Data encryption method and device for long-term rental apartment public offering pricing model

Abstract

The present invention discloses a data encryption method and device for a long-term rental apartment public offering pricing model, which is applied to the technical fields of big data, data analysis and mining. The method comprises: determining the model parameters that need to be encrypted in the long-term rental apartment public offering pricing model; determining the privacy data that needs to be encrypted when the long-term rental apartment public offering pricing model is used for calculation; transforming the long-term rental apartment public offering pricing model according to the model parameters and the privacy data to obtain a linear function with the model parameters and the privacy data as variables; upon receiving a data encryption request from a client, encrypting the model parameters and sending them to the client, and after receiving the encrypted model parameters, the client calculates the model present value ciphertext based on the encrypted model parameters and the privacy data to be encrypted through the linear function; after receiving the model present value ciphertext sent by the client, decrypting to obtain the present value of the long-term rental apartment public offering pricing model. The present invention realizes high credibility of model data encryption.

Description

Technical Field

[0001] The present invention relates to the field of big data, data analysis and mining technology, and in particular to a data encryption method and device for a public offering pricing model for long-term rental apartments. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] In the public offering pricing model of long-term rental apartments, private data may be used. The server (model provider) needs to protect the privacy of the model to avoid model leakage; the client (data provider) cannot export data locally due to regulatory reasons. The model encryption scheme currently used in the market, if a client uses the model, it is first decrypted on the server, and then the client uploads the data to the server to use the model. If there is a problem with the credibility of the server, there will be problems with the model and data privacy. Therefore, there is currently a need for a reliable data encryption for the public offering pricing model of long-term rental apartments. Summary of the invention

[0004] The embodiment of the present invention provides a data encryption method for a long-term rental apartment public offering pricing model, which is used to implement data encryption for the long-term rental apartment public offering pricing model with strong credibility. The method includes:

[0005] Determine the model parameters that need to be encrypted in the public offering pricing model for long-term rental apartments;

[0006] Determine the privacy data that needs to be encrypted when using the public offering pricing model for long-term rental apartments;

[0007] According to the model parameters and the privacy data, the long-term rental apartment public offering pricing model is transformed to obtain a linear function with the model parameters and the privacy data as variables;

[0008] When receiving a data encryption request from a client, encrypt the model parameters and send them to the client, wherein after receiving the encrypted model parameters, the client calculates the model present value ciphertext based on the encrypted model parameters and the privacy data to be encrypted through the linear function;

[0009] After receiving the model present value ciphertext sent by the client, decrypt it to obtain the present value of the long-term rental apartment public offering pricing model.

[0010] The embodiment of the present invention also provides a data encryption device for a long-term rental apartment public offering pricing model, which is used to implement data encryption for the long-term rental apartment public offering pricing model, and has strong credibility. The device includes:

[0011] Model parameter determination module, used to determine the model parameters that need to be encrypted in the public offering pricing model of long-term rental apartments;

[0012] The privacy data determination module is used to determine the privacy data that needs to be encrypted when calculating the long-term rental apartment public offering pricing model;

[0013] A model transformation module, used to transform the long-term rental apartment public offering pricing model according to the model parameters and the privacy data, and obtain a linear function with the model parameters and the privacy data as variables;

[0014] A model present value ciphertext calculation module, configured to encrypt the model parameters and send them to the client upon receiving a data encryption request from the client, wherein after receiving the encrypted model parameters, the client calculates the model present value ciphertext through the linear function based on the encrypted model parameters and the privacy data to be encrypted;

[0015] The present value decryption module is used to decrypt and obtain the present value of the public offering pricing model of the long-term rental apartment after receiving the model present value ciphertext sent by the client.

[0016] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned data encryption method for the public offering pricing model for long-term rental apartments when executing the computer program.

[0017] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned data encryption method for the public offering pricing model for long-term rental apartments.

[0018] An embodiment of the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned data encryption method for the public offering pricing model for long-term rental apartments.

[0019] In an embodiment of the present invention, model parameters that need to be encrypted in a public offering pricing model for long-term rental apartments are determined; privacy data that needs to be encrypted when calculating using the public offering pricing model for long-term rental apartments is determined; the public offering pricing model for long-term rental apartments is transformed according to the model parameters and the privacy data to obtain a linear function with the model parameters and the privacy data as variables; upon receiving a data encryption request from a client, the model parameters are encrypted and sent to the client, wherein after receiving the encrypted model parameters, the client calculates the model present value ciphertext based on the encrypted model parameters and the privacy data to be encrypted through the linear function; after receiving the model present value ciphertext sent by the client, the present value of the public offering pricing model for long-term rental apartments is obtained by decryption. Compared with the prior art in which the complete model needs to be encrypted on the server side, decrypted when used, and then the client directly uploads the data to the server side to use the model, in an embodiment of the present invention, the model parameters that need to be encrypted in the long-term rental apartment public offering pricing model are determined (rather than all model parameters), and then the privacy data is determined. In this way, the long-term rental apartment public offering pricing model is transformed to obtain a linear function with model parameters and privacy data as variables. The model present value ciphertext is calculated through the linear function, and decrypted to obtain the present value of the long-term rental apartment public offering pricing model. The whole process fully protects the privacy of the model and data and is highly credible. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0021] Figure 1 This is a flow chart of a data encryption method for a public offering pricing model for long-term rental apartments in an embodiment of the present invention;

[0022] Figure 2 A detailed description of the implementation of the CKKS fully homomorphic encryption algorithm in an embodiment of the present invention;

[0023] Figure 3 It is the encryption process for the public offering pricing model of long-term rental apartments in the embodiment of the present invention;

[0024] Figure 4 Schematic diagram of a data encryption device for a public offering pricing model for long-term rental apartments in an embodiment of the present invention;

[0025] Figure 5 Schematic diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0026] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0027] Figure 1 The flowchart of the data encryption method for the public offering pricing model of long-term rental apartments in an embodiment of the present invention includes:

[0028] Step 101, determining the model parameters that need to be encrypted in the long-term rental apartment public offering pricing model;

[0029] Step 102, determining the private data that needs to be encrypted when calculating using the public offering pricing model for long-term rental apartments;

[0030] Step 103, transforming the long-term rental apartment public offering pricing model according to the model parameters and the privacy data to obtain a linear function with the model parameters and the privacy data as variables;

[0031] Step 104, upon receiving a data encryption request from the client, encrypt the model parameters and send them to the client, wherein after receiving the encrypted model parameters, the client calculates the model present value ciphertext based on the encrypted model parameters and the privacy data to be encrypted through the linear function;

[0032] Step 105, after receiving the model present value ciphertext sent by the client, decrypt it to obtain the present value of the long-term rental apartment public offering pricing model.

[0033] In an embodiment of the present invention, compared with the prior art in which the complete model needs to be encrypted on the server side, decrypted when used, and then the client directly uploads the data to the server side to use the model, in an embodiment of the present invention, the model parameters that need to be encrypted in the long-term rental apartment public offering pricing model (rather than all model parameters) are determined, and then the privacy data is determined. In this way, the long-term rental apartment public offering pricing model is transformed to obtain a linear function with model parameters and privacy data as variables. The model present value ciphertext is calculated through the linear function, and decrypted to obtain the present value of the long-term rental apartment public offering pricing model. The whole process fully protects the privacy of the model and data and is highly credible.

[0034] Specifically, the formula for the public offering pricing model for long-term rental apartments is as follows:

[0035]

[0036] Among them, r is the discount rate, which does not need to be kept confidential. r′ is the capitalization rate, which is a model parameter that needs to be encrypted. It should be noted that the model successfully identified the actual business significance of these parameters and determined which ones need to be encrypted, which requires a deep understanding and accurate grasp of the real estate industry.

[0037] Y i is the input of the i-th period, which is public data; C i is the cost expenditure in the i-th period, and is the privacy data that needs to be encrypted by the data provider; subtracting the two gives the net cash flow in the i-th period.

[0038] In step 103, the long-term rental apartment public offering pricing model is transformed according to the model parameters and the privacy data to obtain a linear function with the model parameters and the privacy data as variables. In one embodiment, the formula of the linear function with the model parameters and the privacy data as variables is as follows:

[0039] f(x1,…x n )=a1x1+…+a n x n

[0040]

[0041] x i =Y i -C i (1≤i≤n)

[0042] Among them, a i is the model parameter that needs to be kept confidential; x i Y is the private data that needs to be kept confidential; i is the input for the i-th period; C i is the cost expenditure in period i.

[0043] In one embodiment, the model parameters are encrypted and sent to the client, including: using a CKKS fully homomorphic encryption algorithm to encrypt the model parameters;

[0044] Based on the encrypted model parameters and the private data to be encrypted, the model present value ciphertext is calculated through the linear function, including: using the CKKS fully homomorphic encryption algorithm, based on the encrypted model parameters and the private data to be encrypted, the model present value ciphertext is calculated through the linear function;

[0045] Decryption to obtain the present value of the public offering pricing model for long-term rental apartments, including: using the CKKS fully homomorphic encryption algorithm to decrypt to obtain the present value of the public offering pricing model for long-term rental apartments.

[0046] Homomorphic encryption (HE) technology allows calculations to be performed directly on the encrypted model present value ciphertext, and the calculation result is exactly the same as the calculation result of the plaintext after decryption. According to the supported functions, the current fully homomorphic encryption schemes can be divided into "partial homomorphic encryption" and "fully homomorphic encryption" (FHE). The model present value ciphertext calculations performed using homomorphic encryption are also commonly referred to as homomorphic calculations.

[0047] Partially homomorphic encryption refers to a solution that only supports one type of homomorphic operation, including addition homomorphism and multiplication homomorphism. Partially homomorphic encryption is relatively efficient, but because it supports a single operation, it can only implement simple statistical operations such as mean and linear regression, and cannot meet the actual needs of complex application scenarios.

[0048] Fully homomorphic encryption is a scheme that supports arbitrary homomorphic operations, usually referring to a scheme that supports both additive homomorphism and multiplicative homomorphism. At present, mainstream fully homomorphic encryption can be divided into three categories: layered fully homomorphic encryption represented by BGV / BFV, whose basic operations are addition and multiplication of modular polynomials; bootstrapped fully homomorphic encryption represented by FHEW / TFHE, whose basic operations are NAND gates; approximate fully homomorphic encryption represented by CKKS, whose basic operations are addition and multiplication of floating-point numbers (also applying the layered design concept). Among them, in layered fully homomorphic encryption, the parameter scale grows with the multiplication depth of the algebraic circuit; bootstrapped fully homomorphic encryption does not have this limitation, but its implementation efficiency is much lower than that of layered fully homomorphic schemes. The current main fully homomorphic code open source libraries include HELib, Seal, Palisade, cuHE, NFLLib, HEAAN, etc. Frameworks that use fully homomorphic encryption to implement machine learning include CryptoDL, CryptoNet, FHE-DiNN, etc.

[0049] The embodiment of the present invention is mainly based on the CKKS fully homomorphic encryption algorithm, which protects the privacy of the model provider and the data provider at the same time, and effectively breaks the barriers to the use and intercommunication of the above data. There are two aspects here. One is based on the model present value ciphertext modeling. After the data provider encrypts the private data, the model present value ciphertext modeling is performed on the computing node of the model provider (server), thereby protecting the privacy of the private data; the second is the use of the encrypted model. The model provider will need to encrypt the encrypted model parameters and perform calculations on the computing node of the data provider to obtain the encrypted model parameters. Both the model parameters and the encrypted model parameters can only be decrypted by the model provider, thereby protecting the privacy of the model.

[0050] Figure 2 The specific description of the implementation of the CKKS fully homomorphic encryption algorithm in the embodiment of the present invention is as follows:

[0051] 1)Keygen(Params)→SK,PK,EK

[0052] Key generation algorithm generates private key Secret Key (SK), public key Public Key (PK) and EvaluationKey (EK).

[0053] 2) Encrypt(PK,M) → C

[0054] Encryption algorithm, encrypts plaintext M through PK to generate ciphertext C.

[0055] 3)Decrypt(SK,C)→M

[0056] Decryption algorithm, decrypts the ciphertext C through SK to generate plaintext M.

[0057] 4) EvalAdd(EK,C1,C2)→C3

[0058] The homomorphic addition algorithm performs ciphertext addition operation on the ciphertext C1 (the corresponding plaintext is M1) and C2 (the corresponding plaintext is M2) to generate the ciphertext C3, whose corresponding plaintext is M1+M2.

[0059] 5)EvalAddConst(EK,C1,M)→C2

[0060] The homomorphic constant addition algorithm performs a ciphertext addition operation on the ciphertext C1 (the corresponding plaintext is M1) and the plaintext M to generate the ciphertext C2, whose corresponding plaintext is M1+M.

[0061] 6) EvalMult(EK,C1,C2)→C3

[0062] The homomorphic multiplication algorithm performs ciphertext multiplication on the ciphertext C1 (the corresponding plaintext is M1) and C2 (the corresponding plaintext is M2) to generate the ciphertext C3, whose corresponding plaintext is M1*M2.

[0063] 7)EvalMultConst(EK,C1,M)→C2

[0064] The homomorphic constant multiplication algorithm performs ciphertext multiplication on the ciphertext C1 (the corresponding plaintext is M1) and the plaintext M to generate the ciphertext C2, whose corresponding plaintext is M1*M.

[0065] Figure 3 The encryption process of the public offering pricing model for long-term rental apartments in an embodiment of the present invention includes:

[0066] Step 301, when receiving the data encryption request from the client, the (server) calls the Keygen algorithm in the CKKS fully homomorphic encryption algorithm to generate the private key SK, the public key PK and the evaluation key EK;

[0067] Step 302: Call the Encrypt algorithm c in the CKKS fully homomorphic encryption algorithm according to the public key. i =Encrypt(PK,a i )(1≤i≤n) encrypts the model parameters to obtain encrypted model parameters c1,…c n , send the evaluation key and encrypted model parameters to the client;

[0068] Step 303: The client calls the EvalMultConst algorithm in the CKKS fully homomorphic encryption algorithm based on the evaluation key, the encrypted model parameters, and the private data to be encrypted. pi =EvalMultConst(EK,c i ,x i )(1≤i≤n), calculate the single model present value ciphertext, and then repeatedly call the EvalAdd algorithm in the CKKS fully homomorphic encryption algorithm Calculate the sum c of the ciphertext of the present value of multiple single-item models p , obtain the model present value ciphertext, wherein the EvalMultConst algorithm and the EvalAdd algorithm are used to calculate the model present value ciphertext for the linear function.

[0069] Step 304, after receiving the model present value ciphertext sent by the client, the (server) calls the Decrypt algorithm P=Decrypt(SK,c p ), decrypt and obtain the present value P of the public offering pricing model for long-term rental apartments.

[0070] To summarize, in the method proposed in the embodiment of the present invention, the model parameters that need to be encrypted in the public offering pricing model of long-term rental apartments are determined; the privacy data that needs to be encrypted when calculating using the public offering pricing model of long-term rental apartments is determined; according to the model parameters and the privacy data, the public offering pricing model of long-term rental apartments is transformed to obtain a linear function with the model parameters and the privacy data as variables; when receiving a data encryption request from the client, the model parameters are encrypted and sent to the client, wherein after receiving the encrypted model parameters, the client calculates the model present value ciphertext based on the encrypted model parameters and the privacy data to be encrypted through the linear function; after receiving the model present value ciphertext sent by the client, the present value of the public offering pricing model of long-term rental apartments is obtained by decryption. Compared with the prior art in which the complete model needs to be encrypted on the server side, decrypted when used, and then the client directly uploads the data to the server side to use the model, in an embodiment of the present invention, the model parameters that need to be encrypted in the long-term rental apartment public offering pricing model are determined (rather than all model parameters), and then the privacy data is determined. In this way, the long-term rental apartment public offering pricing model is transformed to obtain a linear function with model parameters and privacy data as variables. The model present value ciphertext is calculated through the linear function, and decrypted to obtain the present value of the long-term rental apartment public offering pricing model. The whole process fully protects the privacy of the model and data and is highly credible.

[0071] An embodiment of the present invention also proposes a data encryption device for a public offering pricing model for long-term rental apartments. The principle of the device is similar to the data encryption method for a public offering pricing model for long-term rental apartments, and will not be repeated here.

[0072] Figure 4 This is a schematic diagram of a data encryption device for a public offering pricing model for long-term rental apartments in an embodiment of the present invention, comprising:

[0073] Model parameter determination module 401, used to determine the model parameters that need to be encrypted in the long-term rental apartment public offering pricing model;

[0074] The privacy data determination module 402 is used to determine the privacy data that needs to be encrypted when calculating using the public offering pricing model for long-term rental apartments;

[0075] A model transformation module 403, for transforming the long-term rental apartment public offering pricing model according to the model parameters and the privacy data, to obtain a linear function with the model parameters and the privacy data as variables;

[0076] The model present value ciphertext calculation module 404 is used to encrypt the model parameters and send them to the client when receiving a data encryption request from the client, wherein after receiving the encrypted model parameters, the client calculates the model present value ciphertext based on the encrypted model parameters and the privacy data to be encrypted through the linear function;

[0077] The present value decryption module 405 is used to decrypt and obtain the present value of the public offering pricing model of the long-term rental apartment after receiving the model present value ciphertext sent by the client.

[0078] In one embodiment, the model parameter that needs to be encrypted is the capitalization rate, and the private data that needs to be encrypted is the cost expenditure.

[0079] In one embodiment, the formula of the linear function with model parameters and privacy data as variables is as follows:

[0080] f(x1,…x n )=a1x1+…+a n x n

[0081]

[0082] x i =Y i -C i (1≤i≤n)

[0083] Among them, a i is the model parameter that needs to be kept confidential; x i Y is the private data that needs to be kept confidential; i is the input for the i-th period; C i is the cost expenditure in period i.

[0084] In one embodiment, the model present value ciphertext calculation module has a function for:

[0085] Use the CKKS fully homomorphic encryption algorithm to encrypt the model parameters;

[0086] Using the CKKS fully homomorphic encryption algorithm, based on the encrypted model parameters and the private data to be encrypted, the model present value ciphertext is calculated through the linear function;

[0087] The present value decryption module is specifically used to: use the CKKS fully homomorphic encryption algorithm to decrypt and obtain the present value of the long-term rental apartment public offering pricing model.

[0088] In one embodiment, the model present value ciphertext calculation module is specifically used for:

[0089] When receiving the client's data encryption request, call the Keygen algorithm in the CKKS fully homomorphic encryption algorithm to generate the private key, public key and evaluation key;

[0090] According to the public key, the Encrypt algorithm in the CKKS fully homomorphic encryption algorithm is called to encrypt the model parameters to obtain the encrypted model parameters, and the evaluation key and the encrypted model parameters are sent to the client; wherein, the client calls the EvalMultConst algorithm in the CKKS fully homomorphic encryption algorithm according to the evaluation key, the encrypted model parameters and the privacy data to be encrypted, calculates the single model present value ciphertext, and then repeatedly calls the EvalAdd algorithm in the CKKS fully homomorphic encryption algorithm to calculate the sum of multiple single model present value ciphertexts to obtain the model present value ciphertext, wherein the EvalMultConst algorithm and the EvalAdd algorithm are used to calculate the model present value ciphertext for linear functions.

[0091] In one embodiment, the present value decryption module is specifically used for:

[0092] After receiving the model present value ciphertext sent by the client, the Decrypt algorithm in the CKKS fully homomorphic encryption algorithm is called according to the private key to decrypt and obtain the present value of the long-term rental apartment public offering pricing model.

[0093] To summarize, in the device proposed in the embodiment of the present invention, the model parameter determination module is used to determine the model parameters that need to be encrypted in the public offering pricing model of long-term rental apartments; the privacy data determination module is used to determine the privacy data that needs to be encrypted when calculating using the public offering pricing model of long-term rental apartments; the model transformation module is used to transform the public offering pricing model of long-term rental apartments according to the model parameters and privacy data, and obtain a linear function with the model parameters and privacy data as variables; the model present value ciphertext calculation module is used to encrypt the model parameters and send them to the client after receiving a data encryption request from the client, wherein after receiving the encrypted model parameters, the client calculates the model present value ciphertext through the linear function based on the encrypted model parameters and the privacy data to be encrypted; the present value decryption module is used to decrypt and obtain the present value of the public offering pricing model of long-term rental apartments after receiving the model present value ciphertext sent by the client. Compared with the prior art in which the complete model needs to be encrypted on the server side, decrypted when used, and then the client directly uploads the data to the server side to use the model, in an embodiment of the present invention, the model parameters that need to be encrypted in the long-term rental apartment public offering pricing model are determined (rather than all model parameters), and then the privacy data is determined. In this way, the long-term rental apartment public offering pricing model is transformed to obtain a linear function with model parameters and privacy data as variables. The model present value ciphertext is calculated through the linear function, and decrypted to obtain the present value of the long-term rental apartment public offering pricing model. The whole process fully protects the privacy of the model and data and is highly credible.

[0094] An embodiment of the present invention further provides a computer device, Figure 5It is a schematic diagram of a computer device in an embodiment of the present invention. The computer device 500 includes a memory 510, a processor 520, and a computer program 530 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 530, the above-mentioned horizontal override detection method is implemented.

[0095] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned data encryption method for the public offering pricing model for long-term rental apartments when executing the computer program.

[0096] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned data encryption method for the public offering pricing model for long-term rental apartments.

[0097] An embodiment of the present invention also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the above-mentioned data encryption method for the public offering pricing model for long-term rental apartments.

[0098] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0099] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0100] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0101] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0102] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A data encryption method for a public offering pricing model for long-term rental apartments, characterized in that: include: Determine the model parameters that need to be encrypted in the public offering pricing model for long-term rental apartments; Determine the privacy data that needs to be encrypted when using the public offering pricing model for long-term rental apartments; According to the model parameters and the privacy data, the long-term rental apartment public offering pricing model is transformed to obtain a linear function with the model parameters and the privacy data as variables; When receiving a data encryption request from a client, encrypt the model parameters and send them to the client, wherein after receiving the encrypted model parameters, the client calculates the model present value ciphertext based on the encrypted model parameters and the privacy data to be encrypted through the linear function; After receiving the model present value ciphertext sent by the client, decrypt it to obtain the present value of the public offering pricing model of the long-term rental apartment; The model parameters are encrypted and sent to the client, including: using the CKKS fully homomorphic encryption algorithm to encrypt the model parameters; Based on the encrypted model parameters and the private data to be encrypted, the model present value ciphertext is calculated through the linear function, including: using the CKKS fully homomorphic encryption algorithm, based on the encrypted model parameters and the private data to be encrypted, the model present value ciphertext is calculated through the linear function; Decrypting to obtain the present value of the public offering pricing model of the long-term rental apartment, including: using the CKKS fully homomorphic encryption algorithm to decrypt to obtain the present value of the public offering pricing model of the long-term rental apartment; When receiving a data encryption request from a client, the model parameters are encrypted and sent to the client, wherein after receiving the encrypted model parameters, the client calculates the model present value ciphertext based on the encrypted model parameters and the privacy data to be encrypted through the linear function, including: when receiving the data encryption request from the client, calling the Keygen algorithm in the CKKS fully homomorphic encryption algorithm to generate a private key, a public key and an evaluation key; according to the public key, calling the Encrypt algorithm in the CKKS fully homomorphic encryption algorithm to encrypt the model parameters to obtain the encrypted model parameters, and sending the evaluation key and the encrypted model parameters to the client; wherein the client calls the EvalMultConst algorithm in the CKKS fully homomorphic encryption algorithm according to the evaluation key, the encrypted model parameters and the privacy data to be encrypted to calculate the single model present value ciphertext, and then repeatedly calls the EvalAdd algorithm in the CKKS fully homomorphic encryption algorithm to calculate the sum of multiple single model present value ciphertexts to obtain the model present value ciphertext, wherein the EvalMultConst algorithm and the EvalAdd algorithm are used to calculate the model present value ciphertext for the linear function.

2. The method according to claim 1, characterized in that The model parameter that needs to be encrypted is the capitalization rate, and the privacy data that needs to be encrypted is the cost expenditure.

3. The method according to claim 1, characterized in that The formula of the linear function with model parameters and private data as variables is as follows: f(x1,…x n )=a1x1+…+a n x n x i =Y i -C i (1≤i≤n) Among them, a i is the model parameter that needs to be kept confidential; x i Y is the private data that needs to be kept confidential; i is the input for the i-th period; C i is the cost expenditure in period i.

4. The method according to claim 1, characterized in that After receiving the model present value ciphertext sent by the client, decrypt it to obtain the present value of the public offering pricing model of the long-term rental apartment, including: After receiving the model present value ciphertext sent by the client, the Decrypt algorithm in the CKKS fully homomorphic encryption algorithm is called according to the private key to decrypt and obtain the present value of the long-term rental apartment public offering pricing model.

5. A data encryption device for a long-term rental apartment public offering pricing model, characterized in that: include: Model parameter determination module, used to determine the model parameters that need to be encrypted in the public offering pricing model of long-term rental apartments; The privacy data determination module is used to determine the privacy data that needs to be encrypted when calculating the long-term rental apartment public offering pricing model; A model transformation module, used to transform the long-term rental apartment public offering pricing model according to the model parameters and the privacy data, and obtain a linear function with the model parameters and the privacy data as variables; A model present value ciphertext calculation module, configured to encrypt the model parameters and send them to the client upon receiving a data encryption request from the client, wherein after receiving the encrypted model parameters, the client calculates the model present value ciphertext through the linear function based on the encrypted model parameters and the privacy data to be encrypted; The present value decryption module is used to decrypt and obtain the present value of the public offering pricing model of the long-term rental apartment after receiving the model present value ciphertext sent by the client; The model present value ciphertext calculation module is used to: encrypt the model parameters using the CKKS fully homomorphic encryption algorithm; use the CKKS fully homomorphic encryption algorithm to calculate the model present value ciphertext through the linear function based on the encrypted model parameters and the privacy data to be encrypted; the present value decryption module is specifically used to: use the CKKS fully homomorphic encryption algorithm to decrypt and obtain the present value of the public offering pricing model of the long-term rental apartment; The model present value ciphertext calculation module is specifically used for: when receiving a data encryption request from the client, calling the Keygen algorithm in the CKKS fully homomorphic encryption algorithm to generate a private key, a public key and an evaluation key; according to the public key, calling the Encrypt algorithm in the CKKS fully homomorphic encryption algorithm to encrypt the model parameters, obtaining the encrypted model parameters, and sending the evaluation key and the encrypted model parameters to the client; wherein, the client calls the EvalMultConst algorithm in the CKKS fully homomorphic encryption algorithm according to the evaluation key, the encrypted model parameters and the privacy data to be encrypted, calculates the single model present value ciphertext, and then repeatedly calls the EvalAdd algorithm in the CKKS fully homomorphic encryption algorithm to calculate the sum of multiple single model present value ciphertexts to obtain the model present value ciphertext, wherein the EvalMultConst algorithm and the EvalAdd algorithm are used to calculate the model present value ciphertext for linear functions.

6. The device according to claim 5, characterized in that The model parameter that needs to be encrypted is the capitalization rate, and the privacy data that needs to be encrypted is the cost expenditure.

7. The device according to claim 5, characterized in that The formula of the linear function with model parameters and private data as variables is as follows: f(x1,…x n )=a1x1+…+a n x n x i =Y i -C i (1≤i≤n) Among them, a i is the model parameter that needs to be kept confidential; x i Y is the private data that needs to be kept confidential; i is the input for the i-th period; C i is the cost expenditure in period i.

8. The device according to claim 7, characterized in that The present value decryption module is specifically used for: After receiving the model present value ciphertext sent by the client, the Decrypt algorithm in the CKKS fully homomorphic encryption algorithm is called according to the private key to decrypt and obtain the present value of the long-term rental apartment public offering pricing model.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

11. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images