WO2022116422A1 - 产品推荐方法、装置、电子设备及计算机可读存储介质 - Google Patents

产品推荐方法、装置、电子设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2022116422A1
WO2022116422A1 PCT/CN2021/083076 CN2021083076W WO2022116422A1 WO 2022116422 A1 WO2022116422 A1 WO 2022116422A1 CN 2021083076 W CN2021083076 W CN 2021083076W WO 2022116422 A1 WO2022116422 A1 WO 2022116422A1
Authority
WO
WIPO (PCT)
Prior art keywords
product
user
sequence
client
recommended
Prior art date
Application number
PCT/CN2021/083076
Other languages
English (en)
French (fr)
Inventor
王健宗
李泽远
何安珣
Original Assignee
平安科技(深圳)有限公司
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 平安科技(深圳)有限公司 filed Critical 平安科技(深圳)有限公司
Publication of WO2022116422A1 publication Critical patent/WO2022116422A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION 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
    • G06Q30/00Commerce
    • G06Q30/06Buying, selling or leasing transactions
    • G06Q30/0601Electronic shopping [e-shopping]
    • G06Q30/0631Item recommendations
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60Protecting data
    • G06F21/602Providing cryptographic facilities or services

Definitions

  • the present application relates to the field of big data technologies, and in particular, to a product recommendation method, apparatus, electronic device, and computer-readable storage medium.
  • the feasible method is to use the data of the other party for product collaborative recommendation.
  • product F in platform A is newly added, but product F in platform B has been sold for a period of time, and the data in platform B can be used to recommend users in platform A
  • this method will leak data privacy, and is only suitable for product collaborative recommendation between two platforms sharing data, and the application scope is narrow, which is not conducive to promotion.
  • a product recommendation method provided by this application is applied to the first client, including:
  • the product to be recommended is pushed to the terminal device of each user in the recommended user sequence.
  • the present application also provides a product recommendation method, the method is applied to the second client, including:
  • the recommendation priority value is calculated and screened to obtain an initial recommended user sequence, and the initial user recommended sequence is sent to the first client.
  • the application also provides a product recommendation method, the method is applied to the server, including:
  • the similarity calculation is performed according to all the first decrypted product sequences and all the second decrypted product sequences to obtain the user similarity set, and the user similarity set is sent to the second client.
  • the present application also provides a product recommendation device, the device runs on the first client, including:
  • a product screening module configured to acquire a first product set, receive a second product set sent by a second client, and perform screening according to the first product set and the second product set to obtain a target product sequence, wherein the Both the first product set and the second product set include products to be recommended;
  • the encryption restoration module is used for obtaining the first user set, and constructing the first product scoring sequence of each user in the first user set according to the target product sequence; Perform an encryption operation on each of the first product sequences to obtain a corresponding first encryption standard product sequence, and send all the first encrypted product sequences to the server; receive the initial user recommendation sequence sent by the second client , performing a restoration operation on the initial user recommendation sequence to obtain a recommended user sequence;
  • a product push module configured to push the to-be-recommended product to the terminal device of each user in the recommended user sequence.
  • the present application also provides a product recommendation device, the device runs on the second client, including:
  • a score calculation module configured to obtain the second product set, and send the second product set to the first client; receive the target product sequence sent by the first client; obtain a second user set , constructing the second product scoring sequence of each user in the second user set according to the target product sequence; receiving the public key sent by the server, and using the public key to encrypt each second product sequence, obtaining the corresponding second encryption standard product sequence; sending all the second encryption product sequences to the server, and receiving the user similarity set sent by the server;
  • the priority value calculation and screening module is used to calculate and filter the recommended priority value according to the user similarity set and the second user set, obtain an initial recommended user sequence, and send the initial user recommended sequence to the first customer end.
  • the application also provides a product recommendation device, the device runs on the server, including:
  • a key distribution module configured to construct a key pair using an asymmetric encryption algorithm, and distribute the public key in the key pair to the first client and the second client;
  • a similarity calculation module configured to receive all the first encrypted product sequences sent by the first client and all the second encrypted product sequences sent by the second client; perform decryption operations on all the first encrypted product sequences with the private key, obtain the corresponding first decrypted product sequences, and perform decryption operations on all the received second encrypted product sequences to obtain the corresponding second decrypted product sequences ; Calculate the similarity according to all the first decrypted product sequences and all the second decrypted product sequences, obtain the user similarity set, and send the user similarity set to the second client.
  • the present application also provides an electronic device, the electronic device comprising:
  • the processor executes the computer program stored in the memory to realize the following steps:
  • Receive the public key sent by the server use the public key to encrypt each of the first product sequences to obtain a corresponding first encryption standard product sequence, and send all the first encrypted product sequences to the service end;
  • the product to be recommended is pushed to the terminal device of each user in the recommended user sequence.
  • the present application also provides an electronic device, the electronic device comprising:
  • the processor executes the computer program stored in the memory to realize the following steps:
  • the recommendation priority value is calculated and screened to obtain an initial recommended user sequence, and the initial user recommended sequence is sent to the first client.
  • the present application also provides an electronic device, the electronic device comprising:
  • the processor executes the computer program stored in the memory to realize the following steps:
  • the similarity calculation is performed according to all the first decrypted product sequences and all the second decrypted product sequences to obtain the user similarity set, and the user similarity set is sent to the second client.
  • the present application also provides a computer-readable storage medium, where at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is executed by a processor in an electronic device to implement the following steps:
  • Receive the public key sent by the server use the public key to encrypt each of the first product sequences to obtain a corresponding first encryption standard product sequence, and send all the first encrypted product sequences to the service end;
  • the product to be recommended is pushed to the terminal device of each user in the recommended user sequence.
  • the present application also provides a computer-readable storage medium, where at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is executed by a processor in an electronic device to implement the following steps:
  • the recommendation priority value is calculated and screened to obtain an initial recommended user sequence, and the initial user recommended sequence is sent to the first client.
  • the present application also provides a computer-readable storage medium, where at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is executed by a processor in an electronic device to implement the following steps:
  • the similarity calculation is performed according to all the first decrypted product sequences and all the second decrypted product sequences to obtain the user similarity set, and the user similarity set is sent to the second client.
  • FIG. 1 is a system architecture diagram of a product recommendation provided by an embodiment of the present application
  • FIG. 2 is a schematic flowchart of a product recommendation method provided by an embodiment of the present application applied to a first client;
  • FIG. 3 is a schematic flowchart of a product recommendation method provided by an embodiment of the present application applied to a second client;
  • FIG. 4 is a schematic flowchart of a product recommendation method provided by an embodiment of the present application applied to a server;
  • FIG. 5 is a schematic diagram of a module in which the product recommendation apparatus provided by an embodiment of the present application is applied to a first client;
  • FIG. 6 is a schematic block diagram of a product recommendation apparatus provided by an embodiment of the present application applied to a second client;
  • FIG. 7 is a schematic diagram of a module in which the product recommendation device provided by an embodiment of the present application is applied to a server;
  • FIG. 8 is a schematic diagram of the internal structure of an electronic device for implementing a product recommendation method provided by an embodiment of the present application.
  • the embodiments of the present application provide a product recommendation method.
  • the execution body of the product recommendation method includes, but is not limited to, at least one of electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiments of the present application.
  • the product recommendation method can be executed by software or hardware installed in a terminal device or a server device, and the software can be a blockchain platform.
  • the server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, and the like.
  • the product recommendation method may be implemented by a product recommendation system, and the product recommendation system includes a first client 1 , a second client 2 and a server 3 .
  • the first client 1 is a product monitoring program of the first shopping platform
  • the second client 2 is a product monitoring program of the second platform.
  • the user purchase information of a certain product in the first client 1 recommends the newly listed product, for example: the first client 1 knows that the user's preference for the newly listed product A cannot be recommended to the first client.
  • the user in the terminal 1 recommends, but the product A in the second client 2 has been sold. According to the user purchase information of the product A in the second client 2, the user recommends the product A in the first client 1.
  • the first client 1 obtains a first product set and the second client 2 obtains a second product set, and the first client 1 obtains the first product set and the second product set according to the Perform screening to obtain a target product sequence, wherein both the first product set and the second product set include products to be recommended;
  • the first client 1 obtains the first user set and the second client 2 obtains A second user set, the first client 1 constructs a first product rating sequence for each user in the first user set according to the target product sequence, and the second client 2 constructs a first product rating sequence according to the target product sequence
  • the server encrypts and calculates each user in the first user set and all
  • the similarity value of each user in the second user set is obtained to obtain a user similarity set;
  • the second client 2 performs recommendation priority value calculation and screening according to the user similarity set and the second user set, and obtains The initial recommended user sequence;
  • the first client 1 restores the initial user recommended sequence to obtain the recommended
  • the product recommendation method includes:
  • the first product set and the second product set are product sets sold by different companies, wherein the products include virtual products and physical products, for example, the first product set is sold by company A A collection of products, and the second product set is a collection of products sold by company B.
  • the products to be recommended in the first product set are eliminated to obtain a third product set, wherein the products to be recommended are newly listed but unsold products in the first product set,
  • the products to be recommended are the products that have been sold in the second product set; the products with the same products in the second product set and the third product set are screened out and randomly sorted to obtain the target product sequence, for example: the third product set.
  • the product set includes products B, C, and D
  • the second product set includes products C, D, and F.
  • the same products are C, D, and C and D are randomly sorted to obtain the target product sequence of No. 1 product C and No. 2 product D.
  • the first user set is a set of user information of a company corresponding to the first product set, wherein the user information includes a user name and a product rating of the product purchased by the user.
  • construction of the first product scoring sequence of each user in the first user set according to the target product sequence in the embodiment of the present application includes:
  • Step A obtaining the product rating corresponding to each user in the first user set according to the target product sequence, and obtaining the corresponding initial first product rating sequence;
  • the target product sequence is No. 1 product C, No. 2 product D
  • the first user set includes user A
  • the product score of user A is 4.5 points for product C
  • the score for product F is 3 points
  • the initial first product score of user A is obtained.
  • the sequence is that the No. 1 product has a score of C4.5, and the No. 2 product has a missing D score.
  • Step B Filling the initial first product scoring sequence with missing scores to obtain the first product scoring sequence.
  • a median filling method is used to fill in missing scores on the initial first product scoring sequence to obtain the first product scoring sequence.
  • User A's initial first product rating sequence is 4.5 points for product No. 1, product D for No. 2 is missing, and the median rating of product D in the first user set is 3 points.
  • the product scoring sequence is filled with missing scores, and the first product scoring sequence of User A is obtained as C4.5 for No. 1 product and D3 for No. 2 product.
  • the public key sent by the server is received, and the public key is used to perform an encryption operation on each of the first product sequences to obtain the corresponding The first encryption standard product series.
  • performing an encryption operation on each of the first product sequences using the public key to obtain a corresponding first encryption standard product sequence includes: using a pre-built first user name mapping The table performs a username replacement operation on the first product scoring sequence to obtain a first standard product sequence; wherein, the first username mapping table contains the virtual username mapping corresponding to each username in the first user set
  • the first product scoring sequence is the data of company A
  • company A uses the first user name mapping table to replace the user name corresponding to the first product scoring sequence with a preset virtual user name, and obtain the first user name mapping table.
  • a standard product sequence is the data of company A, and company A uses the first user name mapping table to replace the user name corresponding to the first product scoring sequence with a preset virtual user name, and obtain the first user name mapping table.
  • the first standard product sequence is encrypted by using the public key to obtain the corresponding first encryption standard product sequence. Further, in order to use the first encryption standard The product sequence performs subsequent product recommendation, and in this embodiment of the present application, all the first encrypted product sequences are sent to the server.
  • the user name of the user in the initial recommended user sequence is the virtual user name in the first user name mapping table, and the first user name mapping table needs to be used to The initial recommended user sequence performs the user name restoration operation, and replaces the virtual user name with the real user name to obtain the recommended user sequence.
  • the initial recommended user sequence includes the virtual user name Zhang San, and the real user name corresponding to the virtual user name Zhang San in the first user name mapping table is Li Si, then the second user name mapping table is used to The user name Zhang San in the initial recommended user sequence is replaced with the user name Li Si to obtain the recommended user sequence.
  • the recommended user sequence may be stored in a blockchain node.
  • the product to be recommended is pushed to the terminal device of each user in the recommended user sequence
  • the terminal device includes but is not limited to: a mobile phone, a computer, and a tablet.
  • the product recommendation method includes:
  • the second product set is sent to the first client.
  • the embodiment of the present application receives the target product sequence sent by the first client.
  • the second user set is a set of user information of the company corresponding to the second product set, and further, the second user set of each user in the second user set is constructed according to the target product sequence.
  • the method of the product rating sequence is the same as the method described in S12, and will not be repeated here.
  • the public key sent by the server is received, and the public key is used to perform an encryption operation on each of the second product sequences to obtain the corresponding
  • the second encrypted standard product sequence includes: using a pre-built second user name mapping table to perform a user name replacement operation on the second product scoring sequence to obtain a second standard product sequence, wherein the second user name mapping table
  • the second standard product sequence is encrypted by using the public key to obtain a corresponding second encryption standard product sequence.
  • this embodiment of the present application sends all the second encrypted product sequences to the server, and receives the user similarity set sent by the server.
  • S26 Perform recommendation priority value calculation and screening according to the user similarity set and the second user set to obtain an initial recommended user sequence, and send the initial user recommended sequence to the first client.
  • only users who have collectively purchased the products to be recommended by the second user can help the first client to recommend the products to be recommended. Therefore, obtaining the centralized product score of the second user includes the products to be recommended.
  • users obtain a recommended user set; further, in order to facilitate subsequent screening of the similarity corresponding to the recommended user set in the user similarity set, the users in the first user set can be better recommended products, such as: recommending User A in the user set has purchased product D to be recommended, and the similarity between user A and user B in the first user set is high, so the possibility of user B buying product D to be recommended is also high. Therefore, it is necessary to find the corresponding user in the recommended user set.
  • the second user name mapping table to perform the user name restoration operation on the user similarity set to obtain the target similarity set;
  • the product rating of a user for a product is used to judge the degree of interest of another user in the product to perform product recommendation.
  • the recommendation priority value is calculated and screened to obtain an initial recommended user sequence.
  • the method includes: using a preset priority value algorithm to calculate a recommendation priority value according to the target similarity set and the recommended user set to obtain a recommended priority value set; sorting the recommended priority value set to obtain a standard recommendation priority value set; An initial recommended user sequence is obtained from the users corresponding to the recommended priority value set in the preset ranking range of the standard recommended priority value set.
  • the company corresponding to the first user set is A
  • the company corresponding to the second user set is B. Prove that B is based on the similarity value of the user y in the recommended user set in the target similarity set and the similarity of the product to be recommended by user y.
  • the product rating calculates the recommendation priority value of the corresponding user x, summarizes all recommendation priority values, and obtains a recommendation priority value set, sorts the recommended priority value set from large to small to obtain a standard recommendation priority value set, and finally prioritizes the standard recommendation value.
  • the user names corresponding to the top N recommendation priority values with the highest recommendation priority value in the value set are aggregated to obtain the initial recommended user sequence.
  • the priority value algorithm is as follows:
  • n is the number of users in the recommended user set
  • y is the user in the recommended user set
  • j is the product to be recommended
  • x is the user corresponding to the virtual user name x in the first user name mapping table, sim x
  • y The similarity value between user y and user x in the target similarity set, v y, j is the product rating of user y's product to be recommended, pred x, j is the recommendation priority value of user x's product to be recommended.
  • the user name of the initial recommended user sequence is also virtual on the first client, and in order to restore the virtual user name, the initial user recommendation sequence is sent to the first client.
  • the product recommendation method includes:
  • an asymmetric encryption algorithm is used to construct a key pair, and the public key in the key pair is distributed. to the first client and the second client.
  • the first standard product scoring sequence is the data of company A
  • the second standard product scoring sequence is the data of company B
  • the server is a third-party server trusted by both companies A and B
  • the server Construct a key pair, distribute the public key in the key pair to the first client of Company A and the second client of Company B, keep the private key in the key pair, and use the obtained public key to describe the
  • the first standard product sequence is encrypted to obtain the corresponding first encryption standard product sequence.
  • Company B uses the obtained public key to encrypt the second standard product sequence to obtain the corresponding second encryption standard product sequence; the private key is used to encrypt the second standard product sequence.
  • All the first encrypted product sequences encrypted by company A and all the second encrypted product sequences encrypted by company B received by the server are decrypted, and the corresponding first decrypted product sequence and corresponding second decrypted product are obtained. sequence; the server performs similarity calculation according to all the first decrypted product sequences and all the second decrypted product sequences to obtain the user similarity set.
  • the similarity of the two users is calculated according to the similarity of the product ratings of the same product by the two users, and the similarity calculation is performed by using the following formula:
  • X i represents the i-th product score in the first decrypted product sequence corresponding to user X
  • Y i is the i-th product score in the second decrypted product sequence corresponding to user Y
  • sim(X, Y) represents the user Similarity of X and Y.
  • FIG. 5 it is a functional block diagram of the product recommendation apparatus applied to the first client by the present application.
  • the product recommendation apparatus 100 described in this application may be installed in an electronic device.
  • the product recommendation device may include a product screening module 101, the encryption restoration module 102, and the product push module 103.
  • the modules in the present invention may also be referred to as units, which refer to an electronic A series of computer program segments executed by a device processor and capable of performing fixed functions and stored in the memory of an electronic device.
  • each module/unit is as follows:
  • the product screening module 101 is configured to acquire a first product set, receive a second product set sent by a second client, and perform screening according to the first product set and the second product set to obtain a target product sequence, wherein, Both the first product set and the second product set include products to be recommended.
  • the first product set and the second product set are product sets sold by different companies, wherein the products include virtual products and physical products, for example, the first product set is sold by company A A collection of products, and the second product set is a collection of products sold by company B.
  • the product screening module 101 removes the products to be recommended in the first product set to obtain a third product set, wherein the products to be recommended are new products in the first product set. Unsold products are listed on the shelves, and the products to be recommended are the products that have been sold in the second product set; the product screening module 101 filters out the same products in the second product set and the third product set and Randomly sort to get the target product sequence, for example: the third product set contains products B, C, D, the second product set contains products C, D, F, the same products are C, D, and C and D are randomly sorted to get The target product sequence is No. 1 Product C and No. 2 Product D.
  • the encryption and restoration module 102 is configured to obtain the first user set, construct the first product scoring sequence of each user in the first user set according to the target product sequence; receive the public key sent by the server, use the public key Perform an encryption operation on each of the first product sequences to obtain a corresponding first encryption standard product sequence, and send all the first encrypted product sequences to the server; receive the initial user sent by the second client Recommendation sequence, performing a restoration operation on the initial user recommendation sequence to obtain a recommended user sequence.
  • the first user set is a set of user information of a company corresponding to the first product set, wherein the user information includes a user name and a product rating of the product purchased by the user.
  • the encryption restoration module 102 uses the following means to construct the first product scoring sequence of each user in the first user set, including:
  • the target product sequence is No. 1 product C, No. 2 product D
  • the first user set includes user A
  • the product score of user A is 4.5 points for product C
  • the score for product F is 3 points
  • the initial first product score of user A is obtained.
  • the sequence is that the No. 1 product has a score of C4.5, and the No. 2 product has a missing D score.
  • the initial first product scoring sequence is filled with missing scores to obtain the first product scoring sequence.
  • a median filling method is used to fill in missing scores on the initial first product scoring sequence to obtain the first product scoring sequence.
  • User A's initial first product rating sequence is 4.5 points for product No. 1, product D for No. 2 is missing, and the median rating of product D in the first user set is 3 points.
  • the product scoring sequence is filled with missing scores, and the first product scoring sequence of User A is obtained as C4.5 for No. 1 product and D3 for No. 2 product.
  • the public key sent by the server is received, and the encryption and restoration module 102 uses the public key to perform an operation on each of the first product sequences.
  • An encryption operation is performed to obtain a corresponding first encryption standard product sequence.
  • the encryption restoration module 102 performs an encryption operation on each of the first product sequences by using the following means to obtain a corresponding first encryption standard product sequence, including: using a pre-built first product sequence
  • the user name mapping table performs a user name replacement operation on the first product scoring sequence to obtain a first standard product sequence; wherein, the first user name mapping table contains virtual data corresponding to each user name in the first user set User name mapping table, for example: the first product rating sequence is the data of company A, company A uses the first user name mapping table to replace the user name corresponding to the first product rating sequence with a preset virtual user name , get the first standard product sequence.
  • the first standard product sequence is encrypted by using the public key to obtain the corresponding first encryption standard product sequence. Further, in order to use the first encryption standard The product sequence performs subsequent product recommendation, and in this embodiment of the present application, all the first encrypted product sequences are sent to the server.
  • the user name of the user in the initial recommended user sequence is the virtual user name in the first user name mapping table
  • the encryption restoration module 102 also needs to use the first user name
  • the name mapping table performs a user name restoration operation on the initial recommended user sequence, and replaces the virtual user name with the real user name to obtain the recommended user sequence.
  • the initial recommended user sequence includes the virtual user name Zhang San, and the real user name corresponding to the virtual user name Zhang San in the first user name mapping table is Li Si, then the second user name mapping table is used to The user name Zhang San in the initial recommended user sequence is replaced with the user name Li Si to obtain the recommended user sequence.
  • the recommended user sequence may be stored in a blockchain node.
  • the product pushing module 103 is configured to push the product to be recommended to the terminal device of each user in the recommended user sequence.
  • the product to be recommended is pushed to the terminal device of each user in the recommended user sequence
  • the terminal device includes but is not limited to: a mobile phone, a computer, and a tablet.
  • FIG. 6 it is a functional block diagram of the product recommendation apparatus applied to the second client by the present application.
  • the product recommendation apparatus 200 described in this application may be installed in an electronic device. According to the implemented functions, the product recommendation apparatus may include a score calculation module 201 and a priority value calculation and screening module 202.
  • the modules described in the present invention may also be called units, which refer to a type that can be executed by an electronic device processor, and A series of computer program segments capable of performing a fixed function, which are stored in the memory of an electronic device.
  • each module/unit is as follows:
  • the score calculation module 201 is configured to obtain the second product set, send the second product set to the first client; receive the target product sequence sent by the first client; obtain the second product set.
  • User set construct the second product scoring sequence of each user in the second user set according to the target product sequence; receive the public key sent by the server, and use the public key to encrypt each second product sequence operation to obtain the corresponding second encrypted standard product sequence; send all the second encrypted product sequences to the server, and receive the user similarity set sent by the server;
  • the score calculation module 201 in order for the first client to recommend products to be recommended, sends the second product set to the first client.
  • the score calculation module 201 in this embodiment of the present application receives the target product sequence sent by the first client.
  • the second user set is a set of user information of the company corresponding to the second product set. Further, the score calculation module 201 constructs each of the second user set according to the target product sequence. The user's second product rating sequence.
  • the score calculation module 201 encrypts each of the second product sequences by using the following means
  • the operation to obtain a corresponding second encrypted standard product sequence includes: using a pre-built second user name mapping table to perform a user name replacement operation on the second product scoring sequence to obtain a second standard product sequence, wherein the first The second user name mapping table is a table containing the virtual user name mapping corresponding to each user name in the second user set, and the second standard product sequence is encrypted by using the public key to obtain the corresponding second encryption standard product sequence.
  • the score calculation module 201 in this embodiment of the present application sends all the second encrypted product sequences to the server, and receives the user similarity set sent by the server.
  • the priority value calculation and screening module 202 is configured to calculate and filter the recommendation priority value according to the user similarity set and the second user set, obtain an initial recommended user sequence, and send the initial user recommended sequence to the first user recommendation sequence. a client.
  • the priority value calculation and screening module 202 obtains the second user
  • the product score in the user set includes the users of the product to be recommended, and a recommended user set is obtained; further, in order to facilitate subsequent screening of the similarity corresponding to the recommended user set in the user similarity set, the users in the first user set can be better evaluated.
  • Recommended products are recommended. For example, user A in the recommended user set has purchased product D to be recommended. If the similarity between user A and user B in the first user set is high, then user B is more likely to purchase product D to be recommended.
  • the priority value calculation and screening module 202 uses the second user name mapping table to perform the user name restoration operation on the user similarity set to obtain the target similarity set; further Therefore, the higher the similarity between two users, the more similar the two users’ interests in the same product. Further, the product rating of one user for a product is used to judge the degree of interest of another user in the product to make product recommendations.
  • the priority value calculation and screening module 202 performs recommendation priority value calculation and screening according to the target similarity set and the recommended user set to obtain an initial recommended user sequence , including: using a preset priority value algorithm to calculate a recommendation priority value according to the target similarity set and the recommended user set to obtain a recommended priority value set; sorting the recommended priority value set to obtain a standard recommendation priority value set ; Obtain an initial recommended user sequence from the users corresponding to the recommended priority value set in the preset ranking range of the standard recommended priority value set.
  • the company corresponding to the first user set is A
  • the company corresponding to the second user set is B.
  • the product rating calculates the recommendation priority value of the corresponding user x, summarizes all recommendation priority values, and obtains a recommendation priority value set, sorts the recommended priority value set from large to small to obtain a standard recommendation priority value set, and finally prioritizes the standard recommendation value.
  • the user names corresponding to the top N recommendation priority values with the highest recommendation priority value in the value set are aggregated to obtain the initial recommended user sequence.
  • the priority value algorithm is as follows:
  • n is the number of users in the recommended user set
  • y is the user in the recommended user set
  • j is the product to be recommended
  • x is the user corresponding to the virtual user name x in the first user name mapping table, sim x
  • y The similarity value between user y and user x in the target similarity set, v y, j is the product rating of user y's product to be recommended, pred x, j is the recommendation priority value of user x's product to be recommended.
  • the user name of the initial recommended user sequence is still virtual on the first client.
  • the priority value calculation and screening module 202 sends the initial user recommended sequence to the user. first client.
  • FIG. 7 it is a functional block diagram of the product recommendation apparatus applied to the server by the present application.
  • the product recommendation apparatus 300 described in this application may be installed in an electronic device. According to the implemented functions, the product recommendation apparatus may include a key distribution module 301 and a similarity calculation module 302.
  • the modules described in the present invention may also be referred to as units, which refer to a type that can be executed by an electronic device processor, and A series of computer program segments capable of performing a fixed function, which are stored in the memory of an electronic device.
  • each module/unit is as follows:
  • the key distribution module 301 is configured to construct a key pair using an asymmetric encryption algorithm, and distribute the public key in the key pair to the first client and the second client;
  • the key distribution module 301 uses an asymmetric encryption algorithm to construct a key pair, The public key in the key pair is distributed to the first client and the second client.
  • the similarity calculation module 302 is configured to receive all the first encrypted product sequences sent by the first client and all the second encrypted product sequences sent by the second client; using the key Perform a decryption operation on all the first encrypted product sequences with the private key in the pair to obtain the corresponding first decrypted product sequence and perform a decryption operation on all the received second encrypted product sequences to obtain a corresponding second decrypted product sequence product sequence; perform similarity calculation according to all the first decrypted product sequences and all the second decrypted product sequences to obtain the user similarity set, and send the user similarity set to the second customer end.
  • the first standard product scoring sequence is the data of company A
  • the second standard product scoring sequence is the data of company B
  • the server is a third-party server trusted by both companies A and B
  • the server Construct a key pair, distribute the public key in the key pair to the first client of Company A and the second client of Company B, keep the private key in the key pair, and use the obtained public key to describe the
  • the first standard product sequence is encrypted to obtain the corresponding first encryption standard product sequence.
  • Company B uses the obtained public key to encrypt the second standard product sequence to obtain the corresponding second encryption standard product sequence; the private key is used to encrypt the second standard product sequence.
  • All the first encrypted product sequences encrypted by company A and all the second encrypted product sequences encrypted by company B received by the server are decrypted, and the corresponding first decrypted product sequence and corresponding second decrypted product are obtained. sequence; the server performs similarity calculation according to all the first decrypted product sequences and all the second decrypted product sequences to obtain the user similarity set.
  • the similarity calculation module 302 in the embodiment of the present application calculates the similarity of the two users according to the similarity of the product ratings of the same product by the two users, and uses the following formula to calculate the similarity:
  • X i represents the i-th product score in the first decrypted product sequence corresponding to user X
  • Y i is the i-th product score in the second decrypted product sequence corresponding to user Y
  • sim(X, Y) represents the user Similarity of X and Y.
  • FIG. 8 it is a schematic structural diagram of an electronic device implementing the product recommendation method of the present application.
  • the electronic device 10 may include a processor 11 , a memory 12 and a bus, and may also include a computer program stored in the memory 12 and executable on the processor 11 , such as a product recommendation program 13 .
  • the memory 12 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, magnetic disk, CD etc.
  • the memory 12 may be an internal storage unit of the electronic device 10 in some embodiments, such as a mobile hard disk of the electronic device 10 .
  • the memory 12 may also be an external storage device of the electronic device 10, such as a pluggable mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital) equipped on the electronic device 10. , SD) card, flash memory card (Flash Card), etc.
  • the memory 12 may also include both an internal storage unit of the electronic device 10 and an external storage device.
  • the memory 12 can not only be used to store application software installed in the electronic device 10 and various types of data, such as codes of product recommendation programs, etc., but also can be used to temporarily store data that has been output or will be output.
  • the processor 11 may be composed of integrated circuits, for example, may be composed of a single packaged integrated circuit, or may be composed of multiple integrated circuits packaged with the same function or different functions, including one or more integrated circuits.
  • Central Processing Unit CPU
  • microprocessor digital processing chip
  • graphics processor and combination of various control chips, etc.
  • the processor 11 is the control core (Control Unit) of the electronic device, and uses various interfaces and lines to connect the various components of the entire electronic device, by running or executing the program or module (such as a product) stored in the memory 12. recommend programs, etc.), and call data stored in the memory 12 to perform various functions of the electronic device 10 and process data.
  • the bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (Extended industry standard architecture, EISA for short) bus or the like.
  • PCI peripheral component interconnect
  • EISA Extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on.
  • the bus is configured to enable connection communication between the memory 12 and at least one processor 11 and the like.
  • FIG. 8 only shows an electronic device with components. Those skilled in the art can understand that the structure shown in FIG. 8 does not constitute a limitation on the electronic device 10, and may include fewer or more components than those shown in the drawings. components, or a combination of certain components, or a different arrangement of components.
  • the electronic device 10 may also include a power source (such as a battery) for powering the various components, preferably, the power source may be logically connected to the at least one processor 11 through a power management device, so that the power source can be managed by the power source.
  • the device implements functions such as charge management, discharge management, and power consumption management.
  • the power source may also include one or more DC or AC power sources, recharging devices, power failure detection circuits, power converters or inverters, power status indicators, and any other components.
  • the electronic device 10 may further include various sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.
  • the electronic device 10 may also include a network interface, optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 10 Establish a communication connection with other electronic devices.
  • a network interface optionally, the network interface may include a wired interface and/or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used in the electronic device 10 Establish a communication connection with other electronic devices.
  • the electronic device 10 may further include a user interface, and the user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface or a wireless interface.
  • the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, and the like.
  • the display may also be appropriately called a display screen or a display unit, which is used for displaying information processed in the electronic device 10 and for displaying a visual user interface.
  • the product recommendation program 13 stored in the memory 12 in the electronic device 10 is a combination of multiple computer programs, and when running in the processor 11, a product recommendation method can be implemented.
  • the product recommendation method includes:
  • Receive the public key sent by the server use the public key to encrypt each of the first product sequences to obtain a corresponding first encryption standard product sequence, and send all the first encrypted product sequences to the service end;
  • the product to be recommended is pushed to the terminal device of each user in the recommended user sequence.
  • the product recommendation method includes:
  • the recommendation priority value is calculated and screened to obtain an initial recommended user sequence, and the initial user recommended sequence is sent to the first client.
  • the product recommendation method includes:
  • the similarity calculation is performed according to all the first decrypted product sequences and all the second decrypted product sequences to obtain the user similarity set, and the user similarity set is sent to the second client.
  • modules/units integrated in the electronic device 10 may be stored in a computer-readable storage medium.
  • the computer-readable storage medium may be non-volatile or volatile.
  • the computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory) .
  • the computer usable storage medium may mainly include a stored program area and a stored data area, wherein the stored program area may store an operating system, an application program required for at least one function, and the like; using the created data, etc.
  • modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.
  • the above-mentioned integrated units can be implemented in the form of hardware, or can be implemented in the form of hardware plus software function modules.
  • the blockchain referred to in this application is a new application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, and encryption algorithm.
  • Blockchain essentially a decentralized database, is a series of data blocks associated with cryptographic methods. Each data block contains a batch of network transaction information to verify its Validity of information (anti-counterfeiting) and generation of the next block.
  • the blockchain can include the underlying platform of the blockchain, the platform product service layer, and the application service layer.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Development Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Bioethics (AREA)
  • General Business, Economics & Management (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

一种产品推荐方法、装置、电子设备以及计算机可读存储介质,所述方法包括:根据包含待推荐产品的第一产品集及第二产品集进行筛选,得到目标产品序列;根据目标产品序列构建第一用户集中每个用户的第一产品评分序列及第二用户集中每个用户的第二产品评分序列;根据第一产品评分序列及第二产品评分序列加密两个用户集中用户的相似度得到用户相似度集;根据用户相似度集及第二用户集进行推荐优先值计算及筛选得到推荐用户序列;根据推荐用户序列进行待推荐产品推荐,推荐用户序列可以存储在区块链中。上述方法可以提高产品推荐的灵活性及便利性。

Description

产品推荐方法、装置、电子设备及计算机可读存储介质
本申请要求于2020年12月1日提交中国专利局、申请号为CN202011385258.X、名称为“产品推荐方法、装置、电子设备及计算机可读存储介质”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
技术领域
本申请涉及大数据技术领域,尤其涉及一种产品推荐方法、装置、电子设备及计算机可读存储介质。
背景技术
随着大数据和电子商务的迅猛发展,推荐***成为企业提高市场竞争力的重要工具,然而发明人发现当新产品加入时,该产品在***中不存在用户对其的历史评分数据,因此不能根据传统算法计算用户间的相似度,也就无法为用户进行推荐。
目前可行的办法是利用另一方的数据进行产品协同推荐,例如:平台A中产品F新加入,但是平台B中产品F已经售卖一段时间了,可以利用平台B中的数据向平台A中的用户进行产品推荐,但是该方法会泄露数据隐私,只适用于共享数据的两个平台的产品协同推荐,应用范围较窄,不利于推广。
发明内容
本申请提供的一种产品推荐方法,所述方法应用于第一客户端,包括:
获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;
获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;
接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列;
将所有所述第一加密产品序列发送至所述服务端;
接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列;
将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
本申请还提供一种产品推荐方法,所述方法应用于第二客户端,包括:
获取所述第二产品集,将所述第二产品集发送至所述第一客户端;
接收所述第一客户端发送的所述目标产品序列;
获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;
接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;
将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
本申请还提供一种产品推荐方法,所述方法应用于服务端,包括:
利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
接收所述第一客户端发送的所有所述第一加密产品序列及
所述第二客户端发送的的所有所述第二加密产品序列;
利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及
对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;
根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
本申请还提供一种产品推荐装置,所述装置运行于第一客户端,包括:
产品筛选模块,用于获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;
加密还原模块,用于获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,将所有所述第一加密产品序列发送至所述服务端;接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列;
产品推送模块,用于将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
本申请还提供一种产品推荐装置,所述装置运行于第二客户端,包括:
评分计算模块,用于获取所述第二产品集,将所述第二产品集发送至所述第一客户端;接收所述第一客户端发送的所述目标产品序列;获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
优先值计算筛选模块,用于根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
本申请还提供一种产品推荐装置,所述装置运行于服务端,包括:
密钥分发模块,用于利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
相似度计算模块,用于接收所述第一客户端发送的所有所述第一加密产品序列及所述第二客户端发送的的所有所述第二加密产品序列;利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
本申请还提供一种电子设备,所述电子设备包括:
存储器,存储至少一个计算机程序;及
处理器,执行所述存储器中存储的计算机程序以实现如下步骤:
获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;
获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;
接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,将所有所述第一加密产品序列发送至所述服务端;
接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列;
将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
本申请还提供一种电子设备,所述电子设备包括:
存储器,存储至少一个计算机程序;及
处理器,执行所述存储器中存储的计算机程序以实现如下步骤:
获取所述第二产品集,将所述第二产品集发送至所述第一客户端;
接收所述第一客户端发送的所述目标产品序列;
获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;
接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;
将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
本申请还提供一种电子设备,所述电子设备包括:
存储器,存储至少一个计算机程序;及
处理器,执行所述存储器中存储的计算机程序以实现如下步骤:
利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
接收所述第一客户端发送的所有所述第一加密产品序列及
所述第二客户端发送的的所有所述第二加密产品序列;
利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及
对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;
根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
本申请还提供一种计算机可读存储介质,所述计算机可读存储介质中存储有至少一个计算机程序,所述至少一个计算机程序被电子设备中的处理器执行以实现如下步骤:
获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;
获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;
接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,将所有所述第一加密产品序列发送至所述服务端;
接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列;
将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
本申请还提供一种计算机可读存储介质,所述计算机可读存储介质中存储有至少一个计算机程序,所述至少一个计算机程序被电子设备中的处理器执行以实现如下步骤:
获取所述第二产品集,将所述第二产品集发送至所述第一客户端;
接收所述第一客户端发送的所述目标产品序列;
获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品 评分序列;
接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;
将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
本申请还提供一种计算机可读存储介质,所述计算机可读存储介质中存储有至少一个计算机程序,所述至少一个计算机程序被电子设备中的处理器执行以实现如下步骤:
利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
接收所述第一客户端发送的所有所述第一加密产品序列及
所述第二客户端发送的的所有所述第二加密产品序列;
利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及
对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;
根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
附图说明
图1为本申请一实施例提供的产品推荐的***架构图;
图2为本申请一实施例提供的产品推荐方法应用于第一客户端的流程示意图;
图3为本申请一实施例提供的产品推荐方法应用于第二客户端的流程示意图;
图4为本申请一实施例提供的产品推荐方法应用于服务端的流程示意图;
图5为本申请一实施例提供的产品推荐装置应用于第一客户端的模块示意图;
图6为本申请一实施例提供的产品推荐装置应用于第二客户端的模块示意图;
图7为本申请一实施例提供的产品推荐装置应用于服务端的模块示意图;
图8为本申请一实施例提供的实现产品推荐方法的电子设备的内部结构示意图;
本申请目的的实现、功能特点及优点将结合实施例,参照附图做进一步说明。
具体实施方式
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
本申请实施例提供一种产品推荐方法。所述产品推荐方法的执行主体包括但不限于服务端、终端等能够被配置为执行本申请实施例提供的该方法的电子设备中的至少一种。换言之,所述产品推荐方法可以由安装在终端设备或服务端设备的软件或硬件来执行,所述软件可以是区块链平台。所述服务端包括但不限于:单台服务器、服务器集群、云端服务器或云端服务器集群等。
本申请提供一种产品推荐方法。参见图1所示,本申请实施例中,所述产品推荐方法可以通过一种产品推荐***实现,所述产品推荐***包括第一客户端1、第二客户端2以及服务端3。其中,所述第一客户端1为第一购物平台的产品监控程序,所述第二客户端2为第二平台的产品监控程序,本申请实施例根据所述第二客户端2中已销售的某产品的用户购买信息对所述第一客户端1中新上架的该产品进行推荐,如:所述第一客户端1中得知用户对新上架的产品A的喜好无法对第一客户端1中的用户进行推荐,但是第二客户端2中产品A已经销售过,根据第二客户端2中产品A的用户购买信息对第一客户端1中的产品A进行用户推荐。
详细地,所述第一客户端1获取第一产品集及所述第二客户端2获取第二产品集,所述 第一客户端1根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;所述第一客户端1获取第一用户集及所述第二客户端2获取第二用户集,所述第一客户端1根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列,及所述第二客户端2根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;所述服务端根据所述第一产品评分序列及所述第二产品评分序列加密计算所述第一用户集中的每个用户和所述第二用户集中的每个用户的相似度值,得到用户相似度集;所述第二客户端2根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列;所述第一客户端1对所述初始用户推荐序列进行还原操作,得到推荐用户序列;所述第一客户端1将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
参照图2所示的本申请一实施例提供的应用于第一客户端的产品推荐方法的流程示意图,在本申请实施例中,所述产品推荐方法包括:
S11、获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;
本申请实施例中所述第一产品集及所述第二产品集为不同公司在售的产品集合,其中,所述产品包括虚拟产品和实体产品,例如:第一产品集为A公司在售的产品的集合,第二产品集为B公司在售的产品的集合。
进一步地,本申请实施例中,剔除所述第一产品集中的所述待推荐产品,得到第三产品集,其中,所述待推荐产品为所述第一产品集中新上架未出售的产品,所述待推荐产品为所述第二产品集中已经出售过的产品;筛选出所述第二产品集及所述第三产品集中产品相同的产品并随机排序,得到目标产品序列,例如:第三产品集中包含产品B、C、D,第二产品集中包含产品C、D、F,相同的产品为C、D,将C、D随机排序,得到目标产品序列为1号产品C、2号产品D。
S12、获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;
本申请实施例中,所述第一用户集为所述第一产品集对应的公司的用户信息的集合,其中,所述用户信息包含用户名及用户购买产品的产品评分。
进一步地,本申请实施例中所述根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列,包括:
步骤A、根据所述目标产品序列获取所述第一用户集中每个用户对应的产品评分,得到对应的初始第一产品评分序列;
例如:目标产品序列为1号产品C、2号产品D,第一用户集中包含用户甲,用户甲的产品评分为产品C 4.5分、产品F评分3分,得到用户甲的初始第一产品评分序列为1号产品C4.5分、2号产品D评分缺失。
步骤B、对所述初始第一产品评分序列进行缺失评分填充,得到所述第一产品评分序列。
较佳地,本申请实施例中利用中位数填充方法对所述初始第一产品评分序列进行缺失评分填充,得到所述第一产品评分序列。例如:用户甲的初始第一产品评分序列为1号产品C4.5分、2号产品D评分缺失,第一用户集中产品D的评分中位数为3分,那么对用户甲的初始第一产品评分序列进行缺失评分填充,得到用户甲的第一产品评分序列为1号产品C4.5分、2号产品D3分。
S13、接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,将所有所述第一加密产品序列发送至所述服务端;
本申请实施例中,为了保护在第一客户端用户信息的隐私不被泄露,接收服务端发送 的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列。
详细地,本申请实施例中,所述利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,包括:利用预构建的第一用户名映射表对所述第一产品评分序列进行用户名替换操作,得到第一标准产品序列;其中,所述第一用户名映射表为包含所述第一用户集中每个用户名对应的虚拟用户名映射的表,例如:所述第一产品评分序列为A公司的数据,A公司利用所述第一用户名映射表将第一产品评分序列对应的用户名替换为预设的虚拟用户名,得到第一标准产品序列。进一步地,为了进一步保证数据的安全性,利用所述公钥对所述第一标准产品序列进行加密,得到对应的所述第一加密标准产品序列,进一步地,为了利用所述第一加密标准产品序列进行后续的产品推荐,本申请实施例将所有所述第一加密产品序列发送至所述服务端。
S14、接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列;
详细地,本申请实施例中,所述初始推荐用户序列中的用户的用户名为所述第一用户名映射表中的虚拟用户名,还需要利用所述第一用户名映射表对所述初始推荐用户序列进行用户名还原操作,将虚拟用户名替换为真实用户名,得到推荐用户序列。
例如:所述初始推荐用户序列包含虚拟用户名张三,所述第一用户名映射表中的虚拟用户名张三对应的真实用户名为李四,那么利用所述第二用户名映射表将所述初始推荐用户序列中的用户名张三替换为用户名李四,得到所述推荐用户序列。
本申请的另一实施例中,为了保护数据的隐私性,所述推荐用户序列可以存储在区块链节点中。
S15、将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
本申请实施例中将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备,所述终端设备包括但并不限于:手机、电脑、平板。
参阅图3所示,为本申请一实施例提供的应用于第二客户端的产品推荐方法的流程示意图。在本实施例中,所述产品推荐方法包括:
S21、获取所述第二产品集,将所述第二产品集发送至所述第一客户端;
本申请实施例中,为了所述第一客户端进行待推荐产品推荐,将所述第二产品集发送至所述第一客户端。
S22、接收所述第一客户端发送的所述目标产品序列;
为了后续进行产品推荐计算,本申请实施例接收所述第一客户端发送的所述目标产品序列。
S23、获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;
本申请实施例中所述第二用户集为所述第二产品集对应的公司的用户信息的集合,进一步地所述根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列的方法与S12所述方法相同,在此不再赘述。
S24、接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;
本申请实施例中,为了保护在第二客户端的用户信息的隐私不被泄露,接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列,包括:利用预构建的第二用户名映射表对所述第二产品评分序列进行用户名替换操作,得到第二标准产品序列,其中,所述第二用户名映射表为包含所述第二用户集中每个用户名对应的虚拟用户名映射的表,利用所述公钥对所述第二标准产品序列进行加密,得到对应的第二加密标准产品序列。
S25、将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
为了便于服务器计算所述用户相似度集,本申请实施例将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集。
S26、根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
本申请实施例中,只有所述第二用户集中购买过待推荐产品的用户才能帮助所述第一客户端进行待推荐产品的推荐,因此,获取所述第二用户集中产品评分包含待推荐产品的用户,得到推荐用户集;进一步地,为了便于后续筛选所述用户相似度集中所述推荐用户集对应的相似度更好地对所述第一用户集中的用户进行推荐产品推荐,如:推荐用户集中的用户A购买过待推荐产品D,用户A和第一用户集中的用户B的相似度高,那么用户B购买待推荐产品D的可能性也高,因此,需要寻找推荐用户集中用户对应的相似度,所以利用所述第二用户名映射表对所述用户相似度集进行用户名还原操作,得到目标相似度集;进一步地,两个用户相似度越高,两个用户对相同产品的兴趣也越相似,进一步地,利用一个用户对一个产品的产品评分判断另一个用户对该产品的感兴趣程度从而进行产品推荐,为了计算所述第一用户集中可以推荐待推荐产品的用户,根据所述目标相似度集及所述推荐用户集进行推荐优先值计算及筛选,得到初始推荐用户序列。包括:根据所述目标相似度集及所述推荐用户集利用预设优先值算法进行推荐优先值计算,得到推荐优先值集;对所述推荐优先值集进行排序,得到标准推荐优先值集;从所述标准推荐优先值集预设排名范围的推荐优先值集对应的用户,得到初始推荐用户序列。如:第一用户集对应的公司为A,第二用户集对应的公司为B,证明B根据所述推荐用户集中的用户y在目标相似度集中的相似度值以及用户y的待推荐产品的产品评分计算对应的用户x的推荐优先值,汇总所有推荐优先值,得到推荐优先值集,对所述推荐优先值集进行从大到小的排序得到标准推荐优先值集,最终将标准推荐优先值集中推荐优先值最高的前N个推荐优先值对应的用户名进行汇总得到初始推荐用户序列,所述优先值算法如下:
Figure PCTCN2021083076-appb-000001
其中,n为所述推荐用户集中用户的数量,y为所述推荐用户集中的用户,j为待推荐产品,x为所述第一用户名映射表中的虚拟用户名x对应的用户,sim x,y用户y在目标相似度集与用户x的相似度值,v y,j为用户y的待推荐产品的产品评分,pred x,j为用户x的待推荐产品的推荐优先值。
进一步地,所述初始推荐用户序列的用户名还是所述第一客户端虚拟的,为了对虚拟的用户名进行还原,将所述初始用户推荐序列发送至所述第一客户端。
参阅图4所示,为本申请一实施例提供的应用于服务端的产品推荐方法的流程示意图。在本实施例中,所述产品推荐方法包括:
S31、利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
本申请实施例为了所述第一客户端及所述第二客户端与所述服务端数据交互的安全性,利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端。
S32、接收所述第一客户端发送的所有所述第一加密产品序列及
所述第二客户端发送的的所有所述第二加密产品序列;
S33、利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及
对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;
S34、根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
例如:所述第一标准产品评分序列为A公司的数据,所述第二标准产品评分序列为B公司的数据,所述服务端为A、B公司都信任的第三方服务器,所述服务端构建密钥对,将密钥对中的公钥分发给A公司的第一客户端及B公司的第二客户端,保留密钥对中的私钥,A公司利用得到的公钥对所述第一标准产品序列进行加密,得到对应的第一加密标准产品序列,B公司利用得到的公钥对所述第二标准产品序列进行加密,得到对应的第二加密标准产品序列;利用私钥将服务端接收的A公司加密后的所有所述第一加密产品序列及B公司加密后的所有所述第二加密产品序列进行解密操作,得到对应的第一解密产品序列及对应的第二解密产品序列;所述服务端根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集。
详细地,本申请实施例中根据两个用户对同一产品的产品评分的相似程度从而计算两个用户的相似度,利用下述公式进行相似度计算:
Figure PCTCN2021083076-appb-000002
其中,X i表示用户X对应的第一解密产品序列中的第i个产品评分,Y i为用户Y对应的第二解密产品序列中的第i个产品评分,sim(X,Y)表示用户X和Y的相似度。
如图5所示,是本申请应用于第一客户端的产品推荐装置的功能模块图。
本申请所述产品推荐装置100可以安装于电子设备中。根据实现的功能,所述产品推荐装置可以包括产品筛选模块101、所述加密还原模块102、所述产品推送模块103,本发所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述产品筛选模块101用于获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品。
本申请实施例中所述第一产品集及所述第二产品集为不同公司在售的产品集合,其中,所述产品包括虚拟产品和实体产品,例如:第一产品集为A公司在售的产品的集合,第二产品集为B公司在售的产品的集合。
进一步地,本申请实施例中,所述产品筛选模块101剔除所述第一产品集中的所述待推荐产品,得到第三产品集,其中,所述待推荐产品为所述第一产品集中新上架未出售的产品,所述待推荐产品为所述第二产品集中已经出售过的产品;所述产品筛选模块101筛选出所述第二产品集及所述第三产品集中产品相同的产品并随机排序,得到目标产品序列,例如:第三产品集中包含产品B、C、D,第二产品集中包含产品C、D、F,相同的产品为C、D,将C、D随机排序,得到目标产品序列为1号产品C、2号产品D。
所述加密还原模块102用于获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,将所有所述第一加密产品序列发送至所述服务端;接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列。
本申请实施例中,所述第一用户集为所述第一产品集对应的公司的用户信息的集合,其中,所述用户信息包含用户名及用户购买产品的产品评分。
进一步地,本申请实施例中所述加密还原模块102利用下述手段构建所述第一用户集中每个用户的第一产品评分序列,包括:
根据所述目标产品序列获取所述第一用户集中每个用户对应的产品评分,得到对应的初始第一产品评分序列;
例如:目标产品序列为1号产品C、2号产品D,第一用户集中包含用户甲,用户甲的产品评分为产品C 4.5分、产品F评分3分,得到用户甲的初始第一产品评分序列为1号产品C4.5分、2号产品D评分缺失。
对所述初始第一产品评分序列进行缺失评分填充,得到所述第一产品评分序列。
较佳地,本申请实施例中利用中位数填充方法对所述初始第一产品评分序列进行缺失评分填充,得到所述第一产品评分序列。例如:用户甲的初始第一产品评分序列为1号产品C4.5分、2号产品D评分缺失,第一用户集中产品D的评分中位数为3分,那么对用户甲的初始第一产品评分序列进行缺失评分填充,得到用户甲的第一产品评分序列为1号产品C4.5分、2号产品D3分。
本申请实施例中,为了保护在第一客户端用户信息的隐私不被泄露,接收服务端发送的公钥,所述加密还原模块102利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列。
详细地,本申请实施例中,所述加密还原模块102利用下述手段对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,包括:利用预构建的第一用户名映射表对所述第一产品评分序列进行用户名替换操作,得到第一标准产品序列;其中,所述第一用户名映射表为包含所述第一用户集中每个用户名对应的虚拟用户名映射的表,例如:所述第一产品评分序列为A公司的数据,A公司利用所述第一用户名映射表将第一产品评分序列对应的用户名替换为预设的虚拟用户名,得到第一标准产品序列。进一步地,为了进一步保证数据的安全性,利用所述公钥对所述第一标准产品序列进行加密,得到对应的所述第一加密标准产品序列,进一步地,为了利用所述第一加密标准产品序列进行后续的产品推荐,本申请实施例将所有所述第一加密产品序列发送至所述服务端。
详细地,本申请实施例中,所述初始推荐用户序列中的用户的用户名为所述第一用户名映射表中的虚拟用户名,所述加密还原模块102还需要利用所述第一用户名映射表对所述初始推荐用户序列进行用户名还原操作,将虚拟用户名替换为真实用户名,得到推荐用户序列。
例如:所述初始推荐用户序列包含虚拟用户名张三,所述第一用户名映射表中的虚拟用户名张三对应的真实用户名为李四,那么利用所述第二用户名映射表将所述初始推荐用户序列中的用户名张三替换为用户名李四,得到所述推荐用户序列。
本申请的另一实施例中,为了保护数据的隐私性,所述推荐用户序列可以存储在区块链节点中。
所述产品推送模块103用于将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
本申请实施例中将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备,所述终端设备包括但并不限于:手机、电脑、平板。
如图6所示,是本申请应用于第二客户端的产品推荐装置的功能模块图。
本申请所述产品推荐装置200可以安装于电子设备中。根据实现的功能,所述产品推荐装置可以包括评分计算模块201、优先值计算筛选模块202,本发所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述评分计算模块201用于获取所述第二产品集,将所述第二产品集发送至所述第一客户端;接收所述第一客户端发送的所述目标产品序列;获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;接收服务端发送的公钥, 利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
本申请实施例中,为了所述第一客户端进行待推荐产品推荐,所述评分计算模块201将所述第二产品集发送至所述第一客户端。
为了后续进行产品推荐计算,本申请实施例所述评分计算模块201接收所述第一客户端发送的所述目标产品序列。
本申请实施例中所述第二用户集为所述第二产品集对应的公司的用户信息的集合,进一步地所述评分计算模块201根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列。
本申请实施例中,为了保护在第二客户端的用户信息的隐私不被泄露,接收服务端发送的公钥,所述评分计算模块201利用下述手段对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列,包括:利用预构建的第二用户名映射表对所述第二产品评分序列进行用户名替换操作,得到第二标准产品序列,其中,所述第二用户名映射表为包含所述第二用户集中每个用户名对应的虚拟用户名映射的表,利用所述公钥对所述第二标准产品序列进行加密,得到对应的第二加密标准产品序列。
为了便于服务器计算所述用户相似度集,本申请实施例所述评分计算模块201将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集。
所述优先值计算筛选模块202用于根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
本申请实施例中,只有所述第二用户集中购买过待推荐产品的用户才能帮助所述第一客户端进行待推荐产品的推荐,因此,所述优先值计算筛选模块202获取所述第二用户集中产品评分包含待推荐产品的用户,得到推荐用户集;进一步地,为了便于后续筛选所述用户相似度集中所述推荐用户集对应的相似度更好地对所述第一用户集中的用户进行推荐产品推荐,如:推荐用户集中的用户A购买过待推荐产品D,用户A和第一用户集中的用户B的相似度高,那么用户B购买待推荐产品D的可能性也高,因此,需要寻找推荐用户集中用户对应的相似度,所以所述优先值计算筛选模块202利用所述第二用户名映射表对所述用户相似度集进行用户名还原操作,得到目标相似度集;进一步地,两个用户相似度越高,两个用户对相同产品的兴趣也越相似,进一步地,利用一个用户对一个产品的产品评分判断另一个用户对该产品的感兴趣程度从而进行产品推荐,为了计算所述第一用户集中可以推荐待推荐产品的用户,所述优先值计算筛选模块202根据所述目标相似度集及所述推荐用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,包括:根据所述目标相似度集及所述推荐用户集利用预设优先值算法进行推荐优先值计算,得到推荐优先值集;对所述推荐优先值集进行排序,得到标准推荐优先值集;从所述标准推荐优先值集预设排名范围的推荐优先值集对应的用户,得到初始推荐用户序列。如:第一用户集对应的公司为A,第二用户集对应的公司为B,证明B根据所述推荐用户集中的用户y在目标相似度集中的相似度值以及用户y的待推荐产品的产品评分计算对应的用户x的推荐优先值,汇总所有推荐优先值,得到推荐优先值集,对所述推荐优先值集进行从大到小的排序得到标准推荐优先值集,最终将标准推荐优先值集中推荐优先值最高的前N个推荐优先值对应的用户名进行汇总得到初始推荐用户序列,所述优先值算法如下:
Figure PCTCN2021083076-appb-000003
其中,n为所述推荐用户集中用户的数量,y为所述推荐用户集中的用户,j为待推荐产品,x为所述第一用户名映射表中的虚拟用户名x对应的用户,sim x,y用户y在目标相似度 集与用户x的相似度值,v y,j为用户y的待推荐产品的产品评分,pred x,j为用户x的待推荐产品的推荐优先值。
进一步地,所述初始推荐用户序列的用户名还是所述第一客户端虚拟的,为了对虚拟的用户名进行还原,所述优先值计算筛选模块202将所述初始用户推荐序列发送至所述第一客户端。
如图7所示,是本申请应用于服务端的产品推荐装置的功能模块图。
本申请所述产品推荐装置300可以安装于电子设备中。根据实现的功能,所述产品推荐装置可以包括密钥分发模块301、相似度计算模块302,本发所述模块也可以称之为单元,是指一种能够被电子设备处理器所执行,并且能够完成固定功能的一系列计算机程序段,其存储在电子设备的存储器中。
在本实施例中,关于各模块/单元的功能如下:
所述密钥分发模块301用于利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
本申请实施例为了所述第一客户端及所述第二客户端与所述服务端数据交互的安全性,所述密钥分发模块301利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端。
所述相似度计算模块302用于接收所述第一客户端发送的所有所述第一加密产品序列及所述第二客户端发送的的所有所述第二加密产品序列;利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
例如:所述第一标准产品评分序列为A公司的数据,所述第二标准产品评分序列为B公司的数据,所述服务端为A、B公司都信任的第三方服务器,所述服务端构建密钥对,将密钥对中的公钥分发给A公司的第一客户端及B公司的第二客户端,保留密钥对中的私钥,A公司利用得到的公钥对所述第一标准产品序列进行加密,得到对应的第一加密标准产品序列,B公司利用得到的公钥对所述第二标准产品序列进行加密,得到对应的第二加密标准产品序列;利用私钥将服务端接收的A公司加密后的所有所述第一加密产品序列及B公司加密后的所有所述第二加密产品序列进行解密操作,得到对应的第一解密产品序列及对应的第二解密产品序列;所述服务端根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集。
详细地,本申请实施例中所述相似度计算模块302根据两个用户对同一产品的产品评分的相似程度从而计算两个用户的相似度,利用下述公式进行相似度计算:
Figure PCTCN2021083076-appb-000004
其中,X i表示用户X对应的第一解密产品序列中的第i个产品评分,Y i为用户Y对应的第二解密产品序列中的第i个产品评分,sim(X,Y)表示用户X和Y的相似度。
如图8所示,是本申请实现产品推荐方法的电子设备的结构示意图。
所述电子设备10可以包括处理器11、存储器12和总线,还可以包括存储在所述存储器12中并可在所述处理器11上运行的计算机程序,如产品推荐程序13。
其中,所述存储器12至少包括一种类型的可读存储介质,所述可读存储介质包括闪存、移动硬盘、多媒体卡、卡型存储器(例如:SD或DX存储器等)、磁性存储器、磁盘、光盘等。所述存储器12在一些实施例中可以是电子设备10的内部存储单元,例如该电子设备10的移动硬盘。所述存储器12在另一些实施例中也可以是电子设备10的外部存储设备,例如 电子设备10上配备的插接式移动硬盘、智能存储卡(Smart Media Card,SMC)、安全数字(Secure Digital,SD)卡、闪存卡(Flash Card)等。进一步地,所述存储器12还可以既包括电子设备10的内部存储单元也包括外部存储设备。所述存储器12不仅可以用于存储安装于电子设备10的应用软件及各类数据,例如产品推荐程序的代码等,还可以用于暂时地存储已经输出或者将要输出的数据。
所述处理器11在一些实施例中可以由集成电路组成,例如可以由单个封装的集成电路所组成,也可以是由多个相同功能或不同功能封装的集成电路所组成,包括一个或者多个中央处理器(Central Processing unit,CPU)、微处理器、数字处理芯片、图形处理器及各种控制芯片的组合等。所述处理器11是所述电子设备的控制核心(Control Unit),利用各种接口和线路连接整个电子设备的各个部件,通过运行或执行存储在所述存储器12内的程序或者模块(例如产品推荐程序等),以及调用存储在所述存储器12内的数据,以执行电子设备10的各种功能和处理数据。
所述总线可以是外设部件互连标准(peripheral component interconnect,简称PCI)总线或扩展工业标准结构(extended industry standard architecture,简称EISA)总线等。该总线可以分为地址总线、数据总线、控制总线等。所述总线被设置为实现所述存储器12以及至少一个处理器11等之间的连接通信。
图8仅示出了具有部件的电子设备,本领域技术人员可以理解的是,图8示出的结构并不构成对所述电子设备10的限定,可以包括比图示更少或者更多的部件,或者组合某些部件,或者不同的部件布置。
例如,尽管未示出,所述电子设备10还可以包括给各个部件供电的电源(比如电池),优选地,电源可以通过电源管理装置与所述至少一个处理器11逻辑相连,从而通过电源管理装置实现充电管理、放电管理、以及功耗管理等功能。电源还可以包括一个或一个以上的直流或交流电源、再充电装置、电源故障检测电路、电源转换器或者逆变器、电源状态指示器等任意组件。所述电子设备10还可以包括多种传感器、蓝牙模块、Wi-Fi模块等,在此不再赘述。
进一步地,所述电子设备10还可以包括网络接口,可选地,所述网络接口可以包括有线接口和/或无线接口(如WI-FI接口、蓝牙接口等),通常用于在该电子设备10与其他电子设备之间建立通信连接。
可选地,该电子设备10还可以包括用户接口,用户接口可以是显示器(Display)、输入单元(比如键盘(Keyboard)),可选地,用户接口还可以是标准的有线接口、无线接口。可选地,在一些实施例中,显示器可以是LED显示器、液晶显示器、触控式液晶显示器以及OLED(Organic Light-Emitting Diode,有机发光二极管)触摸器等。其中,显示器也可以适当的称为显示屏或显示单元,用于显示在电子设备10中处理的信息以及用于显示可视化的用户界面。
应该了解,所述实施例仅为说明之用,在专利申请范围上并不受此结构的限制。
所述电子设备10中的所述存储器12存储的产品推荐程序13是多个计算机程序的组合,在所述处理器11中运行时,可以实现一种产品推荐方法。
可选地,当所述电子设备10为第一客户端时,所述产品推荐方法包括:
获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;
获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;
接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,将所有所述第一加密产品序列发送至所述服务端;
接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列;
将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
可选地,当所述电子设备10为第二客户端时,所述产品推荐方法包括:
获取所述第二产品集,将所述第二产品集发送至所述第一客户端;
接收所述第一客户端发送的所述目标产品序列;
获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;
接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;
将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
可选地,当所述电子设备10为服务端时,所述产品推荐方法包括:
利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
接收所述第一客户端发送的所有所述第一加密产品序列及
所述第二客户端发送的的所有所述第二加密产品序列;
利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及
对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;
根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
具体地,所述处理器11对上述计算机程序的具体实现方法可参考图5、图6及图7对应实施例中相关步骤的描述,在此不赘述。
进一步地,所述电子设备10集成的模块/单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。所述计算机可读存储介质可以是非易失性的,也可以是易失性的。所述计算机可读介质可以包括:能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM,Read-Only Memory)。
进一步地,所述计算机可用存储介质可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作***、至少一个功能所需的应用程序等;存储数据区可存储根据区块链节点的使用所创建的数据等。
在本申请所提供的几个实施例中,应该理解到,所揭露的设备,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述模块的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式。
所述作为分离部件说明的模块可以是或者也可以不是物理上分开的,作为模块显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能模块可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用硬件加软件功能模块的形式实现。
对于本领域技术人员而言,显然本申请不限于上述示范性实施例的细节,而且在不背离本申请的精神或基本特征的情况下,能够以其他的具体形式实现本申请。
因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本申请的范围由所附权利要求而不是上述说明限定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附关联图标记视为限制所涉及的权利要求。
本申请所指区块链是分布式数据存储、点对点传输、共识机制、加密算法等计算机技术的新型应用模式。区块链(Blockchain),本质上是一个去中心化的数据库,是一串使用密码学方法相关联产生的数据块,每一个数据块中包含了一批次网络交易的信息,用于验证其信息的有效性(防伪)和生成下一个区块。区块链可以包括区块链底层平台、平台产品服务层以及应用服务层等。
此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。***权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第二等词语用来表示名称,而并不表示任何特定的顺序。
最后应说明的是,以上实施例仅用以说明本申请的技术方案而非限制,尽管参照较佳实施例对本申请进行了详细说明,本领域的普通技术人员应当理解,可以对本申请的技术方案进行修改或等同替换,而不脱离本申请技术方案的精神和范围。

Claims (20)

  1. 一种产品推荐方法,其中,应用于第一客户端,所述方法包括:
    获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;
    获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;
    接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,将所有所述第一加密产品序列发送至所述服务端;
    接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列;
    将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
  2. 如权利要求1所述的产品推荐方法,其中,所述根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列,包括:
    根据所述目标产品序列获取所述第一用户集中每个用户对应的产品评分,得到对应的初始第一产品评分序列;
    对所述初始第一产品评分序列进行缺失评分填充,得到所述第一产品评分序列。
  3. 如权利要求1所述的产品推荐方法,其中,所述利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,包括:
    利用预构建的第一用户名映射表对所述第一产品评分序列进行用户名替换操作,得到第一标准产品序列;
    利用所述公钥对所述第一标准产品序列进行加密,得到对应的所述第一加密标准产品序列。
  4. 一种产品推荐方法,其中,应用于第二客户端,所述方法包括:
    获取所述第二产品集,将所述第二产品集发送至所述第一客户端;
    接收所述第一客户端发送的所述目标产品序列;
    获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;
    接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;
    将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
    根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
  5. 如权利要求4所述的产品推荐方法,其中,所述根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,包括:
    获取所述第二用户集中产品评分包含待推荐产品的用户,得到推荐用户集;
    利用预设的第二用户名映射表对所述用户相似度集进行用户名还原操作,得到目标相似度集;
    根据所述目标相似度集及所述推荐用户集进行推荐优先值计算及筛选,得到初始推荐用户序列。
  6. 如权利要求5所述的产品推荐方法,其中,所述优先值算法如下:
    Figure PCTCN2021083076-appb-100001
    其中,n为所述推荐用户集中用户的数量,y为所述推荐用户集中的用户,j为待推荐产品,x为所述第一用户名映射表中的虚拟用户名x对应的用户,sim x,y用户y在目标相似度集与用户x的相似度值,v y,j为用户y的待推荐产品的产品评分,pred x,j为用户x的待推荐产品的推荐优先值。
  7. 一种产品推荐方法,其中,应用于服务端,所述方法包括:
    利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
    接收所述第一客户端发送的所有所述第一加密产品序列及
    所述第二客户端发送的的所有所述第二加密产品序列;
    利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及
    对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;
    根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
  8. 一种产品推荐装置,运行于第一客户端,其中,所述装置包括:
    产品筛选模块,用于获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;
    加密还原模块,用于获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,将所有所述第一加密产品序列发送至所述服务端;接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列;
    产品推送模块,用于将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
  9. 一种产品推荐装置,运行于第二客户端,其中,所述装置包括:
    评分计算模块,用于获取所述第二产品集,将所述第二产品集发送至所述第一客户端;接收所述第一客户端发送的所述目标产品序列;获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
    优先值计算筛选模块,用于根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
  10. 一种产品推荐装置,运行于服务端,其中,所述装置包括:
    密钥分发模块,用于利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
    相似度计算模块,用于接收所述第一客户端发送的所有所述第一加密产品序列及所述第二客户端发送的的所有所述第二加密产品序列;利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
  11. 一种电子设备,其中,所述电子设备包括:
    至少一个处理器;以及,
    与所述至少一个处理器通信连接的存储器;其中,
    所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下步骤:
    获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;
    获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;
    接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,将所有所述第一加密产品序列发送至所述服务端;
    接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列;
    将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
  12. 如权利要求11所述的电子设备,其中,所述利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,包括:
    利用预构建的第一用户名映射表对所述第一产品评分序列进行用户名替换操作,得到第一标准产品序列;
    利用所述公钥对所述第一标准产品序列进行加密,得到对应的所述第一加密标准产品序列。
  13. 一种电子设备,其中,所述电子设备包括:
    至少一个处理器;以及,
    与所述至少一个处理器通信连接的存储器;其中,
    所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下步骤:
    获取所述第二产品集,将所述第二产品集发送至所述第一客户端;
    接收所述第一客户端发送的所述目标产品序列;
    获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;
    接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;
    将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
    根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
  14. 如权利要求13所述的电子设备,其中,所述根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,包括:
    获取所述第二用户集中产品评分包含待推荐产品的用户,得到推荐用户集;
    利用预设的第二用户名映射表对所述用户相似度集进行用户名还原操作,得到目标相似度集;
    根据所述目标相似度集及所述推荐用户集进行推荐优先值计算及筛选,得到初始推荐用户序列。
  15. 一种电子设备,其中,所述电子设备包括:
    至少一个处理器;以及,
    与所述至少一个处理器通信连接的存储器;其中,
    所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以使所述至少一个处理器能够执行如下步骤:
    利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
    接收所述第一客户端发送的所有所述第一加密产品序列及
    所述第二客户端发送的的所有所述第二加密产品序列;
    利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及
    对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;
    根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
  16. 一种计算机可读存储介质,存储有计算机程序,其中,所述计算机程序被处理器执行时实现如下步骤:
    获取第一产品集,接收第二客户端发送的第二产品集,根据所述第一产品集及所述第二产品集进行筛选,得到目标产品序列,其中,所述第一产品集及所述第二产品集都包含待推荐产品;
    获取第一用户集,根据所述目标产品序列构建所述第一用户集中每个用户的第一产品评分序列;
    接收服务端发送的公钥,利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,将所有所述第一加密产品序列发送至所述服务端;
    接收所述第二客户端发送的初始用户推荐序列,对所述初始用户推荐序列进行还原操作,得到推荐用户序列;
    将所述待推荐产品推送至所述推荐用户序列中每个用户的终端设备。
  17. 如权利要求16所述的计算机可读存储介质,其中,所述利用所述公钥对每个所述第一产品序列进行加密操作,得到对应的第一加密标准产品序列,包括:
    利用预构建的第一用户名映射表对所述第一产品评分序列进行用户名替换操作,得到第一标准产品序列;
    利用所述公钥对所述第一标准产品序列进行加密,得到对应的所述第一加密标准产品序列。
  18. 一种计算机可读存储介质,存储有计算机程序,其中,所述计算机程序被处理器执行时实现如下步骤:
    获取所述第二产品集,将所述第二产品集发送至所述第一客户端;
    接收所述第一客户端发送的所述目标产品序列;
    获取第二用户集,根据所述目标产品序列构建所述第二用户集中每个用户的第二产品评分序列;
    接收服务端发送的公钥,利用所述公钥对每个所述第二产品序列进行加密操作,得到对应的第二加密标准产品序列;
    将所有所述第二加密产品序列发送至所述服务端,接收所述服务端发送的用户相似度集;
    根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,将所述初始用户推荐序列发送至所述第一客户端。
  19. 如权利要求18所述的计算机可读存储介质,其中,所述根据所述用户相似度集及所述第二用户集进行推荐优先值计算及筛选,得到初始推荐用户序列,包括:
    获取所述第二用户集中产品评分包含待推荐产品的用户,得到推荐用户集;
    利用预设的第二用户名映射表对所述用户相似度集进行用户名还原操作,得到目标相似度集;
    根据所述目标相似度集及所述推荐用户集进行推荐优先值计算及筛选,得到初始推荐 用户序列。
  20. 一种计算机可读存储介质,存储有计算机程序,其中,所述计算机程序被处理器执行时实现如下步骤:
    利用非对称加密算法构建密钥对,将所述密钥对中的公钥分发给所述第一客户端及所述第二客户端;
    接收所述第一客户端发送的所有所述第一加密产品序列及
    所述第二客户端发送的的所有所述第二加密产品序列;
    利用所述密钥对中的私钥对所有所述第一加密产品序列进行解密操作,得到对应的所述第一解密产品序列及
    对接收的所有所述第二加密产品序列进行解密操作,得到对应的第二解密产品序列;
    根据所有的所述第一解密产品序列及所有的所述第二解密产品序列进行相似度计算,得到所述用户相似度集,将所述用户相似度集发送至所述第二客户端。
PCT/CN2021/083076 2020-12-01 2021-03-25 产品推荐方法、装置、电子设备及计算机可读存储介质 WO2022116422A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011385258.X 2020-12-01
CN202011385258.XA CN112446765A (zh) 2020-12-01 2020-12-01 产品推荐方法、装置、电子设备及计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2022116422A1 true WO2022116422A1 (zh) 2022-06-09

Family

ID=74740216

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/083076 WO2022116422A1 (zh) 2020-12-01 2021-03-25 产品推荐方法、装置、电子设备及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN112446765A (zh)
WO (1) WO2022116422A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112446765A (zh) * 2020-12-01 2021-03-05 平安科技(深圳)有限公司 产品推荐方法、装置、电子设备及计算机可读存储介质

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102508870A (zh) * 2011-10-10 2012-06-20 南京大学 一种结合评分数据与标签数据的个性化推荐方法
CN102546559A (zh) * 2010-12-29 2012-07-04 北京新媒传信科技有限公司 受限网络中端到端传输数据的方法、设备和***
CN104156388A (zh) * 2014-06-26 2014-11-19 西安邮电大学 个性化搜索中基于信任的隐私保持的协同过滤推荐方法
CN105574430A (zh) * 2015-12-02 2016-05-11 西安邮电大学 协同过滤推荐***中一种新型的隐私保护方法
CN106202331A (zh) * 2016-07-01 2016-12-07 中国传媒大学 分层次隐私保护的推荐***及基于该推荐***的作业方法
CN106375086A (zh) * 2016-08-27 2017-02-01 张春萍 一种基于大数据的互联网教学***的运行方法
CN107766446A (zh) * 2017-09-22 2018-03-06 北京网众共创科技有限公司 资讯信息的推送方法、装置、存储介质及处理器
CN109190023A (zh) * 2018-08-15 2019-01-11 深圳信息职业技术学院 协同推荐的方法、装置及终端设备
CN109360057A (zh) * 2018-10-12 2019-02-19 平安科技(深圳)有限公司 信息推送方法、装置、计算机设备及存储介质
CN110784500A (zh) * 2019-04-02 2020-02-11 北京嘀嘀无限科技发展有限公司 一种信息推送的方法及装置
CN110795624A (zh) * 2019-01-11 2020-02-14 谷歌有限责任公司 分析个性化框架
CN111125544A (zh) * 2019-12-20 2020-05-08 腾讯数码(天津)有限公司 用户推荐方法及装置
CN111985994A (zh) * 2020-08-06 2020-11-24 上海博泰悦臻电子设备制造有限公司 商品推荐方法及相关设备
CN112446765A (zh) * 2020-12-01 2021-03-05 平安科技(深圳)有限公司 产品推荐方法、装置、电子设备及计算机可读存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105279204B (zh) * 2014-07-25 2019-04-09 阿里巴巴集团控股有限公司 信息推送方法和装置
CN106779825A (zh) * 2016-12-02 2017-05-31 乐视控股(北京)有限公司 一种物品推荐方法、装置及电子设备
CN108960899A (zh) * 2018-06-11 2018-12-07 广东因特利信息科技股份有限公司 用于广告投放的用户信息交互方法及***
CN111666481B (zh) * 2019-03-05 2024-04-09 北京沃东天骏信息技术有限公司 数据挖掘方法、装置、计算机可读介质及电子设备
CN111553745A (zh) * 2020-05-08 2020-08-18 深圳前海微众银行股份有限公司 基于联邦的模型更新方法、装置、设备及计算机存储介质

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102546559A (zh) * 2010-12-29 2012-07-04 北京新媒传信科技有限公司 受限网络中端到端传输数据的方法、设备和***
CN102508870A (zh) * 2011-10-10 2012-06-20 南京大学 一种结合评分数据与标签数据的个性化推荐方法
CN104156388A (zh) * 2014-06-26 2014-11-19 西安邮电大学 个性化搜索中基于信任的隐私保持的协同过滤推荐方法
CN105574430A (zh) * 2015-12-02 2016-05-11 西安邮电大学 协同过滤推荐***中一种新型的隐私保护方法
CN106202331A (zh) * 2016-07-01 2016-12-07 中国传媒大学 分层次隐私保护的推荐***及基于该推荐***的作业方法
CN106375086A (zh) * 2016-08-27 2017-02-01 张春萍 一种基于大数据的互联网教学***的运行方法
CN107766446A (zh) * 2017-09-22 2018-03-06 北京网众共创科技有限公司 资讯信息的推送方法、装置、存储介质及处理器
CN109190023A (zh) * 2018-08-15 2019-01-11 深圳信息职业技术学院 协同推荐的方法、装置及终端设备
CN109360057A (zh) * 2018-10-12 2019-02-19 平安科技(深圳)有限公司 信息推送方法、装置、计算机设备及存储介质
CN110795624A (zh) * 2019-01-11 2020-02-14 谷歌有限责任公司 分析个性化框架
CN110784500A (zh) * 2019-04-02 2020-02-11 北京嘀嘀无限科技发展有限公司 一种信息推送的方法及装置
CN111125544A (zh) * 2019-12-20 2020-05-08 腾讯数码(天津)有限公司 用户推荐方法及装置
CN111985994A (zh) * 2020-08-06 2020-11-24 上海博泰悦臻电子设备制造有限公司 商品推荐方法及相关设备
CN112446765A (zh) * 2020-12-01 2021-03-05 平安科技(深圳)有限公司 产品推荐方法、装置、电子设备及计算机可读存储介质

Also Published As

Publication number Publication date
CN112446765A (zh) 2021-03-05

Similar Documents

Publication Publication Date Title
US11743034B2 (en) Systems and methods for establishing a link between identifiers without disclosing specific identifying information
EP3335117B1 (en) Data center privacy
US10609010B2 (en) System, methods and software application for sending secured messages on decentralized networks
US11728974B2 (en) Tenant-based database encryption
CN110768787A (zh) 一种数据加密、解密方法及装置
WO2022141839A1 (zh) 联邦学习模型的更新方法、装置、电子设备及存储介质
WO2021208701A1 (zh) 代码变更的注释生成方法、装置、电子设备及存储介质
WO2021208695A1 (zh) 目标物推荐方法、装置、电子设备及计算机可读存储介质
US11368292B2 (en) Securing data with symmetric keys generated using inaccessible private keys
CN113420049B (zh) 数据流通方法、装置、电子设备及存储介质
US11522686B2 (en) Securing data using key agreement
WO2022227317A1 (zh) 基于区块链的资源转移方法、装置、电子设备及存储介质
WO2021217939A1 (zh) 用于区块链数据处理的方法、装置及可读存储介质
CN112199697A (zh) 基于共享根密钥的信息处理方法、装置、设备及介质
WO2022116422A1 (zh) 产品推荐方法、装置、电子设备及计算机可读存储介质
CN114826736A (zh) 信息共享方法、装置、设备及存储介质
CN112217639B (zh) 数据的加密共享方法、装置、电子设备及计算机存储介质
US10116627B2 (en) Methods and systems for identifying targeted content item for user
CN113806776A (zh) 基于区块链的医疗档案查询方法、装置、电子设备及介质
EP4165821A1 (en) Securing data using key agreement
US11101987B2 (en) Adaptive encryption for entity resolution
JP2019046262A (ja) 情報処理装置、情報処理方法、及び情報処理プログラム
EP2784973A1 (en) Method, system, and device for digital content transmission
CN115643090A (zh) 基于隐私检索的纵向联邦分析方法、装置、设备及介质
CN111130788B (zh) 数据处理方法和***、数据读取方法和iSCSI服务器

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: 21899466

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21899466

Country of ref document: EP

Kind code of ref document: A1