WO2022269743A1 - 秘密計算装置、購買予測システム、秘密計算方法、プログラム - Google Patents

秘密計算装置、購買予測システム、秘密計算方法、プログラム Download PDF

Info

Publication number
WO2022269743A1
WO2022269743A1 PCT/JP2021/023551 JP2021023551W WO2022269743A1 WO 2022269743 A1 WO2022269743 A1 WO 2022269743A1 JP 2021023551 W JP2021023551 W JP 2021023551W WO 2022269743 A1 WO2022269743 A1 WO 2022269743A1
Authority
WO
WIPO (PCT)
Prior art keywords
ciphertext
user
attribute information
purchase
purchase history
Prior art date
Application number
PCT/JP2021/023551
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
敏行 森山
修 瀧野
賢治 太田
慧 高橋
Original Assignee
日本電信電話株式会社
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 日本電信電話株式会社 filed Critical 日本電信電話株式会社
Priority to PCT/JP2021/023551 priority Critical patent/WO2022269743A1/ja
Priority to JP2023529265A priority patent/JPWO2022269743A1/ja
Publication of WO2022269743A1 publication Critical patent/WO2022269743A1/ja

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising

Definitions

  • the present invention relates to a secure computing device, a purchase prediction system, a secure computing method, and a program that generate a prediction model while keeping data confidential.
  • a sales business when a business that sells products (hereinafter referred to as a sales business) develops a new product and puts it on the market, it analyzes based on the purchase history data of past purchases of its own products and makes purchase forecasts. ing.
  • Patent Document 1 discloses a method of calculating the interest value for each customer's product attributes from purchase information, product attribute information, and product number information, and predicting the probability of successful purchase.
  • an object of the present invention is to provide a secure computing device capable of generating a precise prediction model while keeping personal attribute information confidential.
  • the secure computing device of the present invention includes a data storage unit, a data matching unit, a data separation unit, a model generation unit, and a purchase prediction unit.
  • the data storage unit receives a ciphertext obtained by encrypting the user's attribute information and the corresponding user ID from the data owner's device, and encrypts the user's purchase history and the corresponding user ID from the seller's device. ciphertexts received and stores these ciphertexts.
  • the data collating unit collates the ciphertext of the attribute information and the ciphertext of the purchase history based on the ciphertext of the user ID by secure calculation processing.
  • the data separation unit extracts the ciphertext of the user ID corresponding to the ciphertext of the attribute information that has not been collated by secure calculation processing.
  • the model generation unit generates a prediction model based on a supervised learning data set including encrypted purchase history and encrypted attribute information matched with the encrypted purchase history.
  • the purchase prediction unit generates a purchase prediction ciphertext based on the unmatched attribute information ciphertext and the prediction model, and transmits the purchase prediction ciphertext to the seller device.
  • the secure computing device of the present invention it is possible to generate a precise prediction model while keeping personal attribute information confidential.
  • FIG. 1 is a system configuration diagram showing the configuration of a purchase prediction system of Example 1.
  • FIG. 2 is a block diagram showing the functional configuration of each device of the purchase prediction system of Example 1.
  • FIG. 4 is a sequence diagram showing the operation of the purchase prediction system of Example 1.
  • FIG. FIG. 4 is a diagram exemplifying attribute information and a ciphertext of a user ID transmitted to a secure computing device; The figure which shows the example of the ciphertext of matched attribute information and purchase information. The figure which shows the example of the ciphertext of the purchase prediction produced
  • the system block diagram which shows the structure of the purchase prediction system of Example 2.
  • FIG. 10 is a block diagram showing the functional configuration of each device of the purchase prediction system of Example 2;
  • FIG. 11 is a sequence diagram showing the operation of the purchase prediction system of Example 2; The figure which shows the functional structural example of a computer.
  • Example 1 used in the scene of extracting new purchase candidate users by the prediction model generated based on the user attribute information possessed by the data owner and the purchase history of the user possessed by the seller. Describe the system.
  • the purchase prediction system 1 of this embodiment includes a data owner device 11, a seller device 12, and a secret computing device 13, each of which is communicably connected to a network.
  • the data owner device 11 includes an attribute information storage unit 110, an attribute information extraction unit 111, and an encryption unit 112.
  • Seller terminal 12 includes purchase history storage unit 120 , decryption unit 121 , encryption unit 122 , purchase history extraction unit 123 , and purchase prediction storage unit 124 .
  • the secure computing device 13 includes a data storage unit 131 , a data matching unit 132 , a data separation unit 133 , a model generation unit 134 and a purchase prediction unit 135 .
  • the attribute information storage unit 110 stores user attribute information in advance in association with the user ID.
  • the attribute information extraction unit 111 extracts attribute information and a user ID from the attribute information storage unit 110 (S111).
  • the encryption unit 112 encrypts the extracted attribute information and user ID and transmits them to the secure computing device 13 (S112).
  • FIG. 4 shows an example of ciphertext of attribute information and user ID sent to the secure computing device 13 . Note that [*] means the ciphertext of *.
  • the purchase history storage unit 120 stores the user's purchase history in advance in association with the user ID.
  • the purchase history extraction unit 123 extracts the purchase history and user ID from the purchase history storage unit 120 (S123).
  • the encryption unit 122 encrypts the extracted purchase history and user ID and transmits them to the secure computing device 13 (S122).
  • the data storage unit 131 of the secure computing device 13 receives the ciphertext obtained by encrypting the user attribute information and the corresponding user ID from the data owner device 11, and stores the user's purchase history and this from the seller device 12. receive the ciphertexts obtained by encrypting the user ID corresponding to the ciphertexts, and store these ciphertexts (S131).
  • the data collating unit 132 collates the ciphertext of the attribute information and the ciphertext of the purchase history based on the ciphertext of the user ID by secure calculation processing (S132).
  • FIG. 5 shows an example of ciphertexts of matched attribute information and purchase information. Note that [*] means the ciphertext of *.
  • the data separation unit 133 extracts the ciphertext of the user ID corresponding to the unmatched ciphertext of the attribute information by the secure calculation process (S133).
  • Model generation unit 134 generates a prediction model based on a supervised learning data set consisting of a purchase history ciphertext and attribute information ciphertext matched with the purchase history ciphertext ( S134).
  • the purchase prediction unit 135 generates a purchase prediction ciphertext based on the unmatched attribute information ciphertext and the prediction model, and transmits the purchase prediction ciphertext to the seller device 12. (S135).
  • FIG. 6 shows an example of a generated purchase prediction ciphertext.
  • ⁇ Seller Device 12 Decoding Unit 121>
  • the decryption unit 121 of the seller's device 12 receives the ciphertext of the purchase prediction, and decrypts the received ciphertext of the purchase prediction (S121).
  • the purchase prediction storage unit 124 stores the decoded purchase prediction (S124).
  • Example 2 The following describes the purchase prediction system of Example 2, which realizes a reduction in processing time by using plaintext data when generating purchase predictions by inputting attribute information into the generated prediction models.
  • the purchase prediction system 2 of this embodiment includes a data owner device 21, a sales business operator device 22, and a secret computing device 23, each of which is communicably connected to a network.
  • the data owner device 21 includes an attribute information storage unit 110, an attribute information extraction unit 111, an encryption unit 112, a decryption unit 113, and a purchase prediction unit 114.
  • Seller terminal 22 includes purchase history storage unit 120 , encryption unit 122 , purchase history extraction unit 123 , and purchase prediction storage unit 124 .
  • Secure computing device 23 includes data storage unit 131 , data matching unit 132 , data separation unit 133 , and model generation unit 134 .
  • the structural difference from the first embodiment is that the decoding unit 113 and the purchase prediction unit 114, which were not present in the data holder device 11 of the first embodiment, are added to the data holding device 21 of the present embodiment.
  • the decryption unit 121 present in the seller device 12 of the first embodiment is omitted in the seller device 22 of the present embodiment
  • the purchase prediction unit 135 present in the secure computing device 13 of the first embodiment is omitted in the secure computing device 23 of this embodiment.
  • the attribute information storage unit 110 stores the user's attribute information in advance in association with the user ID
  • the purchase history storage unit 120 stores the user's purchase history in advance in association with the user ID. ing.
  • steps S111, S112, S123, S122, S131, and S132 are executed in the same manner as in the first embodiment. Operations different from those of the first embodiment will be described in detail below.
  • the data separation unit 133 extracts the ciphertext of the user ID corresponding to the ciphertext of the unmatched attribute information by the secure calculation process, and transmits it to the data owner device 21 (S133-2).
  • the model generation unit 134 generates a prediction model based on a supervised learning data set composed of a purchase history ciphertext and attribute information ciphertext matched to the purchase history ciphertext by secure calculation processing. , to the data owner device 21 (S134).
  • the decryption unit 113 of the data owner device 21 decrypts the encrypted text of the received user ID (S113).
  • ⁇ Attribute extraction unit 111> The attribute information extraction unit 111 extracts attribute information corresponding to the decrypted user ID from the attribute information storage unit 110 (S111-2).
  • ⁇ Purchase prediction unit 114> The purchase prediction unit 114 generates a purchase prediction based on the attribute information corresponding to the decoded user ID and the prediction model, and transmits the purchase prediction to the seller device 22 (S114).
  • the purchase prediction storage unit 124 of the seller device 22 receives the purchase prediction (plain text) and stores the received purchase prediction (S124-2).
  • the attribute information of the data owner and the purchase history of the seller are encrypted and registered in the secret computing device, and the purchase history and attribute information are combined while encrypted in the secret computing device. Therefore, the data can be used without identifying the individual.
  • the prediction model is generated while encrypted in the secure computing device using secure computing technology, the prediction model itself can also be kept confidential.
  • test data when the test data is configured to be input in plain text, it is possible to perform processing several hundred times faster than prediction using secure computation technology.
  • the seller does not need to disclose the purchase history, which is a trade secret, to the data owner.
  • sellers will be able to receive a wide range of purchase forecast data using the attribute information of data holders, which will enable them to make more efficient sales forecasts than collecting attribute information themselves. .
  • the attribute information disclosed by the data owner to the seller can be kept to the minimum necessary. Since the data registered in the secure computing device is processed by secure computing technology, there is no risk of the data being leaked to others.
  • the apparatus of the present invention includes, for example, a single hardware entity, which includes an input unit to which a keyboard can be connected, an output unit to which a liquid crystal display can be connected, and a communication device (for example, a communication cable) capable of communicating with the outside of the hardware entity.
  • a communication device for example, a communication cable
  • CPU Central Processing Unit, which may include cache memory, registers, etc.
  • memory RAM and ROM external storage device such as hard disk
  • input unit, output unit, communication unit a CPU, a RAM, a ROM, and a bus for connecting data to and from an external storage device.
  • the hardware entity may be provided with a device (drive) capable of reading and writing a recording medium such as a CD-ROM.
  • a physical entity with such hardware resources includes a general purpose computer.
  • the external storage device of the hardware entity stores a program necessary for realizing the functions described above and data required for the processing of this program (not limited to the external storage device; It may be stored in a ROM, which is a dedicated storage device). Data obtained by processing these programs are appropriately stored in a RAM, an external storage device, or the like.
  • each program stored in an external storage device or ROM, etc.
  • the data necessary for processing each program are read into the memory as needed, and interpreted, executed and processed by the CPU as appropriate.
  • the CPU realizes a predetermined function (each component expressed as above, . . . unit, . . . means, etc.).
  • a program that describes this process can be recorded on a computer-readable recording medium.
  • Any computer-readable recording medium may be used, for example, a magnetic recording device, an optical disk, a magneto-optical recording medium, a semiconductor memory, or the like.
  • magnetic recording devices hard disk devices, flexible disks, magnetic tapes, etc., as optical discs, DVD (Digital Versatile Disc), DVD-RAM (Random Access Memory), CD-ROM (Compact Disc Read Only Memory), CD-R (Recordable) / RW (ReWritable), etc.
  • magneto-optical recording media such as MO (Magneto-Optical disc), etc. as semiconductor memory, EEP-ROM (Electrically Erasable and Programmable-Read Only Memory), etc. can be used.
  • this program is carried out, for example, by selling, assigning, lending, etc. portable recording media such as DVDs and CD-ROMs on which the program is recorded.
  • the program may be distributed by storing the program in the storage device of the server computer and transferring the program from the server computer to other computers via the network.
  • a computer that executes such a program for example, first stores the program recorded on a portable recording medium or the program transferred from the server computer once in its own storage device. Then, when executing the process, this computer reads the program stored in its own recording medium and executes the process according to the read program. Also, as another execution form of this program, the computer may read the program directly from a portable recording medium and execute processing according to the program, and the program is transferred from the server computer to this computer. Each time, the processing according to the received program may be executed sequentially. In addition, the above-mentioned processing is executed by a so-called ASP (Application Service Provider) type service, which does not transfer the program from the server computer to this computer, and realizes the processing function only by its execution instruction and result acquisition. may be It should be noted that the program in this embodiment includes information that is used for processing by a computer and that conforms to the program (data that is not a direct instruction to the computer but has the property of prescribing the processing of the computer, etc.).
  • ASP
  • a hardware entity is configured by executing a predetermined program on a computer, but at least part of these processing contents may be implemented by hardware.

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
PCT/JP2021/023551 2021-06-22 2021-06-22 秘密計算装置、購買予測システム、秘密計算方法、プログラム WO2022269743A1 (ja)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/JP2021/023551 WO2022269743A1 (ja) 2021-06-22 2021-06-22 秘密計算装置、購買予測システム、秘密計算方法、プログラム
JP2023529265A JPWO2022269743A1 (enrdf_load_stackoverflow) 2021-06-22 2021-06-22

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2021/023551 WO2022269743A1 (ja) 2021-06-22 2021-06-22 秘密計算装置、購買予測システム、秘密計算方法、プログラム

Publications (1)

Publication Number Publication Date
WO2022269743A1 true WO2022269743A1 (ja) 2022-12-29

Family

ID=84545294

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2021/023551 WO2022269743A1 (ja) 2021-06-22 2021-06-22 秘密計算装置、購買予測システム、秘密計算方法、プログラム

Country Status (2)

Country Link
JP (1) JPWO2022269743A1 (enrdf_load_stackoverflow)
WO (1) WO2022269743A1 (enrdf_load_stackoverflow)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017225116A (ja) * 2016-06-17 2017-12-21 パロ・アルト・リサーチ・センター・インコーポレーテッドＰａｌｏ Ａｌｔｏ Ｒｅｓｅａｒｃｈ Ｃｅｎｔｅｒ Ｉｎｃｏｒｐｏｒａｔｅｄ データ再暗号化を介して機密データを保護するためのコンピュータ実施システムおよび方法
JP2018054765A (ja) * 2016-09-27 2018-04-05 日本電気株式会社 データ処理装置、データ処理方法、およびプログラム
JP6351813B1 (ja) * 2017-09-01 2018-07-04 ヤフー株式会社 選択装置、選択方法および選択プログラム
JP2020149693A (ja) * 2019-03-14 2020-09-17 アクタピオ，インコーポレイテッド 生成装置、生成方法および生成プログラム

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2017225116A (ja) * 2016-06-17 2017-12-21 パロ・アルト・リサーチ・センター・インコーポレーテッドＰａｌｏ Ａｌｔｏ Ｒｅｓｅａｒｃｈ Ｃｅｎｔｅｒ Ｉｎｃｏｒｐｏｒａｔｅｄ データ再暗号化を介して機密データを保護するためのコンピュータ実施システムおよび方法
JP2018054765A (ja) * 2016-09-27 2018-04-05 日本電気株式会社 データ処理装置、データ処理方法、およびプログラム
JP6351813B1 (ja) * 2017-09-01 2018-07-04 ヤフー株式会社 選択装置、選択方法および選択プログラム
JP2020149693A (ja) * 2019-03-14 2020-09-17 アクタピオ，インコーポレイテッド 生成装置、生成方法および生成プログラム

Also Published As

Publication number Publication date
JPWO2022269743A1 (enrdf_load_stackoverflow) 2022-12-29

Similar Documents

Publication Publication Date Title
Silva et al. Antecedents of online purchase intention and behaviour: Uncovering unobserved heterogeneity
US20080091508A1 (en) Multidimensional personal behavioral tomography
US12034705B2 (en) Systems and methods for exchanging data between devices
US9336549B2 (en) Systems and methods for performing in-store and online transactions
TAN et al. Evaluation and improvement of procurement process with data analytics
CN109697454B (zh) 一种基于隐私保护的跨设备个体识别方法及装置
JPWO2020071187A1 (ja) 秘密シグモイド関数計算システム、秘密ロジスティック回帰計算システム、秘密シグモイド関数計算装置、秘密ロジスティック回帰計算装置、秘密シグモイド関数計算方法、秘密ロジスティック回帰計算方法、プログラム
CN116738493B (zh) 一种基于分类类别的数据加密存储方法及装置
US12242467B2 (en) Systems and methods for distributed ledger-based data exchange
JP2023179802A (ja) 取引システム及び取引方法
CN110570303A (zh) 业务信息处理方法、装置、存储介质和服务器集群
JP2021197089A (ja) 出力装置、出力方法及び出力プログラム
US20240289789A1 (en) Secure computing system, financial institution server, information processing system, secure computing method, and recording medium
Mehta et al. A pathway to technology integration: eliciting consumer’s behavioural intention to use paytm services
WO2022269743A1 (ja) 秘密計算装置、購買予測システム、秘密計算方法、プログラム
JP2013210933A (ja) リコメンド支援方法、リコメンド支援装置及びプログラム
US7533095B2 (en) Data mining within a message handling system
Rahman et al. Measuring the consumers’ satisfaction and behavior intention on games marketplace technology platform: A perspective of two combination behavior models
JP7327208B2 (ja) データ記録装置、データ記録方法、データ記録プログラム、システム、方法、および、プログラム
JP2004013472A (ja) 顧客データベース融合方法及び融合処理プログラム、融合リレーショナルデータを記録したコンピュータ読み取り可能な記録媒体
Winnie Customer Interface Quality on Customer E-loyalty and E-satisfaction in Malaysia with the Effects of Trustworthiness
US20220374541A1 (en) Database system, distributed processing apparatus, database apparatus, distributed processing method and distributed processing program
Ban et al. Action Attention GRU: A Data-Driven Approach for Enhancing Purchase Predictions in Digital Marketing
US20190355044A1 (en) Information set purchase recommendations
JP2021170257A (ja) プログラム、情報処理方法及び情報処理装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21947030

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023529265

Country of ref document: JP

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21947030

Country of ref document: EP

Kind code of ref document: A1