CN116910630B

CN116910630B - User identification information storage method, device, electronic equipment and medium

Info

Publication number: CN116910630B
Application number: CN202311183152.5A
Authority: CN
Inventors: 李泽盼; 卢彩霞; 唐志涛; 何嘉; 赵园园; 高天; 谢长涛; 刘明明; 杜晔; 孙兴达
Original assignee: State Grid Information and Telecommunication Co Ltd; Beijing Guodiantong Network Technology Co Ltd
Current assignee: State Grid Information and Telecommunication Co Ltd; Beijing Guodiantong Network Technology Co Ltd
Priority date: 2023-09-14
Filing date: 2023-09-14
Publication date: 2023-11-24
Anticipated expiration: 2043-09-14
Also published as: CN116910630A

Abstract

The embodiment of the disclosure discloses a user identification information storage method, a device, electronic equipment and a medium. One embodiment of the method comprises the following steps: encrypting the electric potential user identification model to obtain an encrypted electric potential user identification model; the encrypted potential power user identification model is respectively sent to a power data service node and a virtual article data service node; generating a power data identification information set according to the power identification information and the power identification weight of each target user; generating a virtual article data identification information set according to the virtual article identification information and the virtual article identification weight of each target user; generating a power potential user identification information set according to the power data identification information set and the virtual article data identification information set; a set of power potential subscriber identification information is stored in a cache. This embodiment may increase the hit rate of accessed potential power consumer information.

Description

User identification information storage method, device, electronic equipment and medium

Technical Field

Embodiments of the present disclosure relate to the field of computer technologies, and in particular, to a method, an apparatus, an electronic device, and a medium for storing user identification information.

Background

With the progress of science and technology, the new energy industry of China has also greatly developed. The popularization and popularization of new energy sources in electric power users (especially potential electric power users) are important to the development of new energy source industry in China. Currently, when storing user identification information, the following methods are generally adopted: the method includes detecting and determining a size of a cache storage capacity, performing potential power subscriber identification using single-ended power data through a machine learning or deep learning model, and storing the identified subscriber information in the cache or cache.

However, the inventors found that when the user identification information is stored in the above manner, there are often the following technical problems:

firstly, multi-terminal multi-dimensional data are not adopted to carry out potential power user identification at the same time, corresponding weights are given according to respective contribution degrees, so that the integrity of user information is low, the accuracy of model-identified potential power user information is low, redundant potential power user information with identification errors is more in information stored in a cache with limited capacity, and when the potential power user information is accessed and inquired, the hit rate of the accessed potential power user information is low, and the access response time is long; furthermore, in the process of carrying out potential power user identification by adopting multi-terminal multi-dimensional data, encryption processing on a model to be subjected to user identification is not considered, so that the safety of an identification result is low.

Second, security and privacy protection of the original target consumer power information and the original target consumer virtual item information data (the consumer's power data information party and virtual item information party do not share data with each other) is not considered in determining the power consumer information to be identified. The data leakage of the power data information and the virtual article information of the user is easy to be caused when the power user object to be identified is determined, and the security of the power user information is low.

The above information disclosed in this background section is only for enhancement of understanding of the background of the inventive concept and, therefore, may contain information that does not form the prior art that is already known to those of ordinary skill in the art in this country.

Disclosure of Invention

The disclosure is in part intended to introduce concepts in a simplified form that are further described below in the detailed description. The disclosure is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.

Some embodiments of the present disclosure propose a user identification information storage method, apparatus, electronic device, and computer readable medium to solve one or more of the technical problems mentioned in the background section above.

In a first aspect, some embodiments of the present disclosure provide a user identification information storage method, the method including: encrypting the pre-trained electric potential user identification model to obtain an encrypted electric potential user identification model; the encrypted power potential user identification models are respectively sent to a power data service node and a virtual article data service node, so that the power data service node identifies all target user power information included in a target user power information set through the encrypted power potential user identification models, and the virtual article data service node identifies all target user virtual article information included in the target user virtual article information set through the encrypted power potential user identification models; responding to receiving the identification information of each target user corresponding to the identified power information of each target user sent by the power data service node and the identification weight of the power corresponding to the power data service node, and generating a power data identification information set according to the identification information of each target user and the identification weight of the power, wherein the identification weight of the power corresponding to the power data service node is the accuracy of potential user identification obtained by the identification of the potential user identification model on a preset power information test data set; responding to receiving each piece of target user virtual article identification information corresponding to each piece of target user virtual article information identified by the virtual article data service node and a virtual article identification weight corresponding to the virtual article data service node, and generating a virtual article data identification information set according to each piece of target user virtual article identification information and the virtual article identification weight, wherein the virtual article identification weight corresponding to the virtual article data service node is the accuracy of potential user identification obtained by the electric potential user identification model in a preset virtual article information test data set, and the virtual article data identification information in the virtual article data identification information set corresponds to electric power data identification information in the electric power data identification information set; generating a power potential user identification information set according to the power data identification information set and the virtual article data identification information set; the set of power potential subscriber identification information is stored in a cache.

In a second aspect, some embodiments of the present disclosure provide a user identification information storage device, the device comprising: the encryption unit is configured to encrypt the pre-trained power potential user identification model to obtain an encrypted power potential user identification model; the transmission unit is configured to transmit the encrypted power potential user identification models to the power data service node and the virtual article data service node respectively, so that the power data service node identifies all target user power information included in the target user power information set through the encrypted power potential user identification models, and the virtual article data service node identifies all target user virtual article information included in the target user virtual article information set through the encrypted power potential user identification models; a first generation unit configured to generate a power data identification information set according to the respective target user power identification information and the power identification weights corresponding to the power data service nodes in response to receiving the respective target user power identification information corresponding to the identified respective target user power information transmitted by the power data service nodes and the power identification weights corresponding to the power data service nodes, wherein the power identification weights corresponding to the power data service nodes are the accuracy of the potential user identification obtained by the potential user identification model by identifying on a preset power information test data set; a second generating unit configured to generate a virtual article data identification information set according to each target user virtual article identification information and the virtual article identification weight corresponding to the virtual article data service node in response to receiving each target user virtual article identification information corresponding to each target user virtual article information identified by the virtual article data service node and the virtual article identification weight corresponding to the virtual article data service node, wherein the virtual article identification weight corresponding to the virtual article data service node is an accuracy rate of potential user identification obtained by the electric potential user identification model identifying on a preset virtual article information test data set, and virtual article data identification information in the virtual article data identification information set corresponds to electric power data identification information in the electric power data identification information set; a third generation unit configured to generate a set of power potential user identification information from the set of power data identification information and the set of virtual article data identification information; and a storage unit configured to store the set of power potential user identification information into a cache.

In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors causes the one or more processors to implement the method described in any of the implementations of the first aspect above.

In a fourth aspect, some embodiments of the present disclosure provide a computer readable medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

The above embodiments of the present disclosure have the following advantageous effects: by the user identification information storage method of some embodiments of the present disclosure, accuracy of model identification of potential power user information can be improved, redundant potential power user information which is stored in a cache with limited capacity and is wrong in identification can be reduced, and hit rate of accessed potential power user information can be improved. Specifically, the accuracy of the potential power consumer information which leads to the model identification is lower, the redundant potential power consumer information which leads to the identification error is more in the information stored in the cache with limited capacity, and when the potential power consumer information is accessed and inquired, the hit rate of the accessed potential power consumer information is lower, and the access response time is longer; furthermore, in the process of using multi-terminal multi-dimensional data to identify potential power users, encryption processing is not considered on a model to be identified, so that the safety of an identification result is low because: the multi-terminal multi-dimensional data is not adopted to carry out potential power user identification at the same time, and corresponding weights are given according to the respective contribution degrees, so that the integrity of user information is lower, the accuracy of the model-identified potential power user information is lower, the redundant potential power user information with wrong identification is more in information stored in a cache with limited capacity, and when the potential power user information is accessed and inquired, the hit rate of the accessed potential power user information is lower, and the access response time is longer; furthermore, in the process of carrying out potential power user identification by adopting multi-terminal multi-dimensional data, encryption processing on a model to be subjected to user identification is not considered, so that the safety of an identification result is low. Based on this, the user identification information storage method of some embodiments of the present disclosure first performs encryption processing on a pre-trained power potential user identification model to obtain an encrypted power potential user identification model. Therefore, the encrypted power potential user identification model can be obtained, and can be used for carrying out power potential user identification and improving the safety of an identification result. And then, the encrypted power potential user identification models are respectively sent to the power data service node and the virtual article data service node, so that the power data service node identifies all target user power information included in the target user power information set through the encrypted power potential user identification models, and the virtual article data service node identifies all target user virtual article information included in the target user virtual article information set through the encrypted power potential user identification models. Therefore, the power data of the power data service node and the virtual article data of the virtual article data service node can be utilized, namely, the data with two dimensions at two ends are adopted to simultaneously carry out potential power user identification, so that the generation of the data island problem can be avoided, and the integrity of user information can be improved. And then, in response to receiving the power identification information of each target user corresponding to the identified power information of each target user transmitted by the power data service node and the power identification weight corresponding to the power data service node, generating a power data identification information set according to the power identification information of each target user and the power identification weight. The power identification weight corresponding to the power data service node is the accuracy of potential user identification obtained by the power potential user identification model through identification on a preset power information test data set. Therefore, the recognition result of the model recognition by the power data service node can be obtained, and the accuracy of the potential user recognition obtained by recognition on the preset power information test data set is used as the contribution weight of the model recognition by the power data service node, so that the accuracy of the recognized potential power user can be improved. And then, responding to the received virtual article identification information of each target user corresponding to the virtual article information of each target user transmitted by the virtual article data service node and the virtual article identification weight corresponding to the virtual article data service node, and generating a virtual article data identification information set according to the virtual article identification information of each target user and the virtual article identification weight. The virtual article identification weight corresponding to the virtual article data service node is the accuracy of potential user identification obtained by the electric potential user identification model through identification on a preset virtual article information test data set, and the virtual article data identification information in the virtual article data identification information set corresponds to the electric power data identification information in the electric power data identification information set. Therefore, the recognition result of the model recognition by the virtual article data service node can be obtained, and the accuracy of the potential user recognition obtained by recognizing the preset electric power information test on the preset virtual article information test data set is used as the contribution weight of the model recognition by the virtual article data service node, so that the accuracy of the recognized potential electric power user can be improved. And then, generating a power potential user identification information set according to the power data identification information set and the virtual article data identification information set. Therefore, the potential power user information can be obtained according to the accuracy rate and the corresponding contribution weight of the prediction of the two ends of the power data service node and the virtual article data service node. Finally, the set of power potential subscriber identification information is stored in a cache. Therefore, the electric power potential user identification information set with high identification accuracy can be stored in the cache, and the electric power potential user identification information set can be used for improving the hit rate of users on potential electric power user information access. And the pre-trained electric potential user identification model is sent to the electric data service node and two ends of the virtual article data service node for identification, so that the generation of data islands can be avoided, and the integrity of user information for identification can be improved. And the contribution weights of the two ends are determined according to the accuracy of the prediction of the models of the two ends, so that the accuracy of the identified potential power user information can be improved, the redundant potential power user information which is stored in a cache with limited capacity and is wrong in identification is reduced, the hit rate of the accessed potential power user information is improved, and the access response time is shortened.

Drawings

The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.

FIG. 1 is a flow chart of some embodiments of a user identification information storage method according to the present disclosure;

FIG. 2 is a schematic diagram of the structure of some embodiments of a user identification information store generating device according to the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.

It should be noted that, for convenience of description, only the portions related to the present invention are shown in the drawings. Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.

It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.

It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.

The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

Fig. 1 illustrates a flow 100 of some embodiments of a user identification information storage method according to the present disclosure. The user identification information storage method comprises the following steps:

And step 101, carrying out encryption processing on the pre-trained electric potential user identification model to obtain an encrypted electric potential user identification model.

In some embodiments, an executing body (e.g., a computing device) of the user identification information storage method may encrypt the pre-trained power latent user identification model to obtain an encrypted power latent user identification model. The power potential user identification model may be a decision tree model with user power information or user virtual article information as input and a power potential user identification result as output. The power potential user identification model may be any type of decision tree model. The power potential user identification result can represent whether the target user corresponding to the user power information and the user virtual object information is the power potential user or not. The user power information may be information on power corresponding to the target user. The above-mentioned user power information may include, but is not limited to, at least one of a user number, a user electricity meter number, a user electricity date, a user daily electricity amount, a user monthly electricity amount, and a user annual electricity amount. The user number may be an identification that uniquely characterizes the target user. For example, the user number may be a mobile phone number of the target user. The user meter number may be a serial number that uniquely characterizes the target user meter. For example, the user meter number may be 1002654785. The user virtual item information may be information about a virtual item value (e.g., finance) corresponding to the target user. The user virtual item information may include, but is not limited to, at least one of: user number, number of virtual items (e.g., number of credit cards), number of monthly payments, number of annual payments, total monthly payments, and total annual payments.

In some alternative implementations of some embodiments, the power potential user identification model is generated by training in the following manner:

the first step is to send the initial power potential subscriber identity model to the power data service node, so that the power data service node performs model training on the initial power potential subscriber identity model through a pre-training power data set. The power data service node may be a server node that performs model training on the initial power potential user identification model using a pre-training power data set. The pre-trained power data set may be a power data set that pre-trains an initial power potential user identification model.

And a second step of transmitting the initial electric potential user identification model to the virtual article data service node, so that the virtual article data service node performs model training on the initial electric potential user identification model through a pre-training virtual article data set. The pre-training virtual article data in the pre-training virtual article data set corresponds to the pre-training power data in the pre-training power data set. The virtual item data service node may be a server node that model trains an initial power potential user identification model using a pre-trained virtual item data set. The pre-trained virtual item data set may be a virtual item data set pre-trained on an initial power potential user identification model.

Third, in response to receiving a real result set of the pre-training power data corresponding to the pre-training power data set sent by the power data service node, the following steps are executed:

and a first training step of generating an updated prediction result according to the power data prediction result and the virtual article data prediction result after model training, which are transmitted by the power data service node, in response to the power data prediction result after model training and the virtual article data prediction result after model training, which are transmitted by the virtual article data service node. The real result of the pretraining power data in the real result set of pretraining power data corresponds to pretraining virtual article data in the pretraining virtual article data set. The pre-training power data real result set may be each tag corresponding to the pre-training virtual article data set. The power data prediction result may include: prediction probability and prediction result. The virtual article data prediction result may include: prediction probability and prediction result. The above predictions may characterize whether the target consumer is a potential power consumer. The prediction probability may be a probability corresponding to a prediction result. I.e. the probability that the target consumer is a potential power consumer. In practice, the execution subject may determine, as the update prediction probability, a mean value of the prediction probabilities included in the power data prediction result and the prediction probability included in the virtual article data prediction result. The updated prediction probability may then be combined with the prediction result to obtain an updated prediction result.

And a second training step of comparing the updated prediction result with the real pre-training power data result set corresponding to the updated prediction result. Here, the comparison may be whether the prediction result included for updating the prediction result is identical to the real result of the pre-training power data.

And a third training step, determining whether the initial power potential user identification model reaches a preset optimization target according to the comparison result. And the optimization target is that the loss function value corresponding to the initial power potential user identification model is smaller than or equal to a preset loss threshold value. Here, the preset loss threshold may be a preset threshold. For example, the preset loss threshold may be 0.1.

And a fourth training step of determining the initial power potential subscriber identity model as a trained power potential subscriber identity model in response to determining that the initial power potential subscriber identity model meets the optimization objective.

Optionally, the above execution body may further execute the following steps:

and a fifth training step of, in response to determining that the initial power potential user recognition model does not reach the above-mentioned optimization target, adjusting the weight parameters of the initial power potential user recognition model, and transmitting the adjusted weight parameters to the power data service node and the virtual article data service node, respectively, so that the power data service node updates the weight parameters of the initial power potential user recognition model corresponding to the power data service node, uses unused pre-training power data to form a pre-training power data set, uses the initial power potential user recognition model updated by the weight parameters as the initial power potential user recognition model, performs model training again and transmits the power data prediction result after model training again, so that the virtual article data service node updates the weight parameters of the initial power potential user recognition model corresponding to the virtual article data service node, uses the unused pre-training virtual article data to form the pre-training virtual article data set, uses the initial power potential user recognition model updated by the weight parameters as the initial power potential user recognition model, and performs model training again and transmits the virtual article data prediction result after model training again. As an example, the network parameters of the initial power potential user identification model described above may be adjusted using a back propagation algorithm (Back Propagation Algorithm, BP algorithm) and a gradient descent method (e.g., a small batch gradient descent algorithm).

In some optional implementations of some embodiments, the executing entity may encrypt the pre-trained power latent subscriber identification model by:

first, generating a model public key according to a preset encryption function. The preset encryption function may be a preset symmetric encryption function. The preset encryption function may include, but is not limited to, at least one of: DES (Data Encryption Standard ), AES (Advanced Encryption Standard, advanced data encryption standard), triple data encryption algorithm (TDEA, triple Data Encryption Algorithm). In practice, the execution body may generate the model public key using DES encryption algorithm.

And secondly, encrypting the pre-trained electric potential user identification model by using the model public key to obtain the encrypted electric potential user identification model.

And thirdly, respectively transmitting the generated model public keys to the power data service node and the virtual article data service node, so that the power data service node decrypts the encrypted power potential user identification model by using the model public keys, and the virtual article data service node decrypts the encrypted power potential user identification model by using the model public keys. The power data service node may be a server node that processes the user power information using a power potential user identification model. The virtual good data service node may be a server node that processes user virtual good information using a power potential user identification model.

In some optional implementations of some embodiments, the set of target user power information is generated by:

and a first step of receiving the public key pair sent by the virtual article data service node. The public key pair is generated by the virtual article data service node according to a preset asymmetric encryption function. The preset asymmetric encryption function may be a preset asymmetric encryption function. The preset asymmetric encryption function may be any one of the following: RSA, elgamal, knapsack algorithm, rabin, D-H and ECC (elliptic curve cryptography). Wherein the public key pair may be (n, e). Where n is a public key. e is an encryption algorithm. The virtual article data service node stores an original target user virtual article information set. The original target user virtual article information set may be an unpreprocessed target user virtual article information set stored by the virtual article data service node. The power data service node stores an original target power information set of the user, and the original target power information set may be a target power information set stored in the power data service node and not subjected to preprocessing. The preprocessing may be data alignment processing of the original target user power information set stored in the power data service node and the original target user virtual article information set stored in the virtual article data service node.

Second, for each original target consumer power information in the original target consumer power information set, the following steps are performed:

and a first sub-step of generating a random number corresponding to the original target user power information according to a preset random generation function. The preset random generation function may be a preset function capable of generating a random number. In practice, the executing body may generate a random number corresponding to the original target user power information by using a preset random generation function.

And a second sub-step, carrying out encryption processing on the random number to obtain an encrypted random number. In practice, the executing body may encrypt the random number by using a public key to obtain an encrypted random number.

And a third sub-step of generating encrypted original target user power information according to the encrypted random number, a preset encryption function and the original target user power information. The encryption original target user power information representation carries out first encryption processing on the original target user power information. In practice, first, the executing body may encrypt the original target power information by using a preset encryption function to obtain first encrypted original target power information. Then, the product of the first encrypted original target power information and the encrypted random number may be determined as the encrypted original target power information. The preset encryption function may be a preset encryption function. Here, the encryption function may be preset As a hash function. The encrypted original target consumer power information may be expressed by the following formula:。

wherein, the aboveRepresenting an encrypted random number. Above->May represent encrypting the original target consumer power information. Above->The sequence number corresponding to the original target consumer power information may be represented. Above->The original target consumer power information may be represented. Above->A preset encryption function may be represented. Above->An encryption algorithm may be represented. Above->May represent a public key. Above->May represent a power data service node.

And thirdly, sending the generated encrypted original target user power information to a virtual article data service node, so that the virtual article data service node decrypts the received encrypted original target user power information by using a private key. The encrypted original target power information in the encrypted original target power information corresponds to the original target power information in the original target power information set one by one. The private key pair is generated by the virtual article data service node according to the preset asymmetric encryption function. Here, the private key pair may be (n, d). d represents a decryption algorithm.

And fourthly, responding to the received decrypted original target user power information sent by the virtual article data service node, and generating a decrypted original target user power information set according to the decrypted original target user power information, the preset encryption function and the encrypted random number set. Wherein, the decrypted original target consumer power information in the decrypted original target consumer power information set corresponds to the original target consumer power information in the original target consumer power information set one-to-one. The decrypted individual encrypted original target consumer power information may be expressed by the following formula:。

wherein,representing the encrypted original target consumer power information after decryption processing. />A sequence number corresponding to the encrypted original target consumer power information may be represented. />Representing the decrypted random number. />A preset encryption function may be represented. />Representing the preset encryption function after decryption processing.

Decrypting the original set of target consumer power information may be expressed by the following formula:。

wherein,representing decryption of the original target consumer power information. />The representation represents the encrypted original target customer power information after decryption processing, with the random number removed. / >And the encrypted original target user power information subjected to decryption processing for removing the influence of the random number is subjected to encryption processing again by using a preset encryption function.

And fifthly, responding to the received encrypted original target user virtual article information set sent by the virtual article data service node, and determining an encrypted target user identification information set according to the decrypted original target user power information set and the encrypted original target user virtual article information set. In practice, the executing entity may determine an intersection of the decrypted original target user power information set and the encrypted original target user virtual item information set as the encrypted target user identification information set. The encryption target user identification information in the encryption target user identification information set may be identification information uniquely representing the user. For example, the encryption target user identification information in the encryption target user identification information set may be a target user number (Key value).

And sixthly, determining a target user power information set according to the encrypted target user identification information set and the original target user power information set. In practice, the executing body may screen each original target subscriber power information corresponding to the encrypted target subscriber identification information set from the original target subscriber power information set as a target subscriber power information set.

And seventhly, transmitting the encrypted target user identification information set to the virtual article data service node, so that the virtual article data service node determines a target user virtual article information set according to the received encrypted target user identification information set and the original target user virtual article information set. Here, the manner of determining the target user virtual article information set is the same as the manner of determining the target user power information set described above.

The first to seventh steps and the related matters thereof described above are taken as an invention point of the embodiments of the present disclosure, and solve the second technical problem mentioned in the background art, that the security and privacy protection of the original target user power information and the original target user virtual article information data (the power data information party and the virtual article information party of the user do not share data with each other) are not considered when determining the power user information to be identified. The security of the power consumer information is low because data leakage of the power data information and the virtual article information of the consumer is easily caused when the power consumer object to be identified is determined. The factors that lead to data leakage of the power data information and the virtual article information of the user and the security of the power user information are low are often as follows: the security and privacy protection of the original target consumer power information and the original target consumer virtual item information data (the consumer's power data information party and virtual item information party do not share data with each other) is not considered in determining the power consumer information to be identified. The method has the advantages that when the power user object to be identified is determined, data leakage of the power data information and the virtual object information of the user is easy to occur, and the safety of the power user information is low. To achieve this, first, a public key pair sent by the virtual article data service node is received. The public key pair is generated by the virtual article data service node according to a preset asymmetric encryption function. Thus, a public key pair can be obtained, which can be used for encrypting the original target user power information. Then, for each original target consumer power information in the set of original target consumer power information, the following steps are performed: and generating a random number corresponding to the original target user power information according to a preset random generation function. Thus, the random number can be obtained, so that the random number can be used for adding noise to the original target user power information and improving the safety of the original target user power information. And then, carrying out encryption processing on the random number to obtain an encrypted random number. And generating the encrypted original target user power information according to the encrypted random number, a preset encryption function and the original target user power information. The encryption original target user power information representation carries out first encryption processing on the original target user power information. Thus, the encrypted original target power information after the first encryption process can be obtained. And then, sending each generated encrypted original target user power information to a virtual article data service node, so that the virtual article data service node decrypts the received each encrypted original target user power information by using a private key, wherein the encrypted original target user power information in each encrypted original target user power information corresponds to the original target user power information in the original target user power information set. The private key pair is generated by the virtual article data service node according to the preset asymmetric encryption function. Thus, each generated encrypted original target user power information can be transmitted to the virtual article data service node, and can be used for decrypting each encrypted original target user power information. And secondly, responding to the received encrypted original target user power information after decryption sent by the virtual article data service node, and generating an encrypted original target user power information set according to the decrypted original target user power information, the preset encryption function and the encrypted random number set. The encrypted original target consumer power information in the encrypted original target consumer power information set corresponds to the original target consumer power information in the original target consumer power information set. Thus, the encrypted original target user power information set after the second encryption processing can be obtained. And then, in response to receiving the encrypted original target user virtual article information set sent by the virtual article data service node, determining an encrypted target user identification information set according to the decrypted original target user power information set and the encrypted original target user virtual article information set. Thus, by the two encryption processes, the encrypted target user identification information set characterizing the target user power information identification can be obtained. And then, determining the target user power information set according to the encrypted target user identification information set and the original target user power information set. Thus, a set of target customer power information corresponding to the power data service node can be determined. And finally, the encrypted target user identification information set is sent to the virtual article data service node, so that the virtual article data service node determines a target user virtual article information set according to the received encrypted target user identification information set and the original target user virtual article information set. Thus, the target user virtual article information set corresponding to the virtual article data service node can be obtained. And because the power data service node performs encryption processing on the original target user power information twice, the safety of the power user information can be improved. And the security of the power user information can be further improved because the noise random number is generated and bound with the original target power user information. So that the probability of data leakage can be reduced.

Step 102, the encrypted power potential user identification model is sent to the power data service node and the virtual article data service node respectively, so that the power data service node identifies each target user power information included in the target user power information set through the encrypted power potential user identification model, and the virtual article data service node identifies each target user virtual article information included in the target user virtual article information set through the encrypted power potential user identification model.

In some embodiments, the executing entity may send the encrypted power latent subscriber identification model to the power data service node and the virtual article data service node, so that the power data service node identifies each target user power information included in the target user power information set through the encrypted power latent subscriber identification model, and the virtual article data service node identifies each target user virtual article information included in the target user virtual article information set through the encrypted power latent subscriber identification model.

In practice, the executing body may send the encrypted power potential user identification model to the power data service node and the virtual article data service node, so that the power data service node identifies each target user power information included in the target user power information set through the encrypted power potential user identification model, and the virtual article data service node identifies each target user virtual article information included in the target user virtual article information set through the encrypted power potential user identification model.

And step 103, responding to the received power data service node, and generating a power data identification information set according to the power identification information and the power identification weight of each target user, wherein the power identification information of each target user corresponds to the power information of each target user and the power identification weight corresponds to the power data service node.

In some embodiments, in response to receiving the respective target customer power identification information corresponding to the respective identified target customer power information transmitted by the power data service node and the power identification weight corresponding to the power data service node, the executing entity may generate a power data identification information set according to the respective target customer power identification information and the power identification weight. The power identification weight corresponding to the power data service node is the accuracy of potential user identification obtained by the power potential user identification model through identification on a preset power information test data set. The preset power information test data set may be a preset power data set for testing the power potential user identification model. The target user power identification information may include: the user number and the user power identification accuracy rate can be the accuracy rate that the power data service node identifies the target user as the potential power user according to the target user power information.

In some optional implementations of some embodiments, the executing entity may generate the power data identification information set according to the respective target user power identification information and the power identification weight by:

first, for each of the above-described individual target consumer power identification information, the following steps are performed:

and a first sub-step of determining, as the target customer power identification accuracy, a product of the customer power identification accuracy included in the target customer power identification information and the power identification weight.

And a second sub-step of combining the target user power identification accuracy with the user number to generate power data identification information. Here, the combination may be splicing.

And a second step of determining each of the generated power data identification information as a power data identification information set.

Step 104, responding to the received virtual article identification information of each target user corresponding to the identified virtual article information of each target user sent by the virtual article data service node and the virtual article identification weight corresponding to the virtual article data service node, and generating a virtual article data identification information set according to the virtual article identification information of each target user and the virtual article identification weight.

In some embodiments, in response to receiving the virtual article identification information of each target user corresponding to the virtual article information of each target user and the virtual article identification weight corresponding to the virtual article data service node, the executing entity may generate the virtual article data identification information set according to the virtual article identification information of each target user and the virtual article identification weight. The virtual article identification weight corresponding to the virtual article data service node is the accuracy of potential user identification obtained by the electric potential user identification model through identification on a preset virtual article information test data set, and the virtual article data identification information in the virtual article data identification information set corresponds to the electric power data identification information in the electric power data identification information set. The preset virtual article information test data set may be a preset virtual article information data set for testing the electric potential user identification model. The target user virtual article identification information may include: the user number and the user virtual article identification accuracy are the accuracy of the virtual article data service node for identifying the target user as the potential power user according to the target user virtual article information.

In some optional implementations of some embodiments, the executing entity may generate the virtual article data identification information set according to the respective target user virtual article identification information and the virtual article identification weight by:

the first step, for each target user virtual article identification information in the above-mentioned each target user virtual article identification information, performs the following steps:

and a first sub-step of determining the product of the user virtual article identification accuracy included in the target user virtual article identification information and the virtual article identification weight as the target user virtual article identification accuracy.

And a second sub-step of combining the target user virtual article identification accuracy with the user number to generate virtual article data identification information. Here, the combination may be splicing.

And a second step of determining each generated virtual article data identification information as a virtual article data identification information set.

Step 105, generating a power potential user identification information set according to the power data identification information set and the virtual article data identification information set.

In some embodiments, the executing entity may generate the set of power potential user identification information based on the set of power data identification information and the set of virtual item data identification information.

In some optional implementations of some embodiments, the executing entity may generate the set of power potential user identification information according to the set of power data identification information and the set of virtual item data identification information by:

first, for each piece of power data identification information in the power data identification information set, combining the power data identification information with virtual article data identification information corresponding to the power data identification information in the virtual article data identification information set to generate power potential user identification information to be determined. In practice, for each of the power data identification information sets, the execution subject may determine, as the target user identification accuracy, a sum of a target user power identification accuracy included in the power data identification information and a target user virtual article identification accuracy included in the virtual article data identification information corresponding to the power data identification information in the virtual article data identification information set. The user number included in the power data identification information and the target user identification accuracy may then be combined to generate the power potential user identification information to be determined.

And secondly, determining each piece of to-be-determined power potential user identification information meeting preset potential user identification conditions in the generated to-be-determined power potential user identification information as a power potential user identification information set. The preset potential user identification condition may be that the target user identification accuracy included in the electric power potential user identification information to be determined is greater than or equal to a preset accuracy threshold. The preset accuracy threshold may be a preset accuracy threshold. Here, the preset accuracy threshold may be 0.95.

Step 106, storing the set of power potential user identification information into a cache.

In some embodiments, the executing entity may store the set of power potential subscriber identification information into a cache. The cache may be a memory included in the execution body. In practice, the executing entity may store the set of power potential subscriber identification information into a cache.

The above embodiments of the present disclosure have the following advantageous effects: by the user identification information storage method of some embodiments of the present disclosure, accuracy of model identification of potential power user information can be improved, and identification of erroneous redundant potential power user information can be reduced, so that occupied cache resources are reduced, and waste of cache resources is caused. Specifically, the accuracy of the potential power consumer information of the model identification is lower, so that the redundant potential power consumer information of the identification error is more, the occupied cache resources are more, and the waste of the cache resources is caused by the following reasons: the multi-terminal multi-dimensional data is not adopted to carry out potential power user identification at the same time, and corresponding weights are given according to the contribution degrees of the multi-terminal multi-dimensional data, so that the integrity of user information is low, the accuracy of the potential power user information identified by the model is low, and therefore, the redundant potential power user information with wrong identification is more, occupied cache resources are more, and the waste of the cache resources is caused. Based on this, the user identification information storage method of some embodiments of the present disclosure first performs encryption processing on a pre-trained power potential user identification model to obtain an encrypted power potential user identification model. Therefore, the encrypted power potential user identification model can be obtained, and can be used for carrying out power potential user identification and improving the safety of an identification result. And then, the encrypted power potential user identification models are respectively sent to the power data service node and the virtual article data service node, so that the power data service node identifies all target user power information included in the target user power information set through the encrypted power potential user identification models, and the virtual article data service node identifies all target user virtual article information included in the target user virtual article information set through the encrypted power potential user identification models. Therefore, the power data of the power data service node and the virtual article data of the virtual article data service node can be utilized, namely, the data with two dimensions at two ends are adopted to simultaneously carry out potential power user identification, so that the generation of the data island problem can be avoided, and the integrity of user information can be improved. And then, responding to receiving the power identification information of each target user corresponding to the identified power information of each target user sent by the power data service node and the power identification weight corresponding to the power data service node, and generating a power data identification information set according to the power identification information of each target user and the power identification weight, wherein the power identification weight corresponding to the power data service node is the accuracy of potential user identification obtained by the power potential user identification model on a preset power information test data set. Therefore, the recognition result of the model recognition by the power data service node can be obtained, and the accuracy of the potential user recognition obtained by recognition on the preset power information test data set is used as the contribution weight of the model recognition by the power data service node, so that the accuracy of the recognized potential power user can be improved. And secondly, responding to receiving the virtual article identification information of each target user corresponding to the virtual article information of each target user and the virtual article identification weight corresponding to the virtual article data service node, and generating a virtual article data identification information set according to the virtual article identification information of each target user and the virtual article identification weight, wherein the virtual article identification weight corresponding to the virtual article data service node is the accuracy of potential user identification obtained by the potential user identification model on a preset virtual article information test data set, and the virtual article data identification information in the virtual article data identification information set corresponds to the electric power data identification information in the electric power data identification information set. Therefore, the recognition result of the model recognition by the virtual article data service node can be obtained, and the accuracy of the potential user recognition obtained by recognizing the preset electric power information test on the preset virtual article information test data set is used as the contribution weight of the model recognition by the virtual article data service node, so that the accuracy of the recognized potential electric power user can be improved. And then, generating a power potential user identification information set according to the power data identification information set and the virtual article data identification information set. Therefore, the potential power user information can be obtained according to the accuracy rate and the corresponding contribution weight of the prediction of the two ends of the power data service node and the virtual article data service node. Finally, the set of power potential subscriber identification information is stored in a cache. Therefore, the power potential user identification information set with high identification accuracy can be stored in the cache, and the method can be used for improving the hit rate of the user on the potential power user information access. And the pre-trained electric potential user identification model is sent to the electric data service node and two ends of the virtual article data service node for identification, so that the generation of data islands can be avoided, and the integrity of user information for identification can be improved. And the contribution weights of the two ends are determined according to the accuracy of the prediction of the models of the two ends, so that the accuracy of the identified potential power user information can be improved, the redundant potential power user information with errors is reduced, occupied cache resources are further reduced, and the waste of the cache resources is reduced.

With further reference to fig. 2, as an implementation of the method shown in the above figures, the present disclosure provides some embodiments of a user identification information storage device, corresponding to those method embodiments shown in fig. 1, which may be applied in particular in various electronic apparatuses.

As shown in fig. 2, the user identification information storage device 200 of some embodiments includes: an encryption unit 201, a transmission unit 202, a first generation unit 203, a second generation unit 204, a third generation unit 205, and a storage unit 206. The encryption unit 201 is configured to encrypt the pre-trained power potential user identification model to obtain an encrypted power potential user identification model; the transmitting unit 202 is configured to transmit the above-mentioned encrypted power potential user identification model to the power data service node and the virtual article data service node, respectively, so that the power data service node identifies each target user power information included in the target user power information set through the encrypted power potential user identification model, and so that the virtual article data service node identifies each target user virtual article information included in the target user virtual article information set through the encrypted power potential user identification model; the first generating unit 203 is configured to generate a power data identification information set according to the respective target user power identification information and the power identification weights corresponding to the power data service nodes in response to receiving the respective target user power identification information corresponding to the identified respective target user power information sent by the power data service nodes and the power identification weights corresponding to the power data service nodes, where the power identification weights corresponding to the power data service nodes are the accuracy of the potential user identification obtained by the potential user identification model by identifying on a preset power information test data set; the second generating unit 204 is configured to generate a virtual article data identification information set according to each target user virtual article identification information and the virtual article identification weight corresponding to the virtual article data service node in response to receiving each target user virtual article identification information corresponding to each target user virtual article information identified by the virtual article data service node and the virtual article identification weight corresponding to the virtual article data service node, where the virtual article identification weight corresponding to the virtual article data service node is an accuracy rate of potential user identification obtained by the electric potential user identification model identifying on a preset virtual article information test data set, and virtual article data identification information in the virtual article data identification information set corresponds to electric power data identification information in the electric power data identification information set; the third generating unit 205 is configured to generate a set of electric potential user identification information from the set of electric power data identification information and the set of virtual article data identification information; the storage unit 206 is configured to store the set of power potential user identification information into a cache.

It will be appreciated that the elements described in the user identification information storage device 200 correspond to the various steps in the method described with reference to fig. 1. Thus, the operations, features and advantages described above with respect to the method are equally applicable to the user identification information storage device 200 and the units contained therein, and are not described herein.

Referring now to fig. 3, a schematic diagram of an electronic device 300 (e.g., a computing device) suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device shown in fig. 3 is merely an example and should not impose any limitations on the functionality and scope of use of embodiments of the present disclosure.

As shown in fig. 3, the electronic device 300 may include a processing means 301 (e.g., a central processing unit, a graphics processor, etc.) that may perform various suitable actions and processes in accordance with a program stored in a Read Only Memory (ROM) 302 or a program loaded from a storage means 308 into a Random Access Memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic apparatus 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input/output (I/O) interface 305 is also connected to bus 304.

In general, the following devices may be connected to the I/O interface 305: input devices 306 including, for example, a touch screen, touchpad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; an output device 307 including, for example, a Liquid Crystal Display (LCD), a speaker, a vibrator, and the like; storage 308 including, for example, magnetic tape, hard disk, etc.; and communication means 309. The communication means 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. While fig. 3 shows an electronic device 300 having various means, it is to be understood that not all of the illustrated means are required to be implemented or provided. More or fewer devices may be implemented or provided instead. Each block shown in fig. 3 may represent one device or a plurality of devices as needed.

In particular, according to some embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such embodiments, the computer program may be downloaded and installed from a network via communications device 309, or from storage device 308, or from ROM 302. The above-described functions defined in the methods of some embodiments of the present disclosure are performed when the computer program is executed by the processing means 301.

It should be noted that, the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, the computer-readable signal medium may comprise a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection 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: electrical wires, fiber optic cables, RF (radio frequency), and the like, or any suitable combination of the foregoing.

In some implementations, the clients, servers may communicate using any currently known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol ), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the internet (e.g., the internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

The computer readable medium may be contained in the electronic device; or may exist alone without being incorporated into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: encrypting the pre-trained electric potential user identification model to obtain an encrypted electric potential user identification model; the encrypted power potential user identification models are respectively sent to a power data service node and a virtual article data service node, so that the power data service node identifies all target user power information included in a target user power information set through the encrypted power potential user identification models, and the virtual article data service node identifies all target user virtual article information included in the target user virtual article information set through the encrypted power potential user identification models; responding to receiving the identification information of each target user corresponding to the identified power information of each target user sent by the power data service node and the identification weight of the power corresponding to the power data service node, and generating a power data identification information set according to the identification information of each target user and the identification weight of the power, wherein the identification weight of the power corresponding to the power data service node is the accuracy of potential user identification obtained by the identification of the potential user identification model on a preset power information test data set; responding to receiving each piece of target user virtual article identification information corresponding to each piece of target user virtual article information identified by the virtual article data service node and a virtual article identification weight corresponding to the virtual article data service node, and generating a virtual article data identification information set according to each piece of target user virtual article identification information and the virtual article identification weight, wherein the virtual article identification weight corresponding to the virtual article data service node is the accuracy of potential user identification obtained by the electric potential user identification model in a preset virtual article information test data set, and the virtual article data identification information in the virtual article data identification information set corresponds to electric power data identification information in the electric power data identification information set; generating a power potential user identification information set according to the power data identification information set and the virtual article data identification information set; the set of power potential subscriber identification information is stored in a cache.

Computer program code for carrying out operations for some embodiments of the present disclosure may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts 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 disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). 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 the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in some embodiments of the present disclosure may be implemented by means of software, or may be implemented by means of hardware. The described units may also be provided in a processor, for example, described as: a processor includes an encryption unit, a transmission unit, a first generation unit, a second generation unit, a third generation unit, and a storage unit. The names of these units do not in some way limit the unit itself, and for example, the storage unit may also be described as "a unit that stores the set of power potential user identification information into a cache" as described above.

The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: the above description of Field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems on a chip (SOCs), complex Programmable Logic Devices (CPLDs), etc. are merely illustrative of some of the preferred embodiments of the present disclosure and the technical principles employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above technical features, but encompasses other technical features formed by any combination of the above technical features or their equivalents without departing from the spirit of the invention. Such as the above-described features, are mutually substituted with (but not limited to) the features having similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A user identification information storage method, comprising:

encrypting the pre-trained electric potential user identification model to obtain an encrypted electric potential user identification model;

the encrypted power potential user identification models are respectively sent to a power data service node and a virtual article data service node, so that the power data service node identifies all target user power information included in a target user power information set through the encrypted power potential user identification models, and the virtual article data service node identifies all target user virtual article information included in the target user virtual article information set through the encrypted power potential user identification models;

responding to receiving each piece of target user power identification information corresponding to each piece of identified target user power information sent by the power data service node and a power identification weight corresponding to the power data service node, and generating a power data identification information set according to each piece of target user power identification information and the power identification weight, wherein the power identification weight corresponding to the power data service node is the accuracy of potential user identification obtained by the power potential user identification model through identification on a preset power information test data set;

Responding to receiving virtual article identification information of each target user corresponding to virtual article information of each target user and virtual article identification weight corresponding to the virtual article data service node, which are sent by the virtual article data service node, and generating a virtual article data identification information set according to the virtual article identification information of each target user and the virtual article identification weight, wherein the virtual article identification weight corresponding to the virtual article data service node is the accuracy of potential user identification obtained by the electric potential user identification model on a preset virtual article information test data set, and the virtual article data identification information in the virtual article data identification information set corresponds to electric data identification information in the electric data identification information set;

generating a power potential user identification information set according to the power data identification information set and the virtual article data identification information set;

the set of power potential subscriber identification information is stored into a cache.

2. The method of claim 1, wherein the encrypting the pre-trained power latent subscriber identification model to obtain an encrypted power latent subscriber identification model comprises:

Generating a model public key according to a preset encryption function;

encrypting the pre-trained electric potential user identification model by using the model public key to obtain an encrypted electric potential user identification model;

and respectively sending the generated model public keys to the electric power data service node and the virtual article data service node, so that the electric power data service node utilizes the model public keys to decrypt the encrypted electric power potential user identification model, and the virtual article data service node utilizes the model public keys to decrypt the encrypted electric power potential user identification model.

3. The method of claim 1, wherein the target consumer power identification information comprises: user numbering and user power identification accuracy; and

the generating a power data identification information set according to the power identification information of each target user and the power identification weight comprises the following steps:

for each of the respective target subscriber power identification information, performing the steps of:

determining the product of the user power identification accuracy rate included in the target user power identification information and the power identification weight as the target user power identification accuracy rate;

Combining the target user power identification accuracy with the user number to generate power data identification information;

each of the generated power data identification information is determined as a power data identification information set.

4. The method of claim 1, wherein the target user virtual article identification information comprises: user numbering and user virtual article identification accuracy; and

the generating a virtual article data identification information set according to the virtual article identification information of each target user and the virtual article identification weight comprises the following steps:

for each of the respective target user virtual article identification information, performing the steps of:

determining the product of the user virtual article identification accuracy rate included in the target user virtual article identification information and the virtual article identification weight as target user virtual article identification accuracy rate;

combining the target user virtual article identification accuracy with the user number to generate virtual article data identification information;

each of the generated virtual article data identification information is determined as a virtual article data identification information set.

5. The method of claim 1, wherein the generating a set of power potential user identification information from the set of power data identification information and the set of virtual item data identification information comprises:

combining, for each piece of power data identification information in the set of power data identification information, the piece of power data identification information with a piece of virtual item data identification information in the set of virtual item data identification information that corresponds to the piece of power data identification information to generate power potential user identification information to be determined;

and determining each piece of to-be-determined power potential user identification information meeting preset potential user identification conditions in the generated each piece of to-be-determined power potential user identification information as a power potential user identification information set.

6. The method of claim 1, wherein the power potential user identification model is generated by training:

transmitting the initial power potential user identification model to the power data service node, so that the power data service node performs model training on the initial power potential user identification model through a pre-training power data set;

Transmitting the initial power potential user identification model to the virtual article data service node, so that the virtual article data service node performs model training on the initial power potential user identification model through a pre-training virtual article data set, wherein pre-training virtual article data in the pre-training virtual article data set corresponds to pre-training power data in the pre-training power data set;

in response to receiving a real pre-training power data result set corresponding to the pre-training power data set sent by the power data service node, the following steps are executed:

responding to the received power data prediction result after model training sent by the power data service node and the virtual article data prediction result after model training sent by the virtual article data service node, and generating an updated prediction result according to the power data prediction result and the virtual article data prediction result, wherein the pre-training power data real result in the pre-training power data real result set corresponds to the pre-training virtual article data in the pre-training virtual article data set;

comparing the updated prediction result with the pre-training power data real result corresponding to the updated prediction result in the pre-training power data real result set;

Determining whether the initial power potential user identification model reaches a preset optimization target according to a comparison result, wherein the optimization target is that a loss function value corresponding to the initial power potential user identification model is smaller than or equal to a preset loss threshold value;

in response to determining that the initial power potential subscriber identification model meets the optimization objective, the initial power potential subscriber identification model is determined as a trained power potential subscriber identification model.

7. The method of claim 6, wherein the method further comprises:

and in response to determining that the initial power potential user identification model does not reach the optimization target, adjusting weight parameters of the initial power potential user identification model, and respectively transmitting the adjusted weight parameters to a power data service node and a virtual article data service node, so that the power data service node updates the weight parameters of the initial power potential user identification model corresponding to the power data service node, uses unused pre-training power data to form a pre-training power data set, uses the initial power potential user identification model with updated weight parameters as the initial power potential user identification model, performs model training again and transmits a power data prediction result after model training again, so that the virtual article data service node updates the weight parameters of the initial power potential user identification model corresponding to the virtual article data service node, uses the initial power potential user identification model with updated weight parameters as the initial power potential user identification model, performs model training again, and transmits a virtual article data prediction result after model training again.

8. A power potential user identification information storage device, comprising:

the encryption unit is configured to encrypt the pre-trained power potential user identification model to obtain an encrypted power potential user identification model;

the transmission unit is configured to transmit the encrypted power potential user identification models to the power data service node and the virtual article data service node respectively, so that the power data service node identifies all target user power information included in the target user power information set through the encrypted power potential user identification models, and the virtual article data service node identifies all target user virtual article information included in the target user virtual article information set through the encrypted power potential user identification models;

a first generation unit configured to generate a power data identification information set according to each target user power identification information and the power identification weight corresponding to the power data service node in response to receiving each target user power identification information corresponding to each identified target user power information sent by the power data service node and the power identification weight corresponding to the power data service node, wherein the power identification weight corresponding to the power data service node is the accuracy of potential user identification obtained by the power potential user identification model through identification on a preset power information test data set;

A second generating unit, configured to respond to receiving each piece of target user virtual article identification information corresponding to each piece of identified target user virtual article information sent by the virtual article data service node and a virtual article identification weight corresponding to the virtual article data service node, and generate a virtual article data identification information set according to each piece of target user virtual article identification information and the virtual article identification weight, wherein the virtual article identification weight corresponding to the virtual article data service node is the accuracy of potential user identification obtained by the electric potential user identification model in a preset virtual article information test data set, and virtual article data identification information in the virtual article data identification information set corresponds to electric power data identification information in the electric power data identification information set;

a third generation unit configured to generate a set of power potential user identification information from the set of power data identification information and the set of virtual article data identification information;

a storage unit configured to store the set of power potential subscriber identification information into a cache.

9. An electronic device, comprising:

one or more processors;

a storage device having one or more programs stored thereon,

when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-7.

10. A computer readable medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any of claims 1-7.