CN115442152A - Method and device for service evaluation - Google Patents

Abstract

The invention discloses a method and a device for service evaluation, and relates to the technical field of computers. One embodiment of the method comprises: acquiring an evaluation model for service evaluation; carrying out homomorphic encryption on the evaluation model, and sending the encrypted evaluation model to a data provider; receiving a ciphertext fed back by the data provider, and analyzing the ciphertext by using a first private key to obtain an evaluation value corresponding to the evaluation model; the ciphertext is obtained by the data provider through calculation according to the encrypted service data and the encrypted evaluation model; and determining the evaluation result of the service according to the evaluation value. According to the embodiment, the model provider and the data provider encrypt the evaluation model and the service data respectively, so that the data security is improved. Meanwhile, the evaluation value corresponding to the evaluation model can be obtained under the condition that the model provider does not know real service data, and the method is convenient and quick.

Description

Method and device for business evaluation

technical field

The invention relates to the technical field of joint learning, in particular to a method and device for business evaluation.

Background technique

In the field of risk control, due to their respective confidentiality requirements, the model provider and the data provider need to keep their respective evaluation models and business data confidential. In order to realize risk assessment using business data without the model provider obtaining real business data, in the existing implementation process, it is usually necessary for the model provider and the data provider to jointly select a trusted server. The provider encrypts the model and stores the encrypted model to the server, and when the data provider needs to use the model, uploads the business data to the server to use the model on the server. This method needs to upload the evaluation model and business data to the server for use at the same time. Therefore, when there is a problem with the credibility of the server, the decrypted model and uploaded data are at risk of leakage, and the security is poor.

Contents of the invention

In view of this, the embodiments of the present invention provide a method and device for business evaluation, without using a trusted third-party server to use the model, the model provider and the data provider respectively encrypt the evaluation model and business data held by them , and only the model provider stores the first private key that can be used to analyze and evaluate the model, which improves data security. At the same time, homomorphic encryption technology is used to realize the calculation between the encrypted business data and the encrypted evaluation model, thereby ensuring that the first private key can also be used to pair the data provider with the model provider without knowing the real business data. The feedback ciphertext is analyzed to obtain the evaluation value corresponding to the evaluation model, which is convenient and quick.

To achieve the above purpose, according to an aspect of the embodiments of the present invention, a method for service evaluation applied to a model provider is provided.

A business evaluation method in an embodiment of the present invention includes: obtaining an evaluation model for business evaluation; performing homomorphic encryption on the evaluation model, and sending the encrypted evaluation model to a data provider; receiving the data provided The ciphertext fed back by the party is analyzed by using the first private key to obtain the evaluation value corresponding to the evaluation model; wherein, the ciphertext is the encrypted business data and the encrypted Calculated by the evaluation model; determine the evaluation result of the business according to the evaluation value.

Optionally, performing homomorphic encryption on the evaluation model, and sending the encrypted evaluation model to the data provider includes: converting the evaluation model into a linear function; Homomorphic encryption: perform homomorphic encryption on the linear function, and send the encrypted linear function to the data provider.

Optionally, performing homomorphic encryption on the linear function includes: performing homomorphic encryption on coefficients corresponding to one or more service data in the linear function by using a probabilistic public key encryption algorithm.

Optionally, the method further includes: constructing the evaluation model by using business revenue and one or more business data that affect the business revenue.

Optionally, constructing the evaluation model by using business revenue and one or more business data affecting the business revenue includes: obtaining the business revenue; determining the one or more business data respectively Corresponding coefficients; using the sum of the products of each of the business data and the corresponding coefficients as the denominator and the business revenue as the numerator to construct the evaluation model.

Optionally, when the business is an Internet data center leasing business, the business data includes: power consumption and water consumption of the business; the evaluation value of the evaluation model indicates the risk situation of the business; the utilization Business revenue and one or more business data that affect the business revenue, constructing the evaluation model, including: determining the business revenue of the leasing business according to the rental and sales price of the unit cabinet; The unit price of electricity and water volume is used to determine the water fee and electricity fee used by the business; the product of the first coefficient corresponding to the water fee and the water fee, and the second coefficient corresponding to the electricity fee and the product of the electricity fee The sum of the products is used as the denominator, and the operating income of the leasing business is used as the numerator to construct the evaluation model.

Optionally, performing homomorphic encryption on the linear function includes: performing homomorphic encryption on the first coefficient, the second coefficient, and the evaluation value corresponding to the evaluation model respectively.

Optionally, the ciphertext is that the data provider performs homomorphic encryption on the electricity consumption and the water consumption respectively, and fills the encrypted electricity consumption and water consumption into the evaluation model The obtained evaluation value.

Optionally, the determining the evaluation result of the business according to the evaluation value includes: when the evaluation value exceeds a preset range, determining that there is an abnormal risk in the evaluation result of the business; When the value does not exceed the preset range, it is determined that there is no abnormal risk in the evaluation result of the business.

Optionally, when the business is a store leasing business, the business data includes: passenger flow and customer consumption unit price; the evaluation value of the evaluation model indicates the risk situation of the business.

To achieve the above object, according to an aspect of the embodiments of the present invention, another method for service evaluation applied to a data provider is provided.

Another business evaluation method in the embodiment of the present invention includes: receiving the encrypted evaluation model sent by the model provider, and obtaining the business data required by the business; performing homomorphic encryption on the business data; Data and the encrypted evaluation model, determine the ciphertext corresponding to the business; send the ciphertext to the model provider, so that the model provider can determine the evaluation of the business according to the ciphertext result.

Optionally, the encrypted service data corresponds to a second private key, and the second private key is different from the first private key.

Optionally, the determining the ciphertext corresponding to the service according to the encrypted service data and the encrypted evaluation model includes: using an additive homomorphic algorithm and/or a multiplicative homomorphic algorithm to encrypt the encrypted The business data and the encrypted evaluation model are calculated to determine the ciphertext corresponding to the business.

In order to achieve the above purpose, according to yet another aspect of the embodiments of the present invention, an apparatus for service evaluation applied to a model provider is provided.

A service evaluation device according to an embodiment of the present invention includes: an acquisition module, configured to obtain an evaluation model for service evaluation; an encryption module, configured to perform homomorphic encryption on the evaluation model, and send the encrypted evaluation model to To the data provider; the parsing module is configured to receive the ciphertext fed back by the data provider, and use the first private key to parse the ciphertext to obtain the evaluation value corresponding to the evaluation model; wherein, the ciphertext The text is calculated by the data provider based on the encrypted business data and the encrypted evaluation model; the evaluation module is configured to determine the evaluation result of the business according to the evaluation value.

In order to achieve the above object, according to yet another aspect of the embodiments of the present invention, an apparatus for service evaluation applied to a data provider is provided.

A business evaluation device according to an embodiment of the present invention includes: an acquisition module, configured to receive the encrypted evaluation model sent by the model provider, and acquire business data required by the business; an encryption module, configured to process the business data Homomorphic encryption; a calculation module, used to determine the ciphertext corresponding to the service according to the encrypted business data and the encrypted evaluation model; a sending module, used to send the ciphertext to the model provider , so that the model provider determines the evaluation result of the service according to the ciphertext.

To achieve the above object, according to still another aspect of the embodiments of the present invention, a service evaluation system is provided.

A business evaluation system in an embodiment of the present invention includes: the above-mentioned model provider and data provider, wherein,

The model provider is used to obtain an evaluation model for business evaluation; perform homomorphic encryption on the evaluation model, and send the encrypted evaluation model to the data provider;

The data provider is used to receive the encrypted evaluation model sent by the model provider, and obtain the business data required by the business; perform homomorphic encryption on the business data; according to the encrypted business data and the encrypted An evaluation model for determining the ciphertext corresponding to the business; sending the ciphertext to the model provider;

The model provider is also used to receive the ciphertext fed back by the data provider, and use the first private key to analyze the ciphertext to obtain the evaluation value corresponding to the evaluation model; wherein, the ciphertext is Calculated by the data provider based on the encrypted business data and the encrypted evaluation model; determine the evaluation result of the business based on the evaluation value.

To achieve the above purpose, according to yet another aspect of the embodiments of the present invention, an electronic device for service evaluation is provided.

An electronic device for business evaluation in an embodiment of the present invention includes: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors Executing, so that the one or more processors implement a service evaluation method in an embodiment of the present invention.

To achieve the above purpose, according to still another aspect of the embodiments of the present invention, a computer-readable storage medium is provided.

A computer-readable storage medium in an embodiment of the present invention stores a computer program thereon, and when the program is executed by a processor, a service evaluation method in an embodiment of the present invention is implemented.

An embodiment of the above invention has the following advantages or beneficial effects: no need to use a trusted third-party server to use the model, the model provider and the data provider respectively encrypt the evaluation model and business data held by them, and only by The model provider stores the first private key that can be used to analyze the evaluation model, and uses homomorphic encryption technology to realize the calculation between the encrypted business data and the encrypted evaluation model, thereby ensuring that the model provider does not know the real business data In the case of , the first private key can also be used to analyze the ciphertext fed back by the data provider to obtain the evaluation value corresponding to the evaluation model.

The further effects of the above-mentioned non-conventional alternatives will be described below in conjunction with specific embodiments.

Description of drawings

The accompanying drawings are used to better understand the present invention, and do not constitute improper limitations to the present invention. in:

FIG. 1 is a schematic flowchart of a method for business evaluation of a model provider according to an embodiment of the present invention;

Fig. 2 is a schematic flow chart of homomorphic encryption according to an embodiment of the present invention;

Fig. 3 is a schematic flow chart of constructing an evaluation model according to an embodiment of the present invention;

Fig. 4 is a schematic flowchart of determining the evaluation result of a service according to an embodiment of the present invention;

Fig. 5 is a schematic flow diagram of constructing an evaluation model under an Internet data center leasing service according to an embodiment of the present invention;

FIG. 6 is a schematic flowchart of a method for business evaluation of a data provider according to an embodiment of the present invention;

Fig. 7 is a schematic diagram of a device for business evaluation of a model provider according to an embodiment of the present invention;

Fig. 8 is a schematic diagram of a device for service evaluation of a data provider according to an embodiment of the present invention;

Fig. 9 is a schematic diagram of a service evaluation system according to an embodiment of the present invention;

Fig. 10 is an exemplary system architecture diagram to which the embodiment of the present invention can be applied;

Fig. 11 is a schematic structural diagram of a computer system suitable for implementing a terminal device or a server according to an embodiment of the present invention.

detailed description

Exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present invention to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

It should be noted that, in the case of no conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

Fig. 1 is a schematic diagram of main steps of a method for business evaluation applied to a model provider according to an embodiment of the present invention.

As shown in Figure 1, the method for service evaluation in the embodiment of the present invention mainly includes the following steps:

Step S101: Obtain an evaluation model for business evaluation;

Step S102: Perform homomorphic encryption on the evaluation model, and send the encrypted evaluation model to the data provider;

Step S103: Receive the ciphertext fed back by the data provider, and use the first private key to analyze the ciphertext to obtain the evaluation value corresponding to the evaluation model; where the ciphertext is the encrypted business data and the encrypted Calculated by the evaluation model;

Step S104: Determine the evaluation result of the business according to the evaluation value.

Among them, the evaluation model is a model used to evaluate the business. In the field of risk control, investors usually design evaluation models for different businesses, that is, the model provider. The operating income and various other data provided are falsified, so as to make reasonable investments in listed companies.

It should be noted that only homomorphic encryption can be used in step S102, and other encryption algorithms cannot be used, because the homomorphic encryption (homomorphic encryption, HE) technology allows direct calculation on the encrypted ciphertext, and the calculation result is decrypted After that, it is exactly the same as the calculation result of the plaintext. According to the supported functions, the current fully homomorphic encryption schemes can be divided into two categories: "partially homomorphic encryption" and "fully homomorphic encryption" (FHE). Because some homomorphic encryption only supports one homomorphic operation scheme, the supported operation is single, and only simple statistical operations such as mean value and linear regression can be realized, which cannot meet the actual needs of complex application scenarios. Therefore, in an optional embodiment, according to different application scenarios, the homomorphic encryption in the embodiment of the present invention refers to fully homomorphic encryption, which can support additive homomorphism and multiplicative homomorphism at the same time.

During the homomorphic encryption process, the corresponding public key and private key will be generated to encrypt and decrypt the evaluation model. The first private key in step S103 is the private key generated by the model provider during the process of encrypting the model. The key is only kept by the model provider, so the security of the evaluation model is guaranteed. If the first private key cannot be obtained by the outside world, the evaluation model cannot be decrypted and the real evaluation model can be obtained. In addition, since the ciphertext fed back by the data provider is calculated by the data provider based on the encrypted business data and the encrypted evaluation model, the data provider also needs to perform homomorphic encryption on the business data before calculation, that is, A second private key is generated that is kept only by the data provider. Since the first private key and the second private key are separately kept by the encrypted party, the privacy of the evaluation model and business data can be guaranteed at the same time.

For the encryption process in step S102, in an optional embodiment, as shown in Figure 2, including:

Step S201: converting the evaluation model into a linear function;

Step S202: Perform homomorphic encryption on the linear function, and send the encrypted linear function to the data provider.

By converting the evaluation model into a linear function, the simplified expression of the evaluation value corresponding to the evaluation model can be obtained, so that multiplication or addition can be performed after homomorphic encryption. For complex evaluation models, it can be converted into multiple linear functions. Then perform homomorphic encryption for each linear function, and send the encrypted multiple linear functions to the data provider. In a further optional embodiment, performing homomorphic encryption on the linear function in step S202 may include: respectively performing homomorphic encryption on coefficients corresponding to one or more service data in the linear function by using a probabilistic public key encryption algorithm. Among them, the probabilistic public key encryption algorithm can be understood as a paillier homomorphic encryption algorithm, which can satisfy addition and multiplication homomorphism at the same time.

For a risk assessment scenario, in an optional embodiment, an assessment model may be constructed using business revenue and one or more business data that affect the business revenue. Specifically as shown in Figure 3, including:

Step S301: Obtain business operating income;

Step S302: Determine coefficients respectively corresponding to one or more business data;

Step S303: The sum of the products of each business data and the corresponding coefficient is used as the denominator, and the operating income of the business is used as the numerator to construct an evaluation model.

Among them, in order to obtain investment, each listed company will provide its business operating income to show each investor that the company is operating well and has investment prospects. The model provider who is going to invest needs to judge whether the listed company has made false reports and whether the operating conditions are good based on the business revenue reported by the listed company. The business operating income in the embodiment of the present invention is the business operating income declared by the listed company, which can be obtained from the official operating conditions, and the evaluation value of the evaluation model indicates the risk of the business.

Further, the business data in step S302 can be understood as a factor for judging whether the business revenue is normal. For example, in an optional embodiment, when the business is Internet data center leasing business, the business data may include: business electricity and water consumption. In another optional embodiment, when the business is a store leasing business, the business data may include: passenger flow and customer consumption unit price. For different businesses, the factors affecting business operating income are also different, so the corresponding business data are also different, which is not limited in the present invention.

By dividing the business operating income by the weighted and summed value of each business data in step S303, the evaluation value for judging whether there is risk can be obtained. In an optional embodiment, in the risk evaluation scenario, the step S104, as shown in Figure 4, further includes:

Step S401: When the evaluation value exceeds the preset range, determine that the evaluation result of the business is abnormal risk;

Step S402: If the evaluation value does not exceed the preset range, it is determined that the evaluation result of the business is that there is no abnormal risk.

Specifically, taking the Internet data center leasing business as an example, the above-mentioned process of constructing an evaluation model is described in detail, using business revenue and one or more business data that affect business revenue to construct the process of the evaluation model, as shown in the figure 5, including:

Step S501: Determine the operating income of the leasing business according to the leasing and selling price of the unit cabinet;

Step S502: Determine the water fee and electricity fee used by the business according to the electricity consumption, water consumption, and unit price of the electricity and water volume of the business;

Step S503: The sum of the product of the first coefficient corresponding to the water fee and the water fee, and the product of the second coefficient corresponding to the electricity fee and the electricity fee is used as the denominator, and the operating income of the leasing business is used as the numerator to construct an evaluation model.

Internet data center leasing business (Internet Data Center, IDC), that is, the leasing business of cabinets, operating income comes from the number of cabinets leased and the unit price of leasing, and the factors for judging operating income are mainly the water consumption of cabinets and the use of cabinets. According to the water consumption and electricity consumption of the cabinet, the operation status of the cabinet can be known, and then the rental status of the cabinet and whether the business operating income is abnormal. Specifically, the evaluation model can be shown in the following formula (1):

Among them, σ represents the risk assessment value, E _income represents the income of IDC in a given time interval, a _water represents the water consumption of IDC in a given time interval, b _electricity represents the electricity consumption of IDC in a given time interval, α, β represent the construction The modulus coefficients are the first coefficient and the second coefficient, corresponding to water consumption and electricity consumption, and [a,b] represent the preset range of risk assessment values.

In an optional embodiment, for the above-mentioned Internet data center leasing service, the process of performing homomorphic encryption on the linear function in step S202 includes: performing homomorphic encryption on the first coefficient and the second coefficient respectively. Since the water consumption and electricity consumption are stored by the data provider, the model provider does not know the real data value, so the encrypted model needs to be sent to the data provider so that the data provider can fill in the corresponding data. The final risk assessment value can be obtained. For the evaluation model, it is only necessary to perform homomorphic encryption on the first coefficient, the second coefficient, and the evaluation value corresponding to the evaluation model, and sending the encrypted evaluation model to the data provider can also ensure the evaluation Models will not be leaked. In a further optional embodiment, the ciphertext is an evaluation value obtained by filling the encrypted electricity consumption and water consumption into the evaluation model after the data provider performs homomorphic encryption on the electricity consumption and water consumption respectively.

According to the business evaluation method of the embodiment of the present invention, it can be seen that this method does not need to use a trusted third-party server to use the model, and the model provider and the data provider respectively encrypt the evaluation model and business data held by them, and Only the model provider stores the first private key that can be used to analyze the evaluation model, and uses homomorphic encryption technology to realize the calculation between the encrypted business data and the encrypted evaluation model, thereby ensuring that the model provider does not know the real In the case of business data, the first private key can also be used to analyze the ciphertext fed back by the data provider to obtain the evaluation value corresponding to the evaluation model.

Fig. 6 is a schematic diagram of main steps of a method for service evaluation applied to a data provider according to an embodiment of the present invention.

As shown in Figure 6, the method for service evaluation in the embodiment of the present invention mainly includes the following steps:

Step S601: Receive the encrypted evaluation model sent by the model provider, and obtain the business data required by the business;

Step S602: Perform homomorphic encryption on business data;

Step S603: Determine the ciphertext corresponding to the business according to the encrypted business data and the encrypted evaluation model;

Step S604: Send the ciphertext to the model provider, so that the model provider can determine the evaluation result of the business according to the ciphertext.

Wherein, the data provider can store various business data, and the business data required for different evaluation models is different, so in step S601, the corresponding business data can be obtained according to the evaluation model.

In order to enable the encrypted business data to be directly calculated with the encrypted evaluation model, the homomorphic encryption in step S602 is the same as the encryption method of the model provider, using a probabilistic public key encryption algorithm for homomorphic encryption. Taking the Internet data center leasing business as an example, the two business data of real water consumption and electricity consumption are encrypted separately, that is, a _water and b _electricity in formula (1) are respectively homomorphically encrypted, and the encrypted The obtained virtual water consumption and virtual electricity consumption are respectively filled into formula (1), and multiplicative homomorphism and additive homomorphism are performed with the encrypted virtual first coefficient and virtual second coefficient, and finally the encrypted risk assessment value is obtained.

For the process of determining the ciphertext in step S603, multiple algorithms may be used depending on the application scenario and the difference in the evaluation model. In the Internet data center leasing business involved in the present invention, the additive homomorphic algorithm and/or the multiplicative homomorphic algorithm can be used The algorithm calculates the encrypted business data and the encrypted evaluation model to determine the ciphertext corresponding to the business.

The evaluation model and business data held by the model provider and the data provider are respectively encrypted to ensure that both parties can still obtain the encrypted risk evaluation value without obtaining the other party's real information. The encrypted encryption method makes the encrypted risk assessment value the same as the real risk assessment value, which ensures the accuracy of the data and realizes the business without using the third-party server and without obtaining real data. Risk assessment, while improving the security of business data and assessment models. It should be noted that the encrypted business data corresponds to the second private key, and the second private key is different from the first private key, that is to say, the data provider and the model provider save their own private keys after encryption , further improving data security.

The following uses formula (1) as an example to describe the encryption process of the data provider and the model provider in detail.

The model provider first performs homomorphic encryption on the first coefficient α, the second coefficient β, and the risk assessment value σ in formula (1), and encrypts the first coefficient α, the second coefficient β, and the risk assessment value σ respectively into Ciphertext m, n and q, that is, formula (2):

Wherein, q represents the risk assessment value after encryption, m represents the first coefficient after encryption, n represents the second coefficient after encryption, and the public key and the first private key for parsing are generated during the encryption process.

After the encryption is completed, the model provider sends the encrypted evaluation model (ie, formula (2)) to the data provider, and the data provider fills in the data a _water and b _electricity .

At this time, after receiving the encrypted evaluation model, the data provider obtains the real data a _water and b _electricity , and performs homomorphic encryption on the real data to obtain encrypted data A and B, where A is the encrypted data Water consumption, B is the encrypted electricity consumption. And the public key and the second private key used for parsing are also generated during the encryption process. Then fill the encrypted water consumption A and electricity consumption B into formula (2) respectively, and formula (3) can be obtained as follows:

Since E _income is the public business income of listed companies and is a known quantity, the encrypted risk assessment value q, which is the ciphertext, can be calculated by formula (3), and the ciphertext is fed back to the model provider.

After obtaining the encrypted risk assessment value q, the model provider can analyze it with the first private key to obtain the real risk assessment value, and determine the business assessment result according to whether the risk assessment value meets the preset range.

According to the business evaluation method of the embodiment of the present invention, it can be seen that there is no need to use a trusted third-party server to use the model, the model provider and the data provider respectively encrypt the evaluation model and business data held by them, and only The model provider stores the first private key that can be used to parse and evaluate the model, improving data security. At the same time, homomorphic encryption technology is used to realize the calculation between the encrypted business data and the encrypted evaluation model, thereby ensuring that the first private key can also be used to pair the data provider with the model provider without knowing the real business data. The feedback ciphertext is analyzed to obtain the evaluation value corresponding to the evaluation model, which is convenient and quick.

Fig. 7 is a schematic diagram of an apparatus for service evaluation of a model provider according to an embodiment of the present invention.

As shown in FIG. 7 , an apparatus 700 for business evaluation of a model provider in an embodiment of the present invention includes:

An obtaining module 701, configured to obtain an evaluation model for business evaluation;

An encryption module 702, configured to perform homomorphic encryption on the evaluation model, and send the encrypted evaluation model to the data provider;

The parsing module 703 is configured to receive the ciphertext fed back by the data provider, and use the first private key to parse the ciphertext to obtain the evaluation value corresponding to the evaluation model; wherein, the ciphertext is the data provider It is calculated by the party based on the encrypted business data and the encrypted evaluation model;

An evaluation module 704, configured to determine an evaluation result of the service according to the evaluation value.

In an optional embodiment of the present invention, the encryption module 702 is also used to convert the evaluation model into a linear function; perform homomorphic encryption on the linear function, and send the encrypted linear function to data provider.

In an optional embodiment of the present invention, the encryption module 702 is further configured to respectively perform homomorphic encryption on coefficients corresponding to one or more service data in the linear function by using a probabilistic public key encryption algorithm.

In an optional embodiment of the present invention, the device further includes a construction module, configured to use business revenue and one or more business data that affect the business revenue to construct the evaluation model.

In an optional embodiment of the present invention, the building module is also used to obtain the business revenue; determine the corresponding coefficients of the one or more business data; use each of the business data and the corresponding coefficient The sum of the products of is used as the denominator, and the operating income of the business is used as the numerator to construct the evaluation model.

In an optional embodiment of the present invention, when the business is an Internet data center leasing business, the business data includes: power consumption and water consumption of the business; the evaluation value of the evaluation model indicates the The risk situation of the business; the building block is also used to determine the operating income of the leasing business according to the rental and sales price of the unit cabinet; to determine the water fee used by the business according to the power consumption, water consumption, and the unit price of the power and water volume of the business and electricity charges; with the sum of the product of the first coefficient corresponding to the water charge and the water charge and the product of the second coefficient corresponding to the electric charge and the electric charge as the denominator, the business of the leasing business Income is used as the numerator to build the valuation model.

In an optional embodiment of the present invention, the encryption module 702 is further configured to perform homomorphic encryption on the first coefficient, the second coefficient, and the evaluation value corresponding to the evaluation model.

In an optional embodiment of the present invention, the ciphertext is after the data provider performs homomorphic encryption on the electricity consumption and the water consumption respectively, and the encrypted electricity consumption and water consumption The water consumption is filled to the evaluation value obtained by the evaluation model.

In an optional embodiment of the present invention, the assessment module 704 is further configured to determine that the assessment result of the business is an abnormal risk when the assessment value exceeds a preset range; If it does not exceed the preset range, it is determined that there is no abnormal risk in the evaluation result of the business.

In an optional embodiment of the present invention, when the business is a store leasing business, the business data includes: passenger flow and customer consumption unit price; the evaluation value of the evaluation model indicates the risk situation of the business .

According to the business evaluation device of the embodiment of the present invention, it can be seen that there is no need to use a trusted third-party server to use the model, the model provider and the data provider respectively encrypt the evaluation model and business data held by them, and only The model provider stores the first private key that can be used to parse and evaluate the model, improving data security. At the same time, homomorphic encryption technology is used to realize the calculation between the encrypted business data and the encrypted evaluation model, thereby ensuring that the first private key can also be used to pair the data provider with the model provider without knowing the real business data. The feedback ciphertext is analyzed to obtain the evaluation value corresponding to the evaluation model, which is convenient and quick.

Fig. 8 is a schematic diagram of an apparatus for service evaluation of a data provider according to an embodiment of the present invention.

As shown in Figure 8, the service evaluation apparatus 800 of the embodiment of the present invention includes:

An acquisition module 801, configured to receive the encrypted evaluation model sent by the model provider, and acquire business data required by the business;

An encryption module 802, configured to perform homomorphic encryption on the business data;

A computing module 803, configured to determine the ciphertext corresponding to the business according to the encrypted business data and the encrypted evaluation model;

A sending module 804, configured to send the ciphertext to the model provider, so that the model provider can determine the evaluation result of the service according to the ciphertext.

In an optional embodiment of the present invention, the encrypted service data corresponds to a second private key, and the second private key is different from the first private key.

In an optional embodiment of the present invention, the calculation module 803 is further configured to use an additive homomorphic algorithm and/or a multiplicative homomorphic algorithm to calculate the encrypted business data and the encrypted evaluation model , to determine the ciphertext corresponding to the service.

According to the business evaluation device of the embodiment of the present invention, it can be seen that the evaluation model and business data held by the model provider and the data provider are respectively encrypted to ensure that the two parties can still obtain the other party's real information. The encrypted risk assessment value is obtained, and due to the homomorphic encryption encryption method, the encrypted risk assessment value is the same as the real risk assessment value, which ensures the accuracy of the data and realizes Risk assessment is performed on the business without obtaining real data on the server side, and at the same time, the security of business data and evaluation models is improved. It should be noted that the encrypted business data corresponds to the second private key, and the second private key is different from the first private key, that is to say, the data provider and the model provider save their own private keys after encryption , further improving data security.

Fig. 9 is a schematic diagram of a service evaluation system according to an embodiment of the present invention.

As shown in Figure 9, the business evaluation system 900 of the embodiment of the present invention includes: the above-mentioned model provider 901 and data provider 902, wherein,

The model provider 901 is configured to obtain an evaluation model for business evaluation; perform homomorphic encryption on the evaluation model, and send the encrypted evaluation model to the data provider;

The data provider 902 is used to receive the encrypted evaluation model sent by the model provider, and obtain the business data required by the business; perform homomorphic encryption on the business data; according to the encrypted business data and the encrypted After the evaluation model, determine the ciphertext corresponding to the business; send the ciphertext to the model provider;

The model provider 901 is also configured to receive the ciphertext fed back by the data provider, and use the first private key to analyze the ciphertext to obtain the evaluation value corresponding to the evaluation model; wherein, the ciphertext It is calculated by the data provider based on the encrypted business data and the encrypted evaluation model; the evaluation result of the business is determined according to the evaluation value.

Fig. 10 shows an exemplary system architecture 1000 to which the service evaluation method or the service evaluation device of the embodiment of the present invention can be applied.

As shown in FIG. 10 , a system architecture 1000 may include terminal devices 1001 , 1002 , and 1003 , a network 1004 and a server 1005 . The network 1004 is used as a medium for providing communication links between the terminal devices 1001 , 1002 , 1003 and the server 1005 . Network 1004 may include various connection types, such as wire, wireless communication links, or fiber optic cables, among others.

Users can use terminal devices 1001, 1002, 1003 to interact with server 1005 through network 1004 to receive or send data and so on. Various communication client applications can be installed on the terminal devices 1001, 1002, and 1003, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and social platform software.

The terminal devices 1001, 1002, and 1003 may be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

The server 1005 may be a server that provides various services, such as a background management server that provides support for evaluation models or business data uploaded by users using the terminal devices 1001 , 1002 , and 1003 . The background management server can analyze and process the received evaluation model or business data, etc., and feed back the processing result (for example, evaluation result) to the terminal device.

It should be noted that the service evaluation method provided by the embodiment of the present invention is generally executed by the server 1005 , and correspondingly, the service evaluation device is generally set in the server 1005 .

It should be understood that the numbers of terminal devices, networks and servers in FIG. 10 are only illustrative. According to the implementation needs, there can be any number of terminal devices, networks and servers.

Referring now to FIG. 11 , it shows a schematic structural diagram of a computer system 1100 suitable for implementing a terminal device according to an embodiment of the present invention. The terminal device shown in FIG. 11 is only an example, and should not limit the functions and scope of use of this embodiment of the present invention.

As shown in FIG. 11 , a computer system 1100 includes a central processing unit (CPU) 1101, which can operate according to a program stored in a read-only memory (ROM) 1102 or a program loaded from a storage section 1108 into a random access memory (RAM) 1103 Instead, various appropriate actions and processes are performed. In the RAM 1103, various programs and data necessary for the operation of the system 1100 are also stored. The CPU 1101 , ROM 1102 , and RAM 1103 are connected to each other via a bus 1104 . An input/output (I/O) first interface 1105 is also connected to the bus 1104 .

The following components are connected to the I/O first interface 1105: an input section 1106 including a keyboard, a mouse, etc.; an output section 1107 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage including a hard disk, etc. section 1108; and a communication section 1109 including a network first interface card such as a LAN card, modem, or the like. The communication section 1109 performs communication processing via a network such as the Internet. A driver 1110 is also connected to the I/O first interface 1105 as needed. A removable medium 1111 such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc. is mounted on the drive 1110 as necessary so that a computer program read therefrom is installed into the storage section 1108 as necessary.

In particular, according to the disclosed embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the disclosed embodiments of the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, where the computer program includes program codes for executing the methods shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network via communication portion 1109 and/or installed from removable media 1111 . When this computer program is executed by a central processing unit (CPU) 1101, the above-mentioned functions defined in the system of the present invention are performed.

It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. A computer readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present invention, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program codes therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. . Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, program segment, or portion of code that includes one or more logical functions for implementing specified executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block in the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a A combination of dedicated hardware and computer instructions.

The modules involved in the embodiments described in the present invention may be realized by software or by hardware. The described modules can also be set in a processor, for example, it can be described as: a processor includes an acquisition module, an encryption module, an analysis module and an evaluation module. Wherein, the names of these modules do not constitute a limitation on the module itself under certain circumstances, for example, the obtaining module may also be described as "a module for obtaining an evaluation model for service evaluation".

As another aspect, the present invention also provides a computer-readable medium. The computer-readable medium may be contained in the device described in the above embodiments, or it may exist independently without being assembled into the device. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by the device, the device includes: acquiring an evaluation model for service evaluation; performing homomorphic encryption on the evaluation model , and send the encrypted evaluation model to the data provider; receive the ciphertext fed back by the data provider, and use the first private key to analyze the ciphertext to obtain the evaluation value corresponding to the evaluation model; wherein , the ciphertext is calculated by the data provider according to the encrypted service data and the encrypted evaluation model; and the evaluation result of the service is determined according to the evaluation value.

According to the technical solution of the embodiment of the present invention, there is no need to use a trusted third-party server to use the model, the model provider and the data provider respectively encrypt the evaluation model and business data held by them, and only the model provider can store The first private key used to parse the evaluation model improves data security. At the same time, homomorphic encryption technology is used to realize the calculation between the encrypted business data and the encrypted evaluation model, thereby ensuring that the first private key can also be used to pair the data provider with the model provider without knowing the real business data. The feedback ciphertext is analyzed to obtain the evaluation value corresponding to the evaluation model, which is convenient and quick.

The above specific implementation methods do not constitute a limitation to the protection scope of the present invention. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (18)

1. A method for service evaluation, applied to a model provider, includes:

acquiring an evaluation model for service evaluation;

carrying out homomorphic encryption on the evaluation model, and sending the encrypted evaluation model to a data provider;

receiving a ciphertext fed back by the data provider, and analyzing the ciphertext by using a first private key to obtain an evaluation value corresponding to the evaluation model; the ciphertext is obtained by a data provider through calculation according to the encrypted business data and the encrypted evaluation model;

and determining the evaluation result of the service according to the evaluation value.

2. The method of claim 1, wherein homomorphically encrypting the assessment model and sending the encrypted assessment model to a data provider comprises:

converting the evaluation model into a linear function;

and homomorphic encryption is carried out on the linear function, and the encrypted linear function is sent to a data provider.

3. The method of claim 2, wherein said homomorphically encrypting said linear function comprises:

and respectively carrying out homomorphic encryption on the coefficients corresponding to one or more service data in the linear function through a probability public key encryption algorithm.

4. The method of claim 2, further comprising: the evaluation model is constructed using business revenue and one or more business data affecting the business revenue.

5. The method of claim 4, wherein the constructing the assessment model using business revenue and one or more business data affecting the business revenue comprises:

acquiring the business income;

determining coefficients corresponding to the one or more service data respectively;

and constructing the evaluation model by taking the sum of the products of each business data and the corresponding coefficient as a denominator and the business income as a numerator.

6. The method of claim 4, wherein when the service is an Internet data center rental service, the service data comprises: electricity and water consumption of the service; the evaluation value of the evaluation model indicates the risk condition of the service; the constructing the evaluation model using the business revenue and one or more business data affecting the business revenue comprises:

determining the business income of the lease service according to the lease and sale price of the unit cabinet;

determining water and electricity charges used by the service according to the electricity consumption and water consumption of the service and the unit price of the electricity and water;

and constructing the evaluation model by taking the sum of the product of a first coefficient corresponding to the water charge and the product of a second coefficient corresponding to the electric charge and the electric charge as a denominator and the business income of the rental business as a numerator.

7. The method of claim 6, wherein said homomorphically encrypting the linear function comprises:

and performing homomorphic encryption on the first coefficient, the second coefficient and the evaluation value corresponding to the evaluation model respectively.

8. The method according to claim 6, wherein the ciphertext is used for homomorphically encrypting the power consumption and the water consumption for the data provider, and filling the encrypted power consumption and water consumption into the evaluation value obtained by the evaluation model.

9. The method of claim 6, wherein the determining the evaluation result of the service according to the evaluation value comprises:

determining that the service evaluation result is abnormal risk when the evaluation value exceeds a preset range;

and under the condition that the evaluation value does not exceed a preset range, determining that the evaluation result of the service does not have abnormal risk.

10. The method of claim 4, wherein when the business is a store rental business, the business data comprises: passenger flow volume and customer consumption unit price; the evaluation value of the evaluation model indicates the risk condition of the business.

11. A method for service evaluation is applied to a data provider, and comprises the following steps:

receiving the encrypted evaluation model sent by the model provider, and acquiring service data required by the service;

carrying out homomorphic encryption on the service data;

determining a ciphertext corresponding to the service according to the encrypted service data and the encrypted evaluation model;

and sending the ciphertext to the model provider so that the model provider can determine the evaluation result of the service according to the ciphertext.

12. The method of claim 11, wherein the encrypted service data corresponds to a second private key, and wherein the second private key is different from the first private key.

13. The method of claim 11, wherein determining the ciphertext corresponding to the service according to the encrypted service data and the encrypted evaluation model comprises:

and calculating the encrypted service data and the encrypted evaluation model by utilizing an addition homomorphic algorithm and/or a multiplication homomorphic algorithm, and determining a ciphertext corresponding to the service.

14. An apparatus for business evaluation, applied to a model provider, comprising:

the acquisition module is used for acquiring an evaluation model for service evaluation;

the encryption module is used for homomorphically encrypting the evaluation model and sending the encrypted evaluation model to a data provider;

the analysis module is used for receiving the ciphertext fed back by the data provider and analyzing the ciphertext by using a first private key to obtain an evaluation value corresponding to the evaluation model; the ciphertext is obtained by a data provider through calculation according to the encrypted business data and the encrypted evaluation model;

and the evaluation module is used for determining the evaluation result of the service according to the evaluation value.

15. An apparatus for evaluating a service, applied to a data provider, comprising:

the acquisition module is used for receiving the encrypted evaluation model sent by the model provider and acquiring service data required by the service;

the encryption module is used for homomorphic encryption of the service data;

the calculation module is used for determining a ciphertext corresponding to the service according to the encrypted service data and the encrypted evaluation model;

and the sending module is used for sending the ciphertext to the model provider so that the model provider can determine the evaluation result of the service according to the ciphertext.

16. A system for business evaluation, comprising: the model provider of claim 14 and the data provider of claim 15, wherein,

the model provider is used for acquiring an evaluation model for service evaluation; homomorphic encryption is carried out on the evaluation model, and the encrypted evaluation model is sent to a data provider;

the data provider is used for receiving the encrypted evaluation model sent by the model provider and acquiring service data required by the service; carrying out homomorphic encryption on the service data; determining a ciphertext corresponding to the service according to the encrypted service data and the encrypted evaluation model; sending the ciphertext to the model provider;

the model provider is further used for receiving the ciphertext fed back by the data provider, and analyzing the ciphertext by using a first private key to obtain an evaluation value corresponding to the evaluation model; the ciphertext is obtained by a data provider through calculation according to the encrypted business data and the encrypted evaluation model; and determining the evaluation result of the service according to the evaluation value.

17. An electronic device for business evaluation, comprising:

one or more processors;

a storage device for storing one or more programs,

when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-13.

18. A computer-readable medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-13.

Images