the like that the user U inputs into a search engine and searches. In the example shown in FIG. 10, one "interest" is shown for each user U, but there may be a plurality of "interests".

For example, in the example shown in FIG. 10, the age of the user U identified by the user ID "U1" is "20's", and the gender is "male". Further, for example, the user U identified by the user ID "U1" indicates that his / her home is "LC11". Further, for example, the user U identified by the user ID "U1" indicates that the work location is "LC12". Further, for example, the user U identified by the user ID "U1" indicates that he / she is interested in "sports".

Here, in the example shown in FIG. 10, abstract values such as “U1”, “LC11”, and “LC12” are used for illustration, but “U1”, “LC11”, and “LC12” are specific. Information such as character strings and numerical values shall be stored. Hereinafter, abstract values may also be illustrated in figures relating to other information.

The user information database 121 is not limited to the above, and various information may be stored depending on the purpose. For example, the user information database 121 may store various information about the client terminal 10 of the user U. In addition, the user information database 121 includes demographics (demographic attributes), psychographics (psychological attributes), geographics (geographical attributes), behavioral attributes (behavioral attributes), etc. of the user U. Information about the attribute may be stored. For example, the user information database 121 includes name, family structure, place of origin (local), occupation, position, income, qualification, living style (detached house, apartment, etc.), presence / absence of a car, commuting time, commuting to school / commuting. Memorize information such as routes, commuter pass sections (stations, routes, etc.), frequently used stations (other than the nearest station to your home / work location), lessons (location, time zone, etc.), hobbies, interests, lifestyle, etc. You may.

(History information database 122)
The history information database 122 stores various information related to history information (log data) indicating the behavior of the user U independently collected by the mother server 100. FIG. 11 is a diagram showing an example of the history information database 122. In the example shown in FIG. 11, the history information database 122 has items such as "user ID", "location history", "search history", "browsing history", "purchasing history", and "posting history".

The "user ID" indicates identification information for identifying the user U. Further, the "position history" indicates a position history which is a history of the position and movement of the user U. Further, the "search history" indicates a search history which is a history of a search query input by the user U. Further, the "browsing history" indicates a browsing history which is a history of the contents browsed by the user U. Further, the "purchase history" indicates a purchase history which is a purchase history by the user U. Further, the "posting history" indicates a posting history which is a posting history by the user U. The "posting history" may include a question regarding the property of the user U.

For example, in the example shown in FIG. 11, the user U identified by the user ID "U1" moves according to "location history # 1", searches according to "search history # 1", and "views". It indicates that the content is browsed according to "History # 1", a predetermined product or the like is purchased at a predetermined store or the like according to "Purchase history # 1", and the content is posted according to "Posting history".

Here, in the example shown in FIG. 11, abstractions such as "U1", "position history # 1", "search history # 1", "browsing history # 1", "purchasing history # 1", and "posting history # 1" Although it is illustrated using a typical value, it is shown in "U1", "location history # 1", "search history # 1", "browsing history # 1", "purchase history # 1", and "posting history # 1". , Specific information such as character strings and numerical values shall be stored.

The history information database 122 is not limited to the above, and various information may be stored depending on the purpose. For example, the history information database 122 may store the usage history of a predetermined service of the user U. Further, the history information database 122 may store the visit history of the actual store of the user U, the visit history of the facility, and the like. Further, the history information database 122 may store the payment history and the like in the payment (electronic payment) using the client terminal 10 of the user U.

(Anonymous information database 123)
The anonymous information database 123 stores various information related to the anonymous information (vector data) of the user U. FIG. 12 is a diagram showing an example of the anonymous information database 123. In the example shown in FIG. 12, the anonymous information database 123 has items such as "common ID", "company-specific ID", "company", "vector", and "inference".

“Common ID” indicates a customer ID common in the data area. Further, the "company-specific ID" indicates a unique customer ID for each company. Further, "company" indicates a company that provided the anonymous information (vector data).

Further, the “vector” indicates a vector value obtained by anonymizing (vectorizing) customer data for each company. The "vector" may be multidimensional. That is, the "vector" may be a set of a plurality of vector values.

In addition, "inference" indicates the result of inference based on a vector. For example, the "inference" may be a product purchase probability list (recommendation list) of each customer of each company. The "inference" is not limited to the inference result for each company (for each company ID), but also includes the inference result common to all companies (common ID).

For example, in the example shown in FIG. 12, the user U identified by the common ID "U1" is managed by the customer data of "Company A" by the company-specific ID "U1A", and the customer data is anonymized (vector). It is shown that "inference A1" can be obtained based on the "vector A1".

Here, in the example shown in FIG. 12, abstract values such as "U1", "U1A", "Company A", "Vector A1" and "Inference A1" are used for illustration, but "U1" and "U1A" are shown. , "Company A", "Vector A1" and "Inference A1", information such as specific character strings and numerical values shall be stored. Hereinafter, abstract values may also be illustrated in figures relating to other information.

The anonymous information database 123 is not limited to the above, and various information may be stored depending on the purpose. For example, the anonymous information database 123 may store information about AI on the client side and the mother side. Further, the anonymous information database 123 may store information related to AI learning and inference methods.

(Control unit 130)
Returning to FIG. 9, the description will be continued. The control unit 130 is a controller, and for example, a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like can be used to control the mother server 100. It is realized by executing various programs (corresponding to an example of an information processing program) stored in an internal storage device using a storage area such as a RAM as a work area. In the example shown in FIG. 9, the control unit 130 includes an acquisition unit 131, a learning unit 132, an estimation unit 133, and a providing unit 134.

(Acquisition unit 131)
The acquisition unit 131 acquires the search query input by the user U. For example, when the user U inputs a search query into a search engine or the like and performs a keyword search, the acquisition unit 131 acquires the search query via the communication unit 110.

In addition, the acquisition unit 131 acquires user information regarding the user U via the communication unit 110. For example, the acquisition unit 131 acquires identification information (user ID, etc.) indicating the user U, position information of the user U, attribute information of the user U, and the like from the client terminal 10 of the user U. In addition, the acquisition unit 131 may acquire identification information indicating the user U, attribute information of the user U, and the like at the time of user registration of the user U. Then, the acquisition unit 131 registers the user information in the user information database 121 of the storage unit 120.

In addition, the acquisition unit 131 acquires various historical information (log data) indicating the behavior of the user U via the communication unit 110. For example, the acquisition unit 131 acquires various historical information indicating the behavior of the user U from the client terminal 10 of the user U or from various servers or the like based on the user ID or the like. Then, the acquisition unit 131 registers various history information in the history information database 122 of the storage unit 120.

In addition, the acquisition unit 131 acquires anonymous information obtained by anonymizing (vectorizing) customer data from the client terminals 10 of each company participating in the data area via the communication unit 110. For example, the acquisition unit 131 acquires anonymized information in which customer data is anonymized (vectorized) by the client-side AI from the client terminal 10 of each company via the communication unit 110.

At this time, the acquisition unit 131 acquires anonymized information in which customer data is anonymized (vectorized) from each client terminal 10 of a plurality of companies in different industries. In addition, a competitor (competitor in the same industry) may be included in the plurality of companies.

The anonymous information is multidimensional vector data obtained by vectorizing customer data, and is irreversible information for which there is no means for restoring customer data. That is, the anonymous information is not the data obtained by encrypting the customer data and cannot be decrypted.

(Learning Department 132)
The learning unit 132 performs machine learning of AI using anonymous information from the client terminal 10 of each company. At this time, the learning unit 132 anonymizes (vectorizes) the customer data (data on the mother side) independently collected by the mother server 100 separately from each company into the anonymous information from the client terminal 10 of each company. AI machine learning may be performed by adding information.

Further, the learning unit 132 sets the purpose of the specific company by using the data corresponding to the purpose among the anonymous information from the client terminals 10 of each company as the correct answer data at the time of machine learning of AI. At this time, the learning unit 132 sets the correct answer data as the data obtained by adding the customer data independently collected by the mother server 100 separately from each company to the data corresponding to the purpose among the anonymous information from the client terminals 10 of each company. You may set the purpose of a specific company. Further, when the mother side AI can anonymize (anonymize (vectorize)) the customer data and convert it into anonymous information in the same manner as the client side AI, the customer data independently collected by the mother server 100 is used as it is on the mother side AI. You may enter in.

(Estimation unit 133)
The estimation unit 133 estimates a customer who fits the purpose of a specific company among a plurality of companies by AI that has undergone machine learning by the learning unit 132.

The estimation unit 133 estimates the customers who meet the purpose of the specific company with higher accuracy as the number of anonymous information from the specific company increases among the plurality of companies. On the flip side, the smaller the number of anonymous information from a particular company, the less accurate it is to estimate a customer that fits the purpose of that particular company.

Further, the estimation unit 133 estimates a customer having a high purchase probability of a specific product of a specific company among a plurality of companies, and generates a product purchase probability list listing the customers.

(Providing section 134)
The providing unit 134 provides the client-side AI for anonymizing (vectorizing) the customer data to the client terminals 10 of each of the plurality of companies via the communication unit 110.

Further, the providing unit 134 provides information based on the estimation result by the estimation unit 133 via the communication unit 110. For example, the providing unit 134 provides the client terminal 10 of the specific company with a product purchase probability list listing the customers who have a high purchase probability of the specific product of the specific company via the communication unit 110. As a result, a specific company (client side) distributes advertisements and coupons to customers listed on the mother side, and as a result, acquires new customers and is anonymous about new customers. By providing the information to the mother side, the accuracy of AI inference is further improved.

In addition, the providing unit 134 distributes advertisements and coupons related to specific products of the specific company to the customers listed in the product purchase probability list via the communication unit 110. As a result, the specific company (client side) acquires new customers and provides anonymous information about the new customers to the mother side, so that the accuracy of AI inference is further improved.

[3. Processing procedure]
Next, the processing procedure by the mother server 100 according to the embodiment will be described with reference to FIG. FIG. 13 is a flowchart showing a processing procedure according to the embodiment. The processing procedure shown below is repeatedly executed by the control unit 130 of the mother server 100.

As shown in FIG. 13, the providing unit 134 provides the client-side AI for anonymizing (vectorizing) customer data to each client terminal 10 of a plurality of companies via the communication unit 110 (step S101). ).

Subsequently, the acquisition unit 131 of the mother server 100 acquires anonymized information in which customer data is anonymized (vectorized) by the client-side AI from the client terminals 10 of each company participating in the data area via the communication unit 110. (Step S102). Companies participating in the data area include competitors and companies from different industries.

Subsequently, the learning unit 132 of the mother server 100 performs machine learning of AI using anonymous information from the client terminal 10 of each company (step S103). At this time, the learning unit 132 anonymizes (vectorizes) the anonymous information from the client terminal 10 of each company and the customer data (data on the mother side) independently collected by the mother server 100 separately from each company. Machine learning of AI is performed using the information door.

Subsequently, the learning unit 132 of the mother server 100 receives the data corresponding to the purpose among the anonymous information from the client terminals 10 of each company at the time of machine learning of AI, and the mother server 100 independently receives the data corresponding to the purpose. The purpose of the specific company is set by using the data including the collected customer data as the correct answer data (step S104). It is optional to add customer data on the mother side. Of course, there is no problem even if only the data corresponding to the purpose among the anonymous information from the client terminal 10 of each company is used as the correct answer data.

Subsequently, the estimation unit 133 of the mother server 100 estimates a customer who fits the purpose of a specific company among a plurality of companies by AI that has undergone machine learning by the learning unit 132 (step S105). The estimation unit 133 estimates the customers who meet the purpose of the specific company with higher accuracy as the number of anonymous information from the specific company increases among the plurality of companies.

Subsequently, the estimation unit 133 of the mother server 100 generates a list of customers suitable for the purpose of the specific company (step S106). For example, the estimation unit 133 generates a product purchase probability list that lists customers who have a high purchase probability of a specific product of a specific company.

Subsequently, the providing unit 134 of the mother server 100 provides the client terminal 10 of the specific company with a list of customers suitable for the purpose of the specific company via the communication unit 110 (step S107). For example, the providing unit 134 provides the client terminal 10 of the specific company with a product purchase probability list listing the customers who have a high purchase probability of the specific product of the specific company via the communication unit 110.

Subsequently, the providing unit 134 of the mother server 100 provides information according to the purpose of the specific company to the customer who meets the purpose of the specific company via the communication unit 110 (step S108). For example, the providing unit 134 distributes advertisements and coupons related to specific products to customers listed in the product purchase probability list via the communication unit 110.

[4. Modification example]
The client terminal 10 and the mother server 100 described above may be implemented in various different forms other than the above-described embodiment. Therefore, a modified example of the embodiment will be described below.

(Standalone)
In the above embodiment, a part or all of the processing executed by the mother server 100 may actually be executed by the client terminal 10. For example, the process may be completed stand-alone (with the client terminal 10 alone). In this case, it is assumed that the client terminal 10 is provided with the function of the mother server 100 in the above embodiment. Further, in the above embodiment, since the client terminal 10 is linked with the mother server 100, from the user U's point of view, it seems that the client terminal 10 is also executing the processing of the mother server 100. That is, from another point of view, it can be said that the client terminal 10 includes the mother server 100. Further, the mother server 100 may also be one of a plurality of client terminals 10.

(Basis vector)
Further, in the above embodiment, in order to further enhance the anonymity of the anonymous information, the mother server 100 determines the base vector in advance and collects the difference data from the base vector as anonymous information from the client terminal 10. You may. In this case, only the vector difference data is transmitted from the client terminal 10 to the mother server 100.

(Change of anonymous information format for each company)
Further, in the above embodiment, the format of anonymous information may be changed for each company. For example, when the anonymous information is multidimensional vector data, it is not necessary that the vector data of company A and the vector data of company B have the same type of data in the same dimension. Even if the information has the same contents, the vector data of company A and the vector data of company B may be arranged in different dimensions. It is sufficient if only the AI on the mother side can recognize which data is arranged in which dimension of the multidimensional vector data of each company. In this case, the AI on the mother side may make the vector data of each company consistent (match) prior to learning or inference. For example, the vector data of each company is converted into the vector data of a common format to perform learning and inference.

(AI learning on the client side)
Further, in the above embodiment, the mother server 100 distributes the AI to the client terminals 10 of each company, but in reality, the client terminals 10 of each company independently generate the AI to be used by the company. Information on the generated AI specifications (vector conversion rules, etc.) or AI itself (vector conversion model, etc.) may be provided to the mother server 100.

For example, the client terminal 10 constructs a learning model by using a customer data and a vector value as a data set and using a machine learning method or the like by a neural network. Then, the client terminal 10 inputs the customer data into the constructed learning model and converts the customer data into a real-valued vector composed of multiple dimensions. That is, the client terminal 10 is generated through machine learning using, for example, a plurality of fully connected layers, VAE (Variational Autoencoder), RNN (Recurrent Neural Network), LSTM (Long short-term memory), Transformer, BERT, and the like. The customer data is input to the vector conversion model, and the anonymous information obtained by anonymizing (vectorizing) the customer data is acquired as an output.

The RNN and LSTM may be a neural network based on an attention mechanism. Attention can handle data such as sentences where the arrangement before and after is important. Further, the client terminal 10 may use the same natural language processing model. By generating vector values from customer data using such a model, it is possible to realize the generation of vector values with more emphasis on the order of information.

Then, when the client terminal 10 of each company transmits anonymous information in which customer data is anonymized (vectorized) to the mother server 100 in response to a request from the mother server 100 or voluntarily, or at an arbitrary timing. Then, the client terminal 10 of each company transmits the difference data (or the model itself) of the trained vector conversion model to the mother server 100.

Further, the client terminal 10 of each company may generate a vector conversion model for converting customer data into a vector by using a method such as federated learning (federated learning). Federated learning is a machine learning method that jointly builds a learning model without leaving the data outside the company. For example, in federated learning, the client terminal 10 of each company performs machine learning on the vector conversion model using customer data as training data, and the difference data between the original model and the trained model is used as the mother server 100. Send to. The mother server 100 receives the difference data from each client terminal 10, integrates and learns them, and generates a common model. Then, the mother server 100 provides the generated common model parameters and the like to each client terminal 10. In this way, by using federated learning, it is possible to perform learning without providing customer data, which is learning data, from the client side to the server side, so consideration should be given to the personal information and privacy of the customer. Can be done.

[5. effect〕
As described above, the information processing device (mother server 100) according to the present application uses an acquisition unit that acquires anonymous information obtained by vectorizing customer data from each of a plurality of companies, and AI using anonymous information from each company. A learning department that performs machine learning, an estimation department that estimates customers who meet the purpose of a specific company among multiple companies by AI that has undergone machine learning, and a provision department that provides information based on the estimation results by the estimation department. To be equipped.

The anonymous information is multidimensional vector data obtained by vectorizing customer data, and is irreversible information for which there is no means for restoring customer data.

In addition, the estimation unit estimates the customers who meet the purpose of the specific company with higher accuracy as the number of anonymous information from the specific company increases among the plurality of companies.

In addition, the providing unit provides each of the plurality of companies with a client-side AI for vectorizing customer data. Then, the acquisition unit acquires anonymous information obtained by vectorizing customer data from each of the plurality of companies by the client-side AI.

In addition, the learning department adds the anonymous information obtained by vectorizing the customer data independently collected by the information processing apparatus separately from each company to the anonymous information from each company to perform machine learning of AI.

In addition, the learning department sets the purpose of the specific company by adding the customer data independently collected by the information processing device to the data corresponding to the purpose among the anonymous information from each company. Do machine learning.

In addition, the estimation unit estimates a customer who has a high purchase probability of a specific product of a specific company among a plurality of companies, and generates a product purchase probability list listing the customers. Then, the providing department provides the product purchase probability list to the specific company.

In addition, the providing department distributes advertisements and coupons related to specific products to customers listed on the product purchase probability list.

In addition, the acquisition department acquires anonymous information obtained by vectorizing customer data from each of a plurality of companies in different industries.

By any or combination of the above-mentioned processes, the information processing apparatus according to the present application can provide a mechanism for a data area member company to want to output its own data. Of course, security can be further enhanced by encrypting the vectorized anonymous information. As a result, each company can improve data area cooperation and targeting accuracy without issuing raw personal information. In addition, since there is a mechanism that does not allow freeride, the overall accuracy will improve synergistically. Also, when viewed from each company, even if they get into the data area, their own data and status cannot be seen by other companies (for example, how many customers visit their stores from the perspective of company A, etc., B. Not known to the company). In addition, when the mother side develops a large number of services (portal site, etc.), it can also be used for mass marketing such as advertisement distribution and SNS.

[6. Hardware configuration]
Further, the client terminal 10 and the mother server 100 according to the above-described embodiment are realized by, for example, a computer 1000 having a configuration as shown in FIG. Hereinafter, the mother server 100 will be described as an example. FIG. 14 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to the output device 1010 and the input device 1020, and the arithmetic unit 1030, the primary storage device 1040, the secondary storage device 1050, the output I / F (Interface) 1060, the input I / F 1070, and the network I / F 1080 are bused. It has a form connected by 1090.

The arithmetic unit 1030 operates based on a program stored in the primary storage device 1040 or the secondary storage device 1050, a program read from the input device 1020, or the like, and executes various processes. The arithmetic unit 1030 is realized by, for example, a CPU (Central Processing Unit), a GPU, a TPU, an MPU (Micro Processing Unit), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or the like.

The primary storage device 1040 is a memory device such as a RAM (Random Access Memory) that temporarily stores data used by the arithmetic unit 1030 for various calculations. Further, the secondary storage device 1050 is a storage device in which data used by the calculation device 1030 for various calculations and various databases are registered, and is a ROM (Read Only Memory), an HDD (Hard Disk Drive), and an SSD (Solid). State Drive), flash memory, etc. The secondary storage device 1050 may be internal storage or external storage. Further, the secondary storage device 1050 may be a removable storage medium such as a USB (Universal Serial Bus) memory or an SD (Secure Digital) memory card. Further, the secondary storage device 1050 may be a cloud storage (online storage), NAS (Network Attached Storage), a file server, or the like.

The output I / F 1060 is an interface for transmitting information to be output to an output device 1010 that outputs various information such as a display, a projector, and a printer. For example, USB (Universal Serial Bus) or DVI. (Digital Visual Interface), HDMI (registered trademark) (High Definition Multimedia Interface), etc. are realized by standard connectors. The input I / F 1070 is an interface for receiving information from various input devices 1020 such as a mouse, keyboard, keypad, buttons, and a scanner, and is realized by, for example, USB.

Further, the output I / F 1060 and the input I / F 1070 may be wirelessly connected to the output device 1010 and the input device 1020, respectively. That is, the output device 1010 and the input device 1020 may be wireless devices.

Further, the output device 1010 and the input device 1020 may be integrated like a touch panel. In this case, the output I / F 1060 and the input I / F 1070 may also be integrated as input / output I / F.

The input device 1020 is, for example, an optical recording medium such as a CD (Compact Disc), a DVD (Digital Versatile Disc), a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), or a tape. It may be a device that reads information from a medium, a magnetic recording medium, a semiconductor memory, or the like.

The network I / F 1080 receives data from another device via the network N and sends it to the arithmetic unit 1030, and also transmits the data generated by the arithmetic unit 1030 to the other device via the network N.

The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output I / F 1060 and the input I / F 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040, and executes the loaded program.

For example, when the computer 1000 functions as the mother server 100, the arithmetic unit 1030 of the computer 1000 realizes the function of the control unit 130 by executing the program loaded on the primary storage device 1040. Further, the arithmetic unit 1030 of the computer 1000 may load a program acquired from another device via the network I / F 1080 onto the primary storage device 1040 and execute the loaded program. Further, the arithmetic unit 1030 of the computer 1000 may cooperate with other devices via the network I / F 1080 to call the functions and data of the program from other programs of the other devices and use them.

[7. others〕
Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. Further, the above-mentioned components include those that can be easily assumed by those skilled in the art, those that are substantially the same, that is, those having a so-called equal range. Furthermore, the components described above can be combined as appropriate. Further, various omissions, replacements or changes of the components can be made without departing from the gist of the above-described embodiment.

Further, among the processes described in the above-described embodiment, all or a part of the processes described as being automatically performed can be manually performed, or the processes described as being manually performed can be performed. All or part of it can be done automatically by a known method. In addition, the processing procedure, specific name, and information including various data and parameters shown in the above document and drawings can be arbitrarily changed unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Further, each component of each of the illustrated devices is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of the device is functionally or physically dispersed / physically distributed in an arbitrary unit according to various loads and usage conditions. Can be integrated and configured.

For example, the above-mentioned mother server 100 may be realized by a plurality of server computers, and depending on the function, an external platform or the like may be called by API (Application Programming Interface), network computing, or the like to realize the configuration. Can be changed flexibly.

Further, the above-described embodiments and modifications can be appropriately combined as long as the processing contents do not contradict each other.

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

1 Information processing system 10 Client terminal 100 Mother server 110 Communication unit 120 Storage unit 121 User information database 122 History information database 123 Anonymous information database 130 Control unit 131 Acquisition unit 132 Learning unit 133 Estimating unit 134 Providing unit

Claims (11)

An acquisition department that acquires anonymous information that vectorizes customer data from each of multiple companies,
The learning department that performs machine learning of AI using anonymous information from each company,
An estimation unit that estimates customers who meet the purpose of a specific company among the plurality of companies by AI that has undergone machine learning, and an estimation unit.
It is provided with a providing unit that provides information based on the estimation result by the estimation unit .
The providing unit provides each of the plurality of companies with a client-side AI for vectorizing the customer data.
The acquisition unit acquires anonymous information obtained by vectorizing customer data from each of the plurality of companies by the client-side AI.
An information processing device characterized by this. The information processing apparatus according to claim 1, wherein the anonymous information is multidimensional vector data obtained by vectorizing the customer data, and is irreversible information for which there is no means for restoring the customer data. The estimation unit is characterized in that, among the plurality of companies, the larger the number of anonymous information from the specific company, the more accurately the customer who fits the purpose of the specific company is estimated. The information processing apparatus according to 2. The learning unit is characterized in that the AI is machine-learned by adding anonymous information obtained by vectorizing customer data independently collected by the information processing apparatus separately from each company to the anonymous information from each company. The information processing apparatus according to any one of claims 1 to 3 . An acquisition department that acquires anonymous information that vectorizes customer data from each of multiple companies,
A learning department that performs machine learning of AI using anonymous information from each company,
An estimation unit that estimates customers who meet the purpose of a specific company among the plurality of companies by AI that has undergone machine learning, and an estimation unit.
With a providing unit that provides information based on the estimation result by the estimation unit
With
The learning unit performs machine learning of the AI by adding anonymous information obtained by vectorizing customer data independently collected by the information processing apparatus separately from each company to the anonymous information from each company.
An information processing device characterized by this. At the time of machine learning of the AI, the learning unit adds customer data independently collected by the information processing device separately from the information processing device to the data corresponding to the purpose among the anonymous information from the companies. The information processing apparatus according to any one of claims 1 to 5, wherein the purpose of the specific company is set by using the data as correct answer data. The estimation unit estimates a customer who has a high purchase probability of a specific product of the specific company among the plurality of companies, and generates a product purchase probability list listing the customers.
The information processing device according to any one of claims 1 to 6, wherein the providing unit provides the product purchase probability list to the specific company. The information processing device according to claim 7, wherein the providing unit distributes advertisements and coupons related to the specific product to customers listed in the product purchase probability list. The information processing apparatus according to any one of claims 1 to 8, wherein the acquisition unit acquires anonymous information obtained by vectorizing customer data from each of a plurality of companies in different industries. It is an information processing method executed by an information processing device.
The acquisition process to acquire anonymous information that vectorizes customer data from each of multiple companies,
A learning process for machine learning of AI using anonymous information from each company,
An estimation process for estimating a customer who fits the purpose of a specific company among the plurality of companies by AI that has undergone the machine learning, and an estimation process.
Including a providing process that provides information based on the estimation result by the estimation process.
In the providing process, a client-side AI for vectorizing the customer data is provided to each of the plurality of companies.
In the acquisition process, anonymous information obtained by vectorizing customer data is acquired from each of the plurality of companies by the client-side AI.
An information processing method characterized by the fact that. Acquisition procedure to acquire anonymous information vectorized customer data from each of multiple companies,
A learning procedure for machine learning of AI using anonymous information from each company,
An estimation procedure for estimating a customer who fits the purpose of a specific company among the plurality of companies by AI that has undergone the machine learning, and an estimation procedure.
Let the computer execute the providing procedure that provides the information based on the estimation result by the estimation procedure.
In the provision procedure, a client-side AI for vectorizing the customer data is provided to each of the plurality of companies.
In the acquisition procedure, anonymous information obtained by vectorizing customer data from each of the plurality of companies is acquired by the client-side AI.
An information processing program characterized by this .

Images